vllm-cpu-avx512bf16 0.14.0__cp313-cp313-manylinux_2_28_x86_64.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (1712) hide show
  1. vllm/_C.abi3.so +0 -0
  2. vllm/__init__.py +225 -0
  3. vllm/_aiter_ops.py +1511 -0
  4. vllm/_bc_linter.py +54 -0
  5. vllm/_custom_ops.py +3206 -0
  6. vllm/_ipex_ops.py +445 -0
  7. vllm/_version.py +34 -0
  8. vllm/assets/__init__.py +0 -0
  9. vllm/assets/audio.py +43 -0
  10. vllm/assets/base.py +40 -0
  11. vllm/assets/image.py +62 -0
  12. vllm/assets/video.py +149 -0
  13. vllm/attention/__init__.py +0 -0
  14. vllm/attention/layer.py +913 -0
  15. vllm/attention/utils/__init__.py +0 -0
  16. vllm/attention/utils/kv_sharing_utils.py +33 -0
  17. vllm/attention/utils/kv_transfer_utils.py +60 -0
  18. vllm/beam_search.py +88 -0
  19. vllm/benchmarks/__init__.py +0 -0
  20. vllm/benchmarks/datasets.py +3277 -0
  21. vllm/benchmarks/latency.py +172 -0
  22. vllm/benchmarks/lib/__init__.py +3 -0
  23. vllm/benchmarks/lib/endpoint_request_func.py +777 -0
  24. vllm/benchmarks/lib/ready_checker.py +72 -0
  25. vllm/benchmarks/lib/utils.py +79 -0
  26. vllm/benchmarks/mm_processor.py +363 -0
  27. vllm/benchmarks/serve.py +1761 -0
  28. vllm/benchmarks/startup.py +321 -0
  29. vllm/benchmarks/sweep/__init__.py +0 -0
  30. vllm/benchmarks/sweep/cli.py +41 -0
  31. vllm/benchmarks/sweep/param_sweep.py +159 -0
  32. vllm/benchmarks/sweep/plot.py +675 -0
  33. vllm/benchmarks/sweep/plot_pareto.py +393 -0
  34. vllm/benchmarks/sweep/serve.py +450 -0
  35. vllm/benchmarks/sweep/serve_sla.py +459 -0
  36. vllm/benchmarks/sweep/server.py +114 -0
  37. vllm/benchmarks/sweep/sla_sweep.py +138 -0
  38. vllm/benchmarks/sweep/utils.py +4 -0
  39. vllm/benchmarks/throughput.py +946 -0
  40. vllm/collect_env.py +857 -0
  41. vllm/compilation/__init__.py +0 -0
  42. vllm/compilation/activation_quant_fusion.py +214 -0
  43. vllm/compilation/backends.py +840 -0
  44. vllm/compilation/base_static_graph.py +57 -0
  45. vllm/compilation/caching.py +196 -0
  46. vllm/compilation/collective_fusion.py +1224 -0
  47. vllm/compilation/compiler_interface.py +639 -0
  48. vllm/compilation/counter.py +50 -0
  49. vllm/compilation/cuda_graph.py +309 -0
  50. vllm/compilation/decorators.py +662 -0
  51. vllm/compilation/fix_functionalization.py +266 -0
  52. vllm/compilation/fusion.py +570 -0
  53. vllm/compilation/fusion_attn.py +363 -0
  54. vllm/compilation/fx_utils.py +92 -0
  55. vllm/compilation/inductor_pass.py +145 -0
  56. vllm/compilation/matcher_utils.py +454 -0
  57. vllm/compilation/monitor.py +62 -0
  58. vllm/compilation/noop_elimination.py +130 -0
  59. vllm/compilation/partition_rules.py +75 -0
  60. vllm/compilation/pass_manager.py +164 -0
  61. vllm/compilation/piecewise_backend.py +191 -0
  62. vllm/compilation/post_cleanup.py +21 -0
  63. vllm/compilation/qk_norm_rope_fusion.py +244 -0
  64. vllm/compilation/rocm_aiter_fusion.py +401 -0
  65. vllm/compilation/sequence_parallelism.py +368 -0
  66. vllm/compilation/torch25_custom_graph_pass.py +44 -0
  67. vllm/compilation/vllm_inductor_pass.py +180 -0
  68. vllm/compilation/wrapper.py +329 -0
  69. vllm/config/__init__.py +112 -0
  70. vllm/config/attention.py +114 -0
  71. vllm/config/cache.py +233 -0
  72. vllm/config/compilation.py +1149 -0
  73. vllm/config/device.py +75 -0
  74. vllm/config/ec_transfer.py +110 -0
  75. vllm/config/kv_events.py +56 -0
  76. vllm/config/kv_transfer.py +119 -0
  77. vllm/config/load.py +124 -0
  78. vllm/config/lora.py +102 -0
  79. vllm/config/model.py +2026 -0
  80. vllm/config/model_arch.py +57 -0
  81. vllm/config/multimodal.py +247 -0
  82. vllm/config/observability.py +157 -0
  83. vllm/config/parallel.py +703 -0
  84. vllm/config/pooler.py +188 -0
  85. vllm/config/profiler.py +199 -0
  86. vllm/config/scheduler.py +298 -0
  87. vllm/config/speculative.py +656 -0
  88. vllm/config/speech_to_text.py +39 -0
  89. vllm/config/structured_outputs.py +78 -0
  90. vllm/config/utils.py +374 -0
  91. vllm/config/vllm.py +1487 -0
  92. vllm/connections.py +189 -0
  93. vllm/device_allocator/__init__.py +0 -0
  94. vllm/device_allocator/cumem.py +301 -0
  95. vllm/distributed/__init__.py +6 -0
  96. vllm/distributed/communication_op.py +43 -0
  97. vllm/distributed/device_communicators/__init__.py +0 -0
  98. vllm/distributed/device_communicators/all2all.py +509 -0
  99. vllm/distributed/device_communicators/all_reduce_utils.py +344 -0
  100. vllm/distributed/device_communicators/base_device_communicator.py +303 -0
  101. vllm/distributed/device_communicators/cpu_communicator.py +209 -0
  102. vllm/distributed/device_communicators/cuda_communicator.py +346 -0
  103. vllm/distributed/device_communicators/cuda_wrapper.py +190 -0
  104. vllm/distributed/device_communicators/custom_all_reduce.py +326 -0
  105. vllm/distributed/device_communicators/mnnvl_compat.py +27 -0
  106. vllm/distributed/device_communicators/pynccl.py +386 -0
  107. vllm/distributed/device_communicators/pynccl_allocator.py +191 -0
  108. vllm/distributed/device_communicators/pynccl_wrapper.py +567 -0
  109. vllm/distributed/device_communicators/quick_all_reduce.py +290 -0
  110. vllm/distributed/device_communicators/ray_communicator.py +259 -0
  111. vllm/distributed/device_communicators/shm_broadcast.py +778 -0
  112. vllm/distributed/device_communicators/shm_object_storage.py +697 -0
  113. vllm/distributed/device_communicators/symm_mem.py +156 -0
  114. vllm/distributed/device_communicators/xpu_communicator.py +98 -0
  115. vllm/distributed/ec_transfer/__init__.py +14 -0
  116. vllm/distributed/ec_transfer/ec_connector/__init__.py +0 -0
  117. vllm/distributed/ec_transfer/ec_connector/base.py +247 -0
  118. vllm/distributed/ec_transfer/ec_connector/example_connector.py +201 -0
  119. vllm/distributed/ec_transfer/ec_connector/factory.py +85 -0
  120. vllm/distributed/ec_transfer/ec_transfer_state.py +42 -0
  121. vllm/distributed/eplb/__init__.py +3 -0
  122. vllm/distributed/eplb/async_worker.py +115 -0
  123. vllm/distributed/eplb/eplb_state.py +1192 -0
  124. vllm/distributed/eplb/policy/__init__.py +19 -0
  125. vllm/distributed/eplb/policy/abstract.py +43 -0
  126. vllm/distributed/eplb/policy/default.py +376 -0
  127. vllm/distributed/eplb/rebalance_execute.py +699 -0
  128. vllm/distributed/kv_events.py +505 -0
  129. vllm/distributed/kv_transfer/README.md +29 -0
  130. vllm/distributed/kv_transfer/__init__.py +20 -0
  131. vllm/distributed/kv_transfer/disagg_prefill_workflow.jpg +0 -0
  132. vllm/distributed/kv_transfer/kv_connector/__init__.py +0 -0
  133. vllm/distributed/kv_transfer/kv_connector/base.py +10 -0
  134. vllm/distributed/kv_transfer/kv_connector/factory.py +203 -0
  135. vllm/distributed/kv_transfer/kv_connector/utils.py +459 -0
  136. vllm/distributed/kv_transfer/kv_connector/v1/__init__.py +19 -0
  137. vllm/distributed/kv_transfer/kv_connector/v1/base.py +607 -0
  138. vllm/distributed/kv_transfer/kv_connector/v1/decode_bench_connector.py +419 -0
  139. vllm/distributed/kv_transfer/kv_connector/v1/example_connector.py +450 -0
  140. vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py +344 -0
  141. vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/__init__.py +18 -0
  142. vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/multi_process_adapter.py +395 -0
  143. vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/utils.py +211 -0
  144. vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/vllm_v1_adapter.py +1431 -0
  145. vllm/distributed/kv_transfer/kv_connector/v1/lmcache_mp_connector.py +941 -0
  146. vllm/distributed/kv_transfer/kv_connector/v1/metrics.py +186 -0
  147. vllm/distributed/kv_transfer/kv_connector/v1/mooncake_connector.py +916 -0
  148. vllm/distributed/kv_transfer/kv_connector/v1/moriio/__init__.py +0 -0
  149. vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_common.py +321 -0
  150. vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_connector.py +1515 -0
  151. vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_engine.py +609 -0
  152. vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py +477 -0
  153. vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py +2688 -0
  154. vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py +557 -0
  155. vllm/distributed/kv_transfer/kv_connector/v1/p2p/__init__.py +0 -0
  156. vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py +531 -0
  157. vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py +632 -0
  158. vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py +273 -0
  159. vllm/distributed/kv_transfer/kv_transfer_state.py +78 -0
  160. vllm/distributed/parallel_state.py +1809 -0
  161. vllm/distributed/utils.py +545 -0
  162. vllm/engine/__init__.py +0 -0
  163. vllm/engine/arg_utils.py +2137 -0
  164. vllm/engine/async_llm_engine.py +6 -0
  165. vllm/engine/llm_engine.py +6 -0
  166. vllm/engine/protocol.py +194 -0
  167. vllm/entrypoints/__init__.py +0 -0
  168. vllm/entrypoints/anthropic/__init__.py +0 -0
  169. vllm/entrypoints/anthropic/protocol.py +162 -0
  170. vllm/entrypoints/anthropic/serving_messages.py +468 -0
  171. vllm/entrypoints/api_server.py +186 -0
  172. vllm/entrypoints/chat_utils.py +1912 -0
  173. vllm/entrypoints/cli/__init__.py +19 -0
  174. vllm/entrypoints/cli/benchmark/__init__.py +0 -0
  175. vllm/entrypoints/cli/benchmark/base.py +25 -0
  176. vllm/entrypoints/cli/benchmark/latency.py +21 -0
  177. vllm/entrypoints/cli/benchmark/main.py +57 -0
  178. vllm/entrypoints/cli/benchmark/mm_processor.py +21 -0
  179. vllm/entrypoints/cli/benchmark/serve.py +21 -0
  180. vllm/entrypoints/cli/benchmark/startup.py +21 -0
  181. vllm/entrypoints/cli/benchmark/sweep.py +21 -0
  182. vllm/entrypoints/cli/benchmark/throughput.py +21 -0
  183. vllm/entrypoints/cli/collect_env.py +38 -0
  184. vllm/entrypoints/cli/main.py +79 -0
  185. vllm/entrypoints/cli/openai.py +260 -0
  186. vllm/entrypoints/cli/run_batch.py +68 -0
  187. vllm/entrypoints/cli/serve.py +253 -0
  188. vllm/entrypoints/cli/types.py +29 -0
  189. vllm/entrypoints/constants.py +12 -0
  190. vllm/entrypoints/context.py +898 -0
  191. vllm/entrypoints/grpc_server.py +531 -0
  192. vllm/entrypoints/launcher.py +175 -0
  193. vllm/entrypoints/llm.py +1807 -0
  194. vllm/entrypoints/logger.py +86 -0
  195. vllm/entrypoints/openai/__init__.py +0 -0
  196. vllm/entrypoints/openai/api_server.py +1390 -0
  197. vllm/entrypoints/openai/cli_args.py +320 -0
  198. vllm/entrypoints/openai/orca_metrics.py +120 -0
  199. vllm/entrypoints/openai/parser/__init__.py +0 -0
  200. vllm/entrypoints/openai/parser/harmony_utils.py +820 -0
  201. vllm/entrypoints/openai/parser/responses_parser.py +176 -0
  202. vllm/entrypoints/openai/protocol.py +2566 -0
  203. vllm/entrypoints/openai/run_batch.py +635 -0
  204. vllm/entrypoints/openai/serving_chat.py +1897 -0
  205. vllm/entrypoints/openai/serving_chat_stream_harmony.py +101 -0
  206. vllm/entrypoints/openai/serving_completion.py +740 -0
  207. vllm/entrypoints/openai/serving_engine.py +1612 -0
  208. vllm/entrypoints/openai/serving_models.py +309 -0
  209. vllm/entrypoints/openai/serving_responses.py +2552 -0
  210. vllm/entrypoints/openai/serving_transcription.py +168 -0
  211. vllm/entrypoints/openai/speech_to_text.py +711 -0
  212. vllm/entrypoints/openai/utils.py +49 -0
  213. vllm/entrypoints/pooling/__init__.py +16 -0
  214. vllm/entrypoints/pooling/classify/__init__.py +0 -0
  215. vllm/entrypoints/pooling/classify/api_router.py +48 -0
  216. vllm/entrypoints/pooling/classify/protocol.py +181 -0
  217. vllm/entrypoints/pooling/classify/serving.py +233 -0
  218. vllm/entrypoints/pooling/embed/__init__.py +0 -0
  219. vllm/entrypoints/pooling/embed/api_router.py +65 -0
  220. vllm/entrypoints/pooling/embed/conftest.py +28 -0
  221. vllm/entrypoints/pooling/embed/protocol.py +217 -0
  222. vllm/entrypoints/pooling/embed/serving.py +684 -0
  223. vllm/entrypoints/pooling/pooling/__init__.py +0 -0
  224. vllm/entrypoints/pooling/pooling/api_router.py +62 -0
  225. vllm/entrypoints/pooling/pooling/protocol.py +146 -0
  226. vllm/entrypoints/pooling/pooling/serving.py +354 -0
  227. vllm/entrypoints/pooling/score/__init__.py +0 -0
  228. vllm/entrypoints/pooling/score/api_router.py +147 -0
  229. vllm/entrypoints/pooling/score/protocol.py +146 -0
  230. vllm/entrypoints/pooling/score/serving.py +511 -0
  231. vllm/entrypoints/renderer.py +411 -0
  232. vllm/entrypoints/responses_utils.py +218 -0
  233. vllm/entrypoints/sagemaker/__init__.py +4 -0
  234. vllm/entrypoints/sagemaker/routes.py +118 -0
  235. vllm/entrypoints/score_utils.py +271 -0
  236. vllm/entrypoints/serve/__init__.py +94 -0
  237. vllm/entrypoints/serve/cache/__init__.py +0 -0
  238. vllm/entrypoints/serve/cache/api_router.py +61 -0
  239. vllm/entrypoints/serve/disagg/__init__.py +0 -0
  240. vllm/entrypoints/serve/disagg/api_router.py +109 -0
  241. vllm/entrypoints/serve/disagg/protocol.py +90 -0
  242. vllm/entrypoints/serve/disagg/serving.py +285 -0
  243. vllm/entrypoints/serve/elastic_ep/__init__.py +0 -0
  244. vllm/entrypoints/serve/elastic_ep/api_router.py +96 -0
  245. vllm/entrypoints/serve/elastic_ep/middleware.py +49 -0
  246. vllm/entrypoints/serve/instrumentator/__init__.py +0 -0
  247. vllm/entrypoints/serve/instrumentator/health.py +33 -0
  248. vllm/entrypoints/serve/instrumentator/metrics.py +45 -0
  249. vllm/entrypoints/serve/instrumentator/offline_docs.py +50 -0
  250. vllm/entrypoints/serve/instrumentator/server_info.py +56 -0
  251. vllm/entrypoints/serve/instrumentator/static/swagger-ui-bundle.js +2 -0
  252. vllm/entrypoints/serve/instrumentator/static/swagger-ui.css +3 -0
  253. vllm/entrypoints/serve/lora/__init__.py +0 -0
  254. vllm/entrypoints/serve/lora/api_router.py +70 -0
  255. vllm/entrypoints/serve/profile/__init__.py +0 -0
  256. vllm/entrypoints/serve/profile/api_router.py +46 -0
  257. vllm/entrypoints/serve/rlhf/__init__.py +0 -0
  258. vllm/entrypoints/serve/rlhf/api_router.py +102 -0
  259. vllm/entrypoints/serve/rpc/__init__.py +0 -0
  260. vllm/entrypoints/serve/rpc/api_router.py +61 -0
  261. vllm/entrypoints/serve/sleep/__init__.py +0 -0
  262. vllm/entrypoints/serve/sleep/api_router.py +56 -0
  263. vllm/entrypoints/serve/tokenize/__init__.py +0 -0
  264. vllm/entrypoints/serve/tokenize/api_router.py +112 -0
  265. vllm/entrypoints/serve/tokenize/serving.py +204 -0
  266. vllm/entrypoints/ssl.py +78 -0
  267. vllm/entrypoints/tool.py +187 -0
  268. vllm/entrypoints/tool_server.py +234 -0
  269. vllm/entrypoints/utils.py +336 -0
  270. vllm/env_override.py +402 -0
  271. vllm/envs.py +1791 -0
  272. vllm/exceptions.py +36 -0
  273. vllm/forward_context.py +375 -0
  274. vllm/grpc/__init__.py +17 -0
  275. vllm/grpc/compile_protos.py +94 -0
  276. vllm/grpc/vllm_engine.proto +195 -0
  277. vllm/grpc/vllm_engine_pb2.py +77 -0
  278. vllm/grpc/vllm_engine_pb2.pyi +213 -0
  279. vllm/grpc/vllm_engine_pb2_grpc.py +330 -0
  280. vllm/inputs/__init__.py +44 -0
  281. vllm/inputs/data.py +359 -0
  282. vllm/inputs/parse.py +147 -0
  283. vllm/inputs/preprocess.py +716 -0
  284. vllm/logger.py +303 -0
  285. vllm/logging_utils/__init__.py +13 -0
  286. vllm/logging_utils/dump_input.py +83 -0
  287. vllm/logging_utils/formatter.py +127 -0
  288. vllm/logging_utils/lazy.py +20 -0
  289. vllm/logging_utils/log_time.py +34 -0
  290. vllm/logits_process.py +121 -0
  291. vllm/logprobs.py +206 -0
  292. vllm/lora/__init__.py +0 -0
  293. vllm/lora/layers/__init__.py +43 -0
  294. vllm/lora/layers/base.py +66 -0
  295. vllm/lora/layers/base_linear.py +172 -0
  296. vllm/lora/layers/column_parallel_linear.py +577 -0
  297. vllm/lora/layers/fused_moe.py +739 -0
  298. vllm/lora/layers/logits_processor.py +203 -0
  299. vllm/lora/layers/replicated_linear.py +70 -0
  300. vllm/lora/layers/row_parallel_linear.py +176 -0
  301. vllm/lora/layers/utils.py +115 -0
  302. vllm/lora/layers/vocal_parallel_embedding.py +140 -0
  303. vllm/lora/lora_model.py +221 -0
  304. vllm/lora/lora_weights.py +227 -0
  305. vllm/lora/model_manager.py +858 -0
  306. vllm/lora/ops/__init__.py +0 -0
  307. vllm/lora/ops/ipex_ops/__init__.py +6 -0
  308. vllm/lora/ops/ipex_ops/lora_ops.py +57 -0
  309. vllm/lora/ops/torch_ops/__init__.py +20 -0
  310. vllm/lora/ops/torch_ops/lora_ops.py +128 -0
  311. vllm/lora/ops/triton_ops/README_TUNING.md +60 -0
  312. vllm/lora/ops/triton_ops/__init__.py +21 -0
  313. vllm/lora/ops/triton_ops/fused_moe_lora_op.py +677 -0
  314. vllm/lora/ops/triton_ops/kernel_utils.py +340 -0
  315. vllm/lora/ops/triton_ops/lora_expand_op.py +310 -0
  316. vllm/lora/ops/triton_ops/lora_kernel_metadata.py +154 -0
  317. vllm/lora/ops/triton_ops/lora_shrink_op.py +287 -0
  318. vllm/lora/ops/triton_ops/utils.py +313 -0
  319. vllm/lora/peft_helper.py +128 -0
  320. vllm/lora/punica_wrapper/__init__.py +10 -0
  321. vllm/lora/punica_wrapper/punica_base.py +493 -0
  322. vllm/lora/punica_wrapper/punica_cpu.py +351 -0
  323. vllm/lora/punica_wrapper/punica_gpu.py +413 -0
  324. vllm/lora/punica_wrapper/punica_selector.py +21 -0
  325. vllm/lora/punica_wrapper/punica_xpu.py +276 -0
  326. vllm/lora/punica_wrapper/utils.py +150 -0
  327. vllm/lora/request.py +60 -0
  328. vllm/lora/resolver.py +88 -0
  329. vllm/lora/utils.py +281 -0
  330. vllm/lora/worker_manager.py +278 -0
  331. vllm/model_executor/__init__.py +9 -0
  332. vllm/model_executor/custom_op.py +203 -0
  333. vllm/model_executor/layers/__init__.py +0 -0
  334. vllm/model_executor/layers/activation.py +628 -0
  335. vllm/model_executor/layers/attention/__init__.py +0 -0
  336. vllm/model_executor/layers/attention/chunked_local_attention.py +130 -0
  337. vllm/model_executor/layers/attention/cross_attention.py +182 -0
  338. vllm/model_executor/layers/attention/encoder_only_attention.py +103 -0
  339. vllm/model_executor/layers/attention/mm_encoder_attention.py +234 -0
  340. vllm/model_executor/layers/attention/static_sink_attention.py +254 -0
  341. vllm/model_executor/layers/attention_layer_base.py +34 -0
  342. vllm/model_executor/layers/batch_invariant.py +1063 -0
  343. vllm/model_executor/layers/conv.py +262 -0
  344. vllm/model_executor/layers/fla/__init__.py +8 -0
  345. vllm/model_executor/layers/fla/ops/__init__.py +17 -0
  346. vllm/model_executor/layers/fla/ops/chunk.py +240 -0
  347. vllm/model_executor/layers/fla/ops/chunk_delta_h.py +344 -0
  348. vllm/model_executor/layers/fla/ops/chunk_o.py +183 -0
  349. vllm/model_executor/layers/fla/ops/chunk_scaled_dot_kkt.py +154 -0
  350. vllm/model_executor/layers/fla/ops/cumsum.py +280 -0
  351. vllm/model_executor/layers/fla/ops/fused_recurrent.py +390 -0
  352. vllm/model_executor/layers/fla/ops/index.py +41 -0
  353. vllm/model_executor/layers/fla/ops/kda.py +1351 -0
  354. vllm/model_executor/layers/fla/ops/l2norm.py +146 -0
  355. vllm/model_executor/layers/fla/ops/layernorm_guard.py +396 -0
  356. vllm/model_executor/layers/fla/ops/op.py +60 -0
  357. vllm/model_executor/layers/fla/ops/solve_tril.py +556 -0
  358. vllm/model_executor/layers/fla/ops/utils.py +194 -0
  359. vllm/model_executor/layers/fla/ops/wy_fast.py +158 -0
  360. vllm/model_executor/layers/fused_moe/__init__.py +120 -0
  361. vllm/model_executor/layers/fused_moe/all2all_utils.py +173 -0
  362. vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py +411 -0
  363. vllm/model_executor/layers/fused_moe/config.py +1111 -0
  364. vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
  365. vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  366. vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
  367. vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
  368. vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
  369. vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
  370. vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
  371. vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json +218 -0
  372. vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H200,dtype=int8_w8a16.json +146 -0
  373. vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
  374. vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
  375. vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
  376. vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
  377. vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
  378. vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
  379. vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
  380. vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X.json +200 -0
  381. vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
  382. vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H100,dtype=fp8_w8a8.json +123 -0
  383. vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  384. vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H200.json +146 -0
  385. vllm/model_executor/layers/fused_moe/configs/E=128,N=1856,device_name=NVIDIA_H100_80GB_HBM3.json +147 -0
  386. vllm/model_executor/layers/fused_moe/configs/E=128,N=1856,device_name=NVIDIA_L40S.json +147 -0
  387. vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  388. vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  389. vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20-3e.json +146 -0
  390. vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20.json +146 -0
  391. vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H200.json +146 -0
  392. vllm/model_executor/layers/fused_moe/configs/E=128,N=352,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +122 -0
  393. vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  394. vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  395. vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  396. vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  397. vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  398. vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e.json +146 -0
  399. vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20.json +146 -0
  400. vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  401. vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200.json +146 -0
  402. vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
  403. vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  404. vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  405. vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +146 -0
  406. vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +114 -0
  407. vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Workstation_Edition,dtype=fp8_w8a8.json +146 -0
  408. vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  409. vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI308X.json +213 -0
  410. vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  411. vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200.json +147 -0
  412. vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  413. vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  414. vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  415. vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json +146 -0
  416. vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  417. vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200.json +146 -0
  418. vllm/model_executor/layers/fused_moe/configs/E=128,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=bf16.json +82 -0
  419. vllm/model_executor/layers/fused_moe/configs/E=128,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +82 -0
  420. vllm/model_executor/layers/fused_moe/configs/E=128,N=928,device_name=NVIDIA_H100_80GB_HBM3.json +147 -0
  421. vllm/model_executor/layers/fused_moe/configs/E=128,N=928,device_name=NVIDIA_L40S.json +147 -0
  422. vllm/model_executor/layers/fused_moe/configs/E=128,N=96,device_name=NVIDIA_H20.json +146 -0
  423. vllm/model_executor/layers/fused_moe/configs/E=129,N=704,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Workstation_Edition,dtype=fp8_w8a8.json +146 -0
  424. vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=AMD_Instinct_MI300X.json +200 -0
  425. vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +147 -0
  426. vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200.json +146 -0
  427. vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H100.json +146 -0
  428. vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  429. vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H200.json +146 -0
  430. vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json +146 -0
  431. vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  432. vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  433. vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
  434. vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  435. vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
  436. vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
  437. vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
  438. vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
  439. vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  440. vllm/model_executor/layers/fused_moe/configs/E=16,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  441. vllm/model_executor/layers/fused_moe/configs/E=16,N=2048,device_name=NVIDIA_H200.json +146 -0
  442. vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  443. vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  444. vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
  445. vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json +146 -0
  446. vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
  447. vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H200,dtype=int8_w8a16.json +146 -0
  448. vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
  449. vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
  450. vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
  451. vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
  452. vllm/model_executor/layers/fused_moe/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
  453. vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
  454. vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  455. vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json +146 -0
  456. vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
  457. vllm/model_executor/layers/fused_moe/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
  458. vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=AMD_Instinct_MI300X.json +201 -0
  459. vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=AMD_Instinct_MI350_OAM,dtype=fp8_w8a8.json +164 -0
  460. vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
  461. vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json +147 -0
  462. vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H20-3e.json +146 -0
  463. vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +147 -0
  464. vllm/model_executor/layers/fused_moe/configs/E=160,N=320,device_name=NVIDIA_H20-3e.json +146 -0
  465. vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
  466. vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI350_OAM,dtype=fp8_w8a8.json +164 -0
  467. vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI355_OAM,dtype=fp8_w8a8.json +164 -0
  468. vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json +147 -0
  469. vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  470. vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  471. vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  472. vllm/model_executor/layers/fused_moe/configs/E=160,N=768,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json +147 -0
  473. vllm/model_executor/layers/fused_moe/configs/E=20,N=1536,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Server_Edition,dtype=fp8_w8a8.json +147 -0
  474. vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  475. vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  476. vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  477. vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  478. vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325X,block_shape=[128,128].json +200 -0
  479. vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
  480. vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  481. vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json +146 -0
  482. vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  483. vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +146 -0
  484. vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  485. vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  486. vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  487. vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  488. vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
  489. vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
  490. vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  491. vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  492. vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  493. vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  494. vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  495. vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  496. vllm/model_executor/layers/fused_moe/configs/E=256,N=384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
  497. vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
  498. vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
  499. vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  500. vllm/model_executor/layers/fused_moe/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
  501. vllm/model_executor/layers/fused_moe/configs/E=32,N=1408,device_name=NVIDIA_B200.json +147 -0
  502. vllm/model_executor/layers/fused_moe/configs/E=32,N=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
  503. vllm/model_executor/layers/fused_moe/configs/E=32,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
  504. vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  505. vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  506. vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  507. vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  508. vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  509. vllm/model_executor/layers/fused_moe/configs/E=40,N=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +147 -0
  510. vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  511. vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  512. vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  513. vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_A100-SXM4-80GB.json +147 -0
  514. vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
  515. vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200.json +146 -0
  516. vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json +147 -0
  517. vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  518. vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H20-3e.json +146 -0
  519. vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H200.json +146 -0
  520. vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
  521. vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200.json +146 -0
  522. vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json +146 -0
  523. vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
  524. vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  525. vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H20-3e.json +146 -0
  526. vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H200.json +146 -0
  527. vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
  528. vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200.json +146 -0
  529. vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json +146 -0
  530. vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  531. vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H20-3e.json +146 -0
  532. vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H200.json +146 -0
  533. vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_A100-SXM4-80GB.json +147 -0
  534. vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_B200.json +146 -0
  535. vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H20-3e.json +146 -0
  536. vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H200.json +146 -0
  537. vllm/model_executor/layers/fused_moe/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json +200 -0
  538. vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json +200 -0
  539. vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json +200 -0
  540. vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json +200 -0
  541. vllm/model_executor/layers/fused_moe/configs/E=62,N=128,device_name=AMD_Instinct_MI300X.json +200 -0
  542. vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=AMD_Instinct_MI300X.json +200 -0
  543. vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  544. vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=AMD_Instinct_MI300X.json +200 -0
  545. vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  546. vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  547. vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
  548. vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
  549. vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  550. vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  551. vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200.json +146 -0
  552. vllm/model_executor/layers/fused_moe/configs/E=64,N=1408,device_name=NVIDIA_B200.json +147 -0
  553. vllm/model_executor/layers/fused_moe/configs/E=64,N=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
  554. vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
  555. vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  556. vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200.json +146 -0
  557. vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
  558. vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20.json +146 -0
  559. vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
  560. vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  561. vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  562. vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200.json +146 -0
  563. vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
  564. vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20.json +146 -0
  565. vllm/model_executor/layers/fused_moe/configs/E=64,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
  566. vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  567. vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
  568. vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json +146 -0
  569. vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
  570. vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  571. vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  572. vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200.json +146 -0
  573. vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H100_PCIe,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
  574. vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
  575. vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20.json +146 -0
  576. vllm/model_executor/layers/fused_moe/configs/E=64,N=896,device_name=NVIDIA_H20.json +146 -0
  577. vllm/model_executor/layers/fused_moe/configs/E=64,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=bf16.json +82 -0
  578. vllm/model_executor/layers/fused_moe/configs/E=64,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +82 -0
  579. vllm/model_executor/layers/fused_moe/configs/E=72,N=192,device_name=AMD_Instinct_MI300X.json +200 -0
  580. vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=AMD_Instinct_MI300X.json +200 -0
  581. vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  582. vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=AMD_Instinct_MI300X.json +200 -0
  583. vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  584. vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
  585. vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json +200 -0
  586. vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
  587. vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json +200 -0
  588. vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +138 -0
  589. vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  590. vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200.json +146 -0
  591. vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
  592. vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json +200 -0
  593. vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
  594. vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json +200 -0
  595. vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
  596. vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json +200 -0
  597. vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
  598. vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json +200 -0
  599. vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json +146 -0
  600. vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  601. vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  602. vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  603. vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200.json +146 -0
  604. vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
  605. vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json +200 -0
  606. vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
  607. vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.json +200 -0
  608. vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  609. vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
  610. vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  611. vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +154 -0
  612. vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  613. vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200.json +146 -0
  614. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
  615. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json +200 -0
  616. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
  617. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json +200 -0
  618. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json +146 -0
  619. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  620. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json +146 -0
  621. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
  622. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  623. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  624. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200.json +146 -0
  625. vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_L40S.json +173 -0
  626. vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
  627. vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json +200 -0
  628. vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
  629. vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X.json +200 -0
  630. vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  631. vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
  632. vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  633. vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  634. vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200.json +146 -0
  635. vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
  636. vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json +200 -0
  637. vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
  638. vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json +200 -0
  639. vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
  640. vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
  641. vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
  642. vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  643. vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200.json +146 -0
  644. vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
  645. vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json +200 -0
  646. vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
  647. vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X.json +200 -0
  648. vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
  649. vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
  650. vllm/model_executor/layers/fused_moe/configs/README +12 -0
  651. vllm/model_executor/layers/fused_moe/cpu_fused_moe.py +444 -0
  652. vllm/model_executor/layers/fused_moe/cutlass_moe.py +1086 -0
  653. vllm/model_executor/layers/fused_moe/deep_gemm_moe.py +364 -0
  654. vllm/model_executor/layers/fused_moe/deep_gemm_utils.py +427 -0
  655. vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py +420 -0
  656. vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py +436 -0
  657. vllm/model_executor/layers/fused_moe/fallback.py +127 -0
  658. vllm/model_executor/layers/fused_moe/flashinfer_cutedsl_moe.py +338 -0
  659. vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py +310 -0
  660. vllm/model_executor/layers/fused_moe/flashinfer_cutlass_prepare_finalize.py +371 -0
  661. vllm/model_executor/layers/fused_moe/flashinfer_trtllm_moe.py +192 -0
  662. vllm/model_executor/layers/fused_moe/fused_batched_moe.py +1018 -0
  663. vllm/model_executor/layers/fused_moe/fused_marlin_moe.py +824 -0
  664. vllm/model_executor/layers/fused_moe/fused_moe.py +2638 -0
  665. vllm/model_executor/layers/fused_moe/fused_moe_method_base.py +119 -0
  666. vllm/model_executor/layers/fused_moe/fused_moe_modular_method.py +117 -0
  667. vllm/model_executor/layers/fused_moe/fused_moe_router.py +40 -0
  668. vllm/model_executor/layers/fused_moe/gpt_oss_triton_kernels_moe.py +531 -0
  669. vllm/model_executor/layers/fused_moe/layer.py +2169 -0
  670. vllm/model_executor/layers/fused_moe/modular_kernel.py +1251 -0
  671. vllm/model_executor/layers/fused_moe/moe_align_block_size.py +192 -0
  672. vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py +229 -0
  673. vllm/model_executor/layers/fused_moe/moe_torch_iterative.py +60 -0
  674. vllm/model_executor/layers/fused_moe/oracle/__init__.py +2 -0
  675. vllm/model_executor/layers/fused_moe/oracle/fp8.py +358 -0
  676. vllm/model_executor/layers/fused_moe/oracle/nvfp4.py +280 -0
  677. vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py +362 -0
  678. vllm/model_executor/layers/fused_moe/prepare_finalize.py +87 -0
  679. vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py +347 -0
  680. vllm/model_executor/layers/fused_moe/routed_experts_capturer.py +324 -0
  681. vllm/model_executor/layers/fused_moe/routing_simulator.py +310 -0
  682. vllm/model_executor/layers/fused_moe/shared_fused_moe.py +96 -0
  683. vllm/model_executor/layers/fused_moe/topk_weight_and_reduce.py +171 -0
  684. vllm/model_executor/layers/fused_moe/triton_cutlass_moe.py +78 -0
  685. vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py +75 -0
  686. vllm/model_executor/layers/fused_moe/trtllm_moe.py +144 -0
  687. vllm/model_executor/layers/fused_moe/unquantized_fused_moe_method.py +403 -0
  688. vllm/model_executor/layers/fused_moe/utils.py +382 -0
  689. vllm/model_executor/layers/fused_moe/zero_expert_fused_moe.py +189 -0
  690. vllm/model_executor/layers/kda.py +442 -0
  691. vllm/model_executor/layers/layernorm.py +451 -0
  692. vllm/model_executor/layers/lightning_attn.py +735 -0
  693. vllm/model_executor/layers/linear.py +1478 -0
  694. vllm/model_executor/layers/logits_processor.py +109 -0
  695. vllm/model_executor/layers/mamba/__init__.py +0 -0
  696. vllm/model_executor/layers/mamba/abstract.py +68 -0
  697. vllm/model_executor/layers/mamba/linear_attn.py +410 -0
  698. vllm/model_executor/layers/mamba/mamba_mixer.py +541 -0
  699. vllm/model_executor/layers/mamba/mamba_mixer2.py +936 -0
  700. vllm/model_executor/layers/mamba/mamba_utils.py +225 -0
  701. vllm/model_executor/layers/mamba/ops/__init__.py +0 -0
  702. vllm/model_executor/layers/mamba/ops/causal_conv1d.py +1240 -0
  703. vllm/model_executor/layers/mamba/ops/layernorm_gated.py +172 -0
  704. vllm/model_executor/layers/mamba/ops/mamba_ssm.py +586 -0
  705. vllm/model_executor/layers/mamba/ops/ssd_bmm.py +211 -0
  706. vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py +456 -0
  707. vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py +700 -0
  708. vllm/model_executor/layers/mamba/ops/ssd_combined.py +230 -0
  709. vllm/model_executor/layers/mamba/ops/ssd_state_passing.py +157 -0
  710. vllm/model_executor/layers/mamba/short_conv.py +254 -0
  711. vllm/model_executor/layers/mla.py +179 -0
  712. vllm/model_executor/layers/pooler/__init__.py +5 -0
  713. vllm/model_executor/layers/pooler/abstract.py +39 -0
  714. vllm/model_executor/layers/pooler/activations.py +162 -0
  715. vllm/model_executor/layers/pooler/common.py +32 -0
  716. vllm/model_executor/layers/pooler/seqwise/__init__.py +45 -0
  717. vllm/model_executor/layers/pooler/seqwise/heads.py +151 -0
  718. vllm/model_executor/layers/pooler/seqwise/methods.py +93 -0
  719. vllm/model_executor/layers/pooler/seqwise/poolers.py +127 -0
  720. vllm/model_executor/layers/pooler/special.py +128 -0
  721. vllm/model_executor/layers/pooler/tokwise/__init__.py +39 -0
  722. vllm/model_executor/layers/pooler/tokwise/heads.py +133 -0
  723. vllm/model_executor/layers/pooler/tokwise/methods.py +122 -0
  724. vllm/model_executor/layers/pooler/tokwise/poolers.py +127 -0
  725. vllm/model_executor/layers/quantization/__init__.py +195 -0
  726. vllm/model_executor/layers/quantization/auto_round.py +454 -0
  727. vllm/model_executor/layers/quantization/awq.py +277 -0
  728. vllm/model_executor/layers/quantization/awq_marlin.py +795 -0
  729. vllm/model_executor/layers/quantization/awq_triton.py +337 -0
  730. vllm/model_executor/layers/quantization/base_config.py +170 -0
  731. vllm/model_executor/layers/quantization/bitblas.py +502 -0
  732. vllm/model_executor/layers/quantization/bitsandbytes.py +631 -0
  733. vllm/model_executor/layers/quantization/compressed_tensors/__init__.py +3 -0
  734. vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py +982 -0
  735. vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py +2368 -0
  736. vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py +37 -0
  737. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py +392 -0
  738. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py +55 -0
  739. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py +176 -0
  740. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_mxfp4.py +106 -0
  741. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py +124 -0
  742. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py +218 -0
  743. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_fp8.py +176 -0
  744. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_int.py +153 -0
  745. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py +138 -0
  746. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +203 -0
  747. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py +125 -0
  748. vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py +230 -0
  749. vllm/model_executor/layers/quantization/compressed_tensors/transform/__init__.py +0 -0
  750. vllm/model_executor/layers/quantization/compressed_tensors/transform/linear.py +260 -0
  751. vllm/model_executor/layers/quantization/compressed_tensors/transform/module.py +173 -0
  752. vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/__init__.py +0 -0
  753. vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/linear_qutlass_nvfp4.py +64 -0
  754. vllm/model_executor/layers/quantization/compressed_tensors/transform/utils.py +13 -0
  755. vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py +224 -0
  756. vllm/model_executor/layers/quantization/compressed_tensors/utils.py +216 -0
  757. vllm/model_executor/layers/quantization/cpu_wna16.py +299 -0
  758. vllm/model_executor/layers/quantization/deepspeedfp.py +218 -0
  759. vllm/model_executor/layers/quantization/experts_int8.py +209 -0
  760. vllm/model_executor/layers/quantization/fbgemm_fp8.py +195 -0
  761. vllm/model_executor/layers/quantization/fp8.py +1224 -0
  762. vllm/model_executor/layers/quantization/fp_quant.py +420 -0
  763. vllm/model_executor/layers/quantization/gguf.py +682 -0
  764. vllm/model_executor/layers/quantization/gptq.py +393 -0
  765. vllm/model_executor/layers/quantization/gptq_bitblas.py +482 -0
  766. vllm/model_executor/layers/quantization/gptq_marlin.py +934 -0
  767. vllm/model_executor/layers/quantization/gptq_marlin_24.py +320 -0
  768. vllm/model_executor/layers/quantization/hqq_marlin.py +372 -0
  769. vllm/model_executor/layers/quantization/inc.py +65 -0
  770. vllm/model_executor/layers/quantization/input_quant_fp8.py +212 -0
  771. vllm/model_executor/layers/quantization/ipex_quant.py +403 -0
  772. vllm/model_executor/layers/quantization/kernels/__init__.py +0 -0
  773. vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py +94 -0
  774. vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py +113 -0
  775. vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py +115 -0
  776. vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py +323 -0
  777. vllm/model_executor/layers/quantization/kernels/mixed_precision/conch.py +98 -0
  778. vllm/model_executor/layers/quantization/kernels/mixed_precision/cpu.py +126 -0
  779. vllm/model_executor/layers/quantization/kernels/mixed_precision/cutlass.py +130 -0
  780. vllm/model_executor/layers/quantization/kernels/mixed_precision/dynamic_4bit.py +111 -0
  781. vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py +168 -0
  782. vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py +159 -0
  783. vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py +200 -0
  784. vllm/model_executor/layers/quantization/kernels/mixed_precision/xpu.py +97 -0
  785. vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py +76 -0
  786. vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py +77 -0
  787. vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py +128 -0
  788. vllm/model_executor/layers/quantization/kernels/scaled_mm/cpu.py +220 -0
  789. vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py +147 -0
  790. vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py +88 -0
  791. vllm/model_executor/layers/quantization/kv_cache.py +153 -0
  792. vllm/model_executor/layers/quantization/modelopt.py +1665 -0
  793. vllm/model_executor/layers/quantization/moe_wna16.py +518 -0
  794. vllm/model_executor/layers/quantization/mxfp4.py +1145 -0
  795. vllm/model_executor/layers/quantization/petit.py +319 -0
  796. vllm/model_executor/layers/quantization/ptpc_fp8.py +140 -0
  797. vllm/model_executor/layers/quantization/quark/__init__.py +0 -0
  798. vllm/model_executor/layers/quantization/quark/quark.py +570 -0
  799. vllm/model_executor/layers/quantization/quark/quark_moe.py +797 -0
  800. vllm/model_executor/layers/quantization/quark/schemes/__init__.py +9 -0
  801. vllm/model_executor/layers/quantization/quark/schemes/quark_ocp_mx.py +343 -0
  802. vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py +55 -0
  803. vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py +179 -0
  804. vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py +139 -0
  805. vllm/model_executor/layers/quantization/quark/utils.py +105 -0
  806. vllm/model_executor/layers/quantization/qutlass_utils.py +185 -0
  807. vllm/model_executor/layers/quantization/rtn.py +626 -0
  808. vllm/model_executor/layers/quantization/schema.py +90 -0
  809. vllm/model_executor/layers/quantization/torchao.py +380 -0
  810. vllm/model_executor/layers/quantization/utils/__init__.py +6 -0
  811. vllm/model_executor/layers/quantization/utils/allspark_utils.py +67 -0
  812. vllm/model_executor/layers/quantization/utils/bitblas_utils.py +229 -0
  813. vllm/model_executor/layers/quantization/utils/configs/N=10240,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  814. vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  815. vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  816. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  817. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  818. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  819. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  820. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  821. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  822. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  823. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  824. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  825. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  826. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  827. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  828. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  829. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  830. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  831. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  832. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  833. vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  834. vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  835. vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  836. vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  837. vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  838. vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  839. vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  840. vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  841. vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  842. vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  843. vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  844. vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  845. vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  846. vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  847. vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  848. vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  849. vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  850. vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  851. vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  852. vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  853. vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  854. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  855. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  856. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  857. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  858. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  859. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  860. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  861. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  862. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  863. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  864. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  865. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  866. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  867. vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  868. vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  869. vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  870. vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  871. vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  872. vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  873. vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  874. vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  875. vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  876. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  877. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  878. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  879. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  880. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  881. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  882. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  883. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  884. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  885. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  886. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  887. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  888. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  889. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  890. vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  891. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  892. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  893. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  894. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  895. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  896. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  897. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  898. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  899. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  900. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  901. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  902. vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  903. vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  904. vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  905. vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  906. vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  907. vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  908. vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  909. vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  910. vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  911. vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  912. vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  913. vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  914. vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  915. vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  916. vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  917. vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  918. vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  919. vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  920. vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  921. vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  922. vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  923. vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  924. vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  925. vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  926. vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  927. vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  928. vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  929. vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  930. vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  931. vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  932. vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  933. vllm/model_executor/layers/quantization/utils/configs/N=5120,K=25600,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  934. vllm/model_executor/layers/quantization/utils/configs/N=5120,K=8192,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  935. vllm/model_executor/layers/quantization/utils/configs/N=51200,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  936. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  937. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  938. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  939. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  940. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  941. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  942. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  943. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  944. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  945. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  946. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +18 -0
  947. vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  948. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  949. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  950. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  951. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  952. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  953. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  954. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  955. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  956. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  957. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  958. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  959. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  960. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  961. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  962. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  963. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  964. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  965. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  966. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  967. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  968. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  969. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  970. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  971. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  972. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  973. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  974. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  975. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  976. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  977. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  978. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  979. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  980. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  981. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  982. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  983. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  984. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  985. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  986. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  987. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  988. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  989. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  990. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  991. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  992. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  993. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  994. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  995. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  996. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  997. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  998. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  999. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1000. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1001. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  1002. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  1003. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  1004. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  1005. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  1006. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1007. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1008. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1009. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  1010. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  1011. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  1012. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  1013. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  1014. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1015. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1016. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1017. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  1018. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
  1019. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
  1020. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
  1021. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1022. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1023. vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1024. vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1025. vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1026. vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
  1027. vllm/model_executor/layers/quantization/utils/configs/README.md +3 -0
  1028. vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py +514 -0
  1029. vllm/model_executor/layers/quantization/utils/flashinfer_utils.py +370 -0
  1030. vllm/model_executor/layers/quantization/utils/fp8_utils.py +1658 -0
  1031. vllm/model_executor/layers/quantization/utils/gptq_utils.py +158 -0
  1032. vllm/model_executor/layers/quantization/utils/int8_utils.py +477 -0
  1033. vllm/model_executor/layers/quantization/utils/layer_utils.py +41 -0
  1034. vllm/model_executor/layers/quantization/utils/machete_utils.py +56 -0
  1035. vllm/model_executor/layers/quantization/utils/marlin_utils.py +720 -0
  1036. vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py +565 -0
  1037. vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py +378 -0
  1038. vllm/model_executor/layers/quantization/utils/marlin_utils_test.py +219 -0
  1039. vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py +467 -0
  1040. vllm/model_executor/layers/quantization/utils/mxfp4_utils.py +189 -0
  1041. vllm/model_executor/layers/quantization/utils/mxfp6_utils.py +142 -0
  1042. vllm/model_executor/layers/quantization/utils/mxfp8_utils.py +24 -0
  1043. vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py +142 -0
  1044. vllm/model_executor/layers/quantization/utils/nvfp4_moe_support.py +67 -0
  1045. vllm/model_executor/layers/quantization/utils/ocp_mx_utils.py +51 -0
  1046. vllm/model_executor/layers/quantization/utils/petit_utils.py +124 -0
  1047. vllm/model_executor/layers/quantization/utils/quant_utils.py +767 -0
  1048. vllm/model_executor/layers/quantization/utils/w8a8_utils.py +519 -0
  1049. vllm/model_executor/layers/resampler.py +283 -0
  1050. vllm/model_executor/layers/rotary_embedding/__init__.py +291 -0
  1051. vllm/model_executor/layers/rotary_embedding/base.py +282 -0
  1052. vllm/model_executor/layers/rotary_embedding/common.py +289 -0
  1053. vllm/model_executor/layers/rotary_embedding/deepseek_scaling_rope.py +184 -0
  1054. vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py +218 -0
  1055. vllm/model_executor/layers/rotary_embedding/dynamic_ntk_alpha_rope.py +43 -0
  1056. vllm/model_executor/layers/rotary_embedding/dynamic_ntk_scaling_rope.py +68 -0
  1057. vllm/model_executor/layers/rotary_embedding/ernie45_vl_rope.py +82 -0
  1058. vllm/model_executor/layers/rotary_embedding/linear_scaling_rope.py +115 -0
  1059. vllm/model_executor/layers/rotary_embedding/llama3_rope.py +54 -0
  1060. vllm/model_executor/layers/rotary_embedding/llama4_vision_rope.py +83 -0
  1061. vllm/model_executor/layers/rotary_embedding/mrope.py +412 -0
  1062. vllm/model_executor/layers/rotary_embedding/ntk_scaling_rope.py +47 -0
  1063. vllm/model_executor/layers/rotary_embedding/phi3_long_rope_scaled_rope.py +159 -0
  1064. vllm/model_executor/layers/rotary_embedding/xdrope.py +160 -0
  1065. vllm/model_executor/layers/rotary_embedding/yarn_scaling_rope.py +84 -0
  1066. vllm/model_executor/layers/utils.py +251 -0
  1067. vllm/model_executor/layers/vocab_parallel_embedding.py +564 -0
  1068. vllm/model_executor/model_loader/__init__.py +150 -0
  1069. vllm/model_executor/model_loader/base_loader.py +71 -0
  1070. vllm/model_executor/model_loader/bitsandbytes_loader.py +821 -0
  1071. vllm/model_executor/model_loader/default_loader.py +304 -0
  1072. vllm/model_executor/model_loader/dummy_loader.py +28 -0
  1073. vllm/model_executor/model_loader/gguf_loader.py +371 -0
  1074. vllm/model_executor/model_loader/online_quantization.py +275 -0
  1075. vllm/model_executor/model_loader/runai_streamer_loader.py +115 -0
  1076. vllm/model_executor/model_loader/sharded_state_loader.py +214 -0
  1077. vllm/model_executor/model_loader/tensorizer.py +793 -0
  1078. vllm/model_executor/model_loader/tensorizer_loader.py +151 -0
  1079. vllm/model_executor/model_loader/utils.py +299 -0
  1080. vllm/model_executor/model_loader/weight_utils.py +1183 -0
  1081. vllm/model_executor/models/__init__.py +44 -0
  1082. vllm/model_executor/models/adapters.py +592 -0
  1083. vllm/model_executor/models/afmoe.py +697 -0
  1084. vllm/model_executor/models/aimv2.py +248 -0
  1085. vllm/model_executor/models/apertus.py +567 -0
  1086. vllm/model_executor/models/arcee.py +428 -0
  1087. vllm/model_executor/models/arctic.py +633 -0
  1088. vllm/model_executor/models/aria.py +663 -0
  1089. vllm/model_executor/models/audioflamingo3.py +639 -0
  1090. vllm/model_executor/models/aya_vision.py +448 -0
  1091. vllm/model_executor/models/bagel.py +591 -0
  1092. vllm/model_executor/models/baichuan.py +493 -0
  1093. vllm/model_executor/models/bailing_moe.py +643 -0
  1094. vllm/model_executor/models/bamba.py +511 -0
  1095. vllm/model_executor/models/bee.py +157 -0
  1096. vllm/model_executor/models/bert.py +911 -0
  1097. vllm/model_executor/models/bert_with_rope.py +729 -0
  1098. vllm/model_executor/models/blip.py +350 -0
  1099. vllm/model_executor/models/blip2.py +736 -0
  1100. vllm/model_executor/models/bloom.py +390 -0
  1101. vllm/model_executor/models/chameleon.py +1095 -0
  1102. vllm/model_executor/models/chatglm.py +502 -0
  1103. vllm/model_executor/models/clip.py +1045 -0
  1104. vllm/model_executor/models/cohere2_vision.py +470 -0
  1105. vllm/model_executor/models/commandr.py +469 -0
  1106. vllm/model_executor/models/config.py +571 -0
  1107. vllm/model_executor/models/dbrx.py +484 -0
  1108. vllm/model_executor/models/deepencoder.py +679 -0
  1109. vllm/model_executor/models/deepseek_eagle.py +253 -0
  1110. vllm/model_executor/models/deepseek_mtp.py +447 -0
  1111. vllm/model_executor/models/deepseek_ocr.py +601 -0
  1112. vllm/model_executor/models/deepseek_v2.py +1727 -0
  1113. vllm/model_executor/models/deepseek_vl2.py +642 -0
  1114. vllm/model_executor/models/dots1.py +566 -0
  1115. vllm/model_executor/models/dots_ocr.py +830 -0
  1116. vllm/model_executor/models/ernie45.py +53 -0
  1117. vllm/model_executor/models/ernie45_moe.py +755 -0
  1118. vllm/model_executor/models/ernie45_vl.py +1702 -0
  1119. vllm/model_executor/models/ernie45_vl_moe.py +801 -0
  1120. vllm/model_executor/models/ernie_mtp.py +278 -0
  1121. vllm/model_executor/models/exaone.py +524 -0
  1122. vllm/model_executor/models/exaone4.py +518 -0
  1123. vllm/model_executor/models/exaone_moe.py +579 -0
  1124. vllm/model_executor/models/exaone_moe_mtp.py +255 -0
  1125. vllm/model_executor/models/fairseq2_llama.py +154 -0
  1126. vllm/model_executor/models/falcon.py +543 -0
  1127. vllm/model_executor/models/falcon_h1.py +675 -0
  1128. vllm/model_executor/models/flex_olmo.py +155 -0
  1129. vllm/model_executor/models/fuyu.py +371 -0
  1130. vllm/model_executor/models/gemma.py +425 -0
  1131. vllm/model_executor/models/gemma2.py +435 -0
  1132. vllm/model_executor/models/gemma3.py +520 -0
  1133. vllm/model_executor/models/gemma3_mm.py +664 -0
  1134. vllm/model_executor/models/gemma3n.py +1166 -0
  1135. vllm/model_executor/models/gemma3n_audio_utils.py +57 -0
  1136. vllm/model_executor/models/gemma3n_mm.py +820 -0
  1137. vllm/model_executor/models/glm.py +24 -0
  1138. vllm/model_executor/models/glm4.py +295 -0
  1139. vllm/model_executor/models/glm4_1v.py +1823 -0
  1140. vllm/model_executor/models/glm4_moe.py +725 -0
  1141. vllm/model_executor/models/glm4_moe_mtp.py +365 -0
  1142. vllm/model_executor/models/glm4v.py +783 -0
  1143. vllm/model_executor/models/glmasr.py +1154 -0
  1144. vllm/model_executor/models/glmasr_utils.py +188 -0
  1145. vllm/model_executor/models/gpt2.py +385 -0
  1146. vllm/model_executor/models/gpt_bigcode.py +339 -0
  1147. vllm/model_executor/models/gpt_j.py +346 -0
  1148. vllm/model_executor/models/gpt_neox.py +340 -0
  1149. vllm/model_executor/models/gpt_oss.py +745 -0
  1150. vllm/model_executor/models/granite.py +475 -0
  1151. vllm/model_executor/models/granite_speech.py +919 -0
  1152. vllm/model_executor/models/granitemoe.py +561 -0
  1153. vllm/model_executor/models/granitemoehybrid.py +703 -0
  1154. vllm/model_executor/models/granitemoeshared.py +328 -0
  1155. vllm/model_executor/models/gritlm.py +242 -0
  1156. vllm/model_executor/models/grok1.py +803 -0
  1157. vllm/model_executor/models/h2ovl.py +554 -0
  1158. vllm/model_executor/models/hunyuan_v1.py +1042 -0
  1159. vllm/model_executor/models/hunyuan_vision.py +1034 -0
  1160. vllm/model_executor/models/hyperclovax_vision.py +1163 -0
  1161. vllm/model_executor/models/idefics2_vision_model.py +427 -0
  1162. vllm/model_executor/models/idefics3.py +734 -0
  1163. vllm/model_executor/models/interfaces.py +1180 -0
  1164. vllm/model_executor/models/interfaces_base.py +252 -0
  1165. vllm/model_executor/models/intern_vit.py +454 -0
  1166. vllm/model_executor/models/internlm2.py +451 -0
  1167. vllm/model_executor/models/internlm2_ve.py +139 -0
  1168. vllm/model_executor/models/interns1.py +828 -0
  1169. vllm/model_executor/models/interns1_vit.py +433 -0
  1170. vllm/model_executor/models/internvl.py +1436 -0
  1171. vllm/model_executor/models/iquest_loopcoder.py +595 -0
  1172. vllm/model_executor/models/isaac.py +1503 -0
  1173. vllm/model_executor/models/jais.py +397 -0
  1174. vllm/model_executor/models/jais2.py +508 -0
  1175. vllm/model_executor/models/jamba.py +599 -0
  1176. vllm/model_executor/models/jina_vl.py +145 -0
  1177. vllm/model_executor/models/kanana_v.py +756 -0
  1178. vllm/model_executor/models/keye.py +1709 -0
  1179. vllm/model_executor/models/keye_vl1_5.py +726 -0
  1180. vllm/model_executor/models/kimi_linear.py +659 -0
  1181. vllm/model_executor/models/kimi_vl.py +577 -0
  1182. vllm/model_executor/models/lfm2.py +515 -0
  1183. vllm/model_executor/models/lfm2_moe.py +746 -0
  1184. vllm/model_executor/models/lfm2_vl.py +732 -0
  1185. vllm/model_executor/models/lightonocr.py +197 -0
  1186. vllm/model_executor/models/llama.py +724 -0
  1187. vllm/model_executor/models/llama4.py +860 -0
  1188. vllm/model_executor/models/llama4_eagle.py +225 -0
  1189. vllm/model_executor/models/llama_eagle.py +213 -0
  1190. vllm/model_executor/models/llama_eagle3.py +375 -0
  1191. vllm/model_executor/models/llava.py +879 -0
  1192. vllm/model_executor/models/llava_next.py +583 -0
  1193. vllm/model_executor/models/llava_next_video.py +467 -0
  1194. vllm/model_executor/models/llava_onevision.py +922 -0
  1195. vllm/model_executor/models/longcat_flash.py +767 -0
  1196. vllm/model_executor/models/longcat_flash_mtp.py +348 -0
  1197. vllm/model_executor/models/mamba.py +276 -0
  1198. vllm/model_executor/models/mamba2.py +288 -0
  1199. vllm/model_executor/models/medusa.py +179 -0
  1200. vllm/model_executor/models/midashenglm.py +826 -0
  1201. vllm/model_executor/models/mimo.py +188 -0
  1202. vllm/model_executor/models/mimo_mtp.py +294 -0
  1203. vllm/model_executor/models/mimo_v2_flash.py +718 -0
  1204. vllm/model_executor/models/minicpm.py +660 -0
  1205. vllm/model_executor/models/minicpm3.py +233 -0
  1206. vllm/model_executor/models/minicpm_eagle.py +386 -0
  1207. vllm/model_executor/models/minicpmo.py +768 -0
  1208. vllm/model_executor/models/minicpmv.py +1742 -0
  1209. vllm/model_executor/models/minimax_m2.py +552 -0
  1210. vllm/model_executor/models/minimax_text_01.py +1008 -0
  1211. vllm/model_executor/models/minimax_vl_01.py +395 -0
  1212. vllm/model_executor/models/mistral3.py +638 -0
  1213. vllm/model_executor/models/mistral_large_3.py +63 -0
  1214. vllm/model_executor/models/mistral_large_3_eagle.py +137 -0
  1215. vllm/model_executor/models/mixtral.py +599 -0
  1216. vllm/model_executor/models/mllama4.py +1170 -0
  1217. vllm/model_executor/models/mlp_speculator.py +235 -0
  1218. vllm/model_executor/models/modernbert.py +458 -0
  1219. vllm/model_executor/models/module_mapping.py +74 -0
  1220. vllm/model_executor/models/molmo.py +1592 -0
  1221. vllm/model_executor/models/moonvit.py +601 -0
  1222. vllm/model_executor/models/mpt.py +335 -0
  1223. vllm/model_executor/models/nano_nemotron_vl.py +1725 -0
  1224. vllm/model_executor/models/nemotron.py +499 -0
  1225. vllm/model_executor/models/nemotron_h.py +902 -0
  1226. vllm/model_executor/models/nemotron_nas.py +474 -0
  1227. vllm/model_executor/models/nemotron_parse.py +958 -0
  1228. vllm/model_executor/models/nemotron_vl.py +651 -0
  1229. vllm/model_executor/models/nvlm_d.py +216 -0
  1230. vllm/model_executor/models/olmo.py +412 -0
  1231. vllm/model_executor/models/olmo2.py +454 -0
  1232. vllm/model_executor/models/olmoe.py +498 -0
  1233. vllm/model_executor/models/opencua.py +262 -0
  1234. vllm/model_executor/models/openpangu.py +1378 -0
  1235. vllm/model_executor/models/openpangu_mtp.py +265 -0
  1236. vllm/model_executor/models/opt.py +426 -0
  1237. vllm/model_executor/models/orion.py +365 -0
  1238. vllm/model_executor/models/ouro.py +507 -0
  1239. vllm/model_executor/models/ovis.py +557 -0
  1240. vllm/model_executor/models/ovis2_5.py +661 -0
  1241. vllm/model_executor/models/paddleocr_vl.py +1261 -0
  1242. vllm/model_executor/models/paligemma.py +429 -0
  1243. vllm/model_executor/models/persimmon.py +373 -0
  1244. vllm/model_executor/models/phi.py +363 -0
  1245. vllm/model_executor/models/phi3.py +18 -0
  1246. vllm/model_executor/models/phi3v.py +729 -0
  1247. vllm/model_executor/models/phi4mm.py +1250 -0
  1248. vllm/model_executor/models/phi4mm_audio.py +1296 -0
  1249. vllm/model_executor/models/phi4mm_utils.py +1907 -0
  1250. vllm/model_executor/models/phimoe.py +671 -0
  1251. vllm/model_executor/models/pixtral.py +1437 -0
  1252. vllm/model_executor/models/plamo2.py +993 -0
  1253. vllm/model_executor/models/plamo3.py +437 -0
  1254. vllm/model_executor/models/qwen.py +377 -0
  1255. vllm/model_executor/models/qwen2.py +600 -0
  1256. vllm/model_executor/models/qwen2_5_omni_thinker.py +1200 -0
  1257. vllm/model_executor/models/qwen2_5_vl.py +1598 -0
  1258. vllm/model_executor/models/qwen2_audio.py +478 -0
  1259. vllm/model_executor/models/qwen2_moe.py +604 -0
  1260. vllm/model_executor/models/qwen2_rm.py +120 -0
  1261. vllm/model_executor/models/qwen2_vl.py +1588 -0
  1262. vllm/model_executor/models/qwen3.py +331 -0
  1263. vllm/model_executor/models/qwen3_moe.py +752 -0
  1264. vllm/model_executor/models/qwen3_next.py +1410 -0
  1265. vllm/model_executor/models/qwen3_next_mtp.py +293 -0
  1266. vllm/model_executor/models/qwen3_omni_moe_thinker.py +1814 -0
  1267. vllm/model_executor/models/qwen3_vl.py +2120 -0
  1268. vllm/model_executor/models/qwen3_vl_moe.py +474 -0
  1269. vllm/model_executor/models/qwen_vl.py +821 -0
  1270. vllm/model_executor/models/radio.py +573 -0
  1271. vllm/model_executor/models/registry.py +1218 -0
  1272. vllm/model_executor/models/roberta.py +239 -0
  1273. vllm/model_executor/models/rvl.py +107 -0
  1274. vllm/model_executor/models/seed_oss.py +492 -0
  1275. vllm/model_executor/models/siglip.py +1259 -0
  1276. vllm/model_executor/models/siglip2.py +495 -0
  1277. vllm/model_executor/models/siglip2navit.py +660 -0
  1278. vllm/model_executor/models/skyworkr1v.py +951 -0
  1279. vllm/model_executor/models/smolvlm.py +38 -0
  1280. vllm/model_executor/models/solar.py +484 -0
  1281. vllm/model_executor/models/stablelm.py +354 -0
  1282. vllm/model_executor/models/starcoder2.py +365 -0
  1283. vllm/model_executor/models/step3_text.py +554 -0
  1284. vllm/model_executor/models/step3_vl.py +1147 -0
  1285. vllm/model_executor/models/swin.py +500 -0
  1286. vllm/model_executor/models/tarsier.py +624 -0
  1287. vllm/model_executor/models/telechat2.py +153 -0
  1288. vllm/model_executor/models/teleflm.py +78 -0
  1289. vllm/model_executor/models/terratorch.py +318 -0
  1290. vllm/model_executor/models/transformers/__init__.py +127 -0
  1291. vllm/model_executor/models/transformers/base.py +523 -0
  1292. vllm/model_executor/models/transformers/causal.py +65 -0
  1293. vllm/model_executor/models/transformers/legacy.py +90 -0
  1294. vllm/model_executor/models/transformers/moe.py +329 -0
  1295. vllm/model_executor/models/transformers/multimodal.py +441 -0
  1296. vllm/model_executor/models/transformers/pooling.py +102 -0
  1297. vllm/model_executor/models/transformers/utils.py +253 -0
  1298. vllm/model_executor/models/ultravox.py +786 -0
  1299. vllm/model_executor/models/utils.py +832 -0
  1300. vllm/model_executor/models/vision.py +546 -0
  1301. vllm/model_executor/models/voxtral.py +867 -0
  1302. vllm/model_executor/models/voxtral_streaming.py +304 -0
  1303. vllm/model_executor/models/whisper.py +993 -0
  1304. vllm/model_executor/models/whisper_utils.py +299 -0
  1305. vllm/model_executor/models/zamba2.py +986 -0
  1306. vllm/model_executor/parameter.py +642 -0
  1307. vllm/model_executor/utils.py +113 -0
  1308. vllm/model_executor/warmup/__init__.py +0 -0
  1309. vllm/model_executor/warmup/deep_gemm_warmup.py +371 -0
  1310. vllm/model_executor/warmup/kernel_warmup.py +97 -0
  1311. vllm/model_inspection.py +136 -0
  1312. vllm/multimodal/__init__.py +38 -0
  1313. vllm/multimodal/audio.py +287 -0
  1314. vllm/multimodal/base.py +60 -0
  1315. vllm/multimodal/cache.py +829 -0
  1316. vllm/multimodal/evs.py +294 -0
  1317. vllm/multimodal/hasher.py +123 -0
  1318. vllm/multimodal/image.py +155 -0
  1319. vllm/multimodal/inputs.py +1027 -0
  1320. vllm/multimodal/parse.py +674 -0
  1321. vllm/multimodal/processing.py +2469 -0
  1322. vllm/multimodal/profiling.py +351 -0
  1323. vllm/multimodal/registry.py +375 -0
  1324. vllm/multimodal/utils.py +550 -0
  1325. vllm/multimodal/video.py +512 -0
  1326. vllm/outputs.py +347 -0
  1327. vllm/platforms/__init__.py +277 -0
  1328. vllm/platforms/cpu.py +423 -0
  1329. vllm/platforms/cuda.py +618 -0
  1330. vllm/platforms/interface.py +707 -0
  1331. vllm/platforms/rocm.py +586 -0
  1332. vllm/platforms/tpu.py +20 -0
  1333. vllm/platforms/xpu.py +262 -0
  1334. vllm/plugins/__init__.py +81 -0
  1335. vllm/plugins/io_processors/__init__.py +68 -0
  1336. vllm/plugins/io_processors/interface.py +77 -0
  1337. vllm/plugins/lora_resolvers/__init__.py +0 -0
  1338. vllm/plugins/lora_resolvers/filesystem_resolver.py +52 -0
  1339. vllm/pooling_params.py +229 -0
  1340. vllm/profiler/__init__.py +0 -0
  1341. vllm/profiler/layerwise_profile.py +392 -0
  1342. vllm/profiler/utils.py +151 -0
  1343. vllm/profiler/wrapper.py +241 -0
  1344. vllm/py.typed +2 -0
  1345. vllm/ray/__init__.py +0 -0
  1346. vllm/ray/lazy_utils.py +30 -0
  1347. vllm/ray/ray_env.py +79 -0
  1348. vllm/reasoning/__init__.py +96 -0
  1349. vllm/reasoning/abs_reasoning_parsers.py +318 -0
  1350. vllm/reasoning/basic_parsers.py +175 -0
  1351. vllm/reasoning/deepseek_r1_reasoning_parser.py +67 -0
  1352. vllm/reasoning/deepseek_v3_reasoning_parser.py +69 -0
  1353. vllm/reasoning/ernie45_reasoning_parser.py +165 -0
  1354. vllm/reasoning/glm4_moe_reasoning_parser.py +13 -0
  1355. vllm/reasoning/gptoss_reasoning_parser.py +173 -0
  1356. vllm/reasoning/granite_reasoning_parser.py +363 -0
  1357. vllm/reasoning/holo2_reasoning_parser.py +89 -0
  1358. vllm/reasoning/hunyuan_a13b_reasoning_parser.py +237 -0
  1359. vllm/reasoning/identity_reasoning_parser.py +63 -0
  1360. vllm/reasoning/minimax_m2_reasoning_parser.py +110 -0
  1361. vllm/reasoning/mistral_reasoning_parser.py +154 -0
  1362. vllm/reasoning/olmo3_reasoning_parser.py +302 -0
  1363. vllm/reasoning/qwen3_reasoning_parser.py +67 -0
  1364. vllm/reasoning/seedoss_reasoning_parser.py +27 -0
  1365. vllm/reasoning/step3_reasoning_parser.py +113 -0
  1366. vllm/sampling_params.py +629 -0
  1367. vllm/scalar_type.py +355 -0
  1368. vllm/scripts.py +17 -0
  1369. vllm/sequence.py +64 -0
  1370. vllm/tasks.py +13 -0
  1371. vllm/third_party/__init__.py +0 -0
  1372. vllm/third_party/pynvml.py +6140 -0
  1373. vllm/tokenizers/__init__.py +18 -0
  1374. vllm/tokenizers/deepseek_v32.py +187 -0
  1375. vllm/tokenizers/deepseek_v32_encoding.py +463 -0
  1376. vllm/tokenizers/detokenizer_utils.py +198 -0
  1377. vllm/tokenizers/grok2.py +443 -0
  1378. vllm/tokenizers/hf.py +119 -0
  1379. vllm/tokenizers/mistral.py +543 -0
  1380. vllm/tokenizers/protocol.py +123 -0
  1381. vllm/tokenizers/registry.py +238 -0
  1382. vllm/tool_parsers/__init__.py +158 -0
  1383. vllm/tool_parsers/abstract_tool_parser.py +274 -0
  1384. vllm/tool_parsers/deepseekv31_tool_parser.py +388 -0
  1385. vllm/tool_parsers/deepseekv32_tool_parser.py +591 -0
  1386. vllm/tool_parsers/deepseekv3_tool_parser.py +390 -0
  1387. vllm/tool_parsers/ernie45_tool_parser.py +210 -0
  1388. vllm/tool_parsers/functiongemma_tool_parser.py +321 -0
  1389. vllm/tool_parsers/gigachat3_tool_parser.py +190 -0
  1390. vllm/tool_parsers/glm47_moe_tool_parser.py +23 -0
  1391. vllm/tool_parsers/glm4_moe_tool_parser.py +215 -0
  1392. vllm/tool_parsers/granite_20b_fc_tool_parser.py +273 -0
  1393. vllm/tool_parsers/granite_tool_parser.py +253 -0
  1394. vllm/tool_parsers/hermes_tool_parser.py +495 -0
  1395. vllm/tool_parsers/hunyuan_a13b_tool_parser.py +420 -0
  1396. vllm/tool_parsers/internlm2_tool_parser.py +227 -0
  1397. vllm/tool_parsers/jamba_tool_parser.py +323 -0
  1398. vllm/tool_parsers/kimi_k2_tool_parser.py +598 -0
  1399. vllm/tool_parsers/llama4_pythonic_tool_parser.py +341 -0
  1400. vllm/tool_parsers/llama_tool_parser.py +324 -0
  1401. vllm/tool_parsers/longcat_tool_parser.py +37 -0
  1402. vllm/tool_parsers/minimax_m2_tool_parser.py +776 -0
  1403. vllm/tool_parsers/minimax_tool_parser.py +849 -0
  1404. vllm/tool_parsers/mistral_tool_parser.py +612 -0
  1405. vllm/tool_parsers/olmo3_tool_parser.py +366 -0
  1406. vllm/tool_parsers/openai_tool_parser.py +111 -0
  1407. vllm/tool_parsers/phi4mini_tool_parser.py +120 -0
  1408. vllm/tool_parsers/pythonic_tool_parser.py +332 -0
  1409. vllm/tool_parsers/qwen3coder_tool_parser.py +781 -0
  1410. vllm/tool_parsers/qwen3xml_tool_parser.py +1316 -0
  1411. vllm/tool_parsers/seed_oss_tool_parser.py +744 -0
  1412. vllm/tool_parsers/step3_tool_parser.py +303 -0
  1413. vllm/tool_parsers/utils.py +229 -0
  1414. vllm/tool_parsers/xlam_tool_parser.py +556 -0
  1415. vllm/tracing.py +135 -0
  1416. vllm/transformers_utils/__init__.py +26 -0
  1417. vllm/transformers_utils/chat_templates/__init__.py +5 -0
  1418. vllm/transformers_utils/chat_templates/registry.py +73 -0
  1419. vllm/transformers_utils/chat_templates/template_basic.jinja +3 -0
  1420. vllm/transformers_utils/chat_templates/template_blip2.jinja +11 -0
  1421. vllm/transformers_utils/chat_templates/template_chatml.jinja +10 -0
  1422. vllm/transformers_utils/chat_templates/template_deepseek_ocr.jinja +14 -0
  1423. vllm/transformers_utils/chat_templates/template_deepseek_vl2.jinja +23 -0
  1424. vllm/transformers_utils/chat_templates/template_fuyu.jinja +3 -0
  1425. vllm/transformers_utils/chat_templates/template_minicpmv45.jinja +93 -0
  1426. vllm/transformers_utils/config.py +1169 -0
  1427. vllm/transformers_utils/config_parser_base.py +20 -0
  1428. vllm/transformers_utils/configs/__init__.py +106 -0
  1429. vllm/transformers_utils/configs/afmoe.py +87 -0
  1430. vllm/transformers_utils/configs/arctic.py +216 -0
  1431. vllm/transformers_utils/configs/bagel.py +53 -0
  1432. vllm/transformers_utils/configs/chatglm.py +75 -0
  1433. vllm/transformers_utils/configs/deepseek_vl2.py +126 -0
  1434. vllm/transformers_utils/configs/dotsocr.py +71 -0
  1435. vllm/transformers_utils/configs/eagle.py +90 -0
  1436. vllm/transformers_utils/configs/falcon.py +89 -0
  1437. vllm/transformers_utils/configs/flex_olmo.py +82 -0
  1438. vllm/transformers_utils/configs/hunyuan_vl.py +322 -0
  1439. vllm/transformers_utils/configs/isaac.py +100 -0
  1440. vllm/transformers_utils/configs/jais.py +243 -0
  1441. vllm/transformers_utils/configs/kimi_linear.py +148 -0
  1442. vllm/transformers_utils/configs/kimi_vl.py +38 -0
  1443. vllm/transformers_utils/configs/lfm2_moe.py +163 -0
  1444. vllm/transformers_utils/configs/medusa.py +65 -0
  1445. vllm/transformers_utils/configs/midashenglm.py +103 -0
  1446. vllm/transformers_utils/configs/mistral.py +263 -0
  1447. vllm/transformers_utils/configs/mlp_speculator.py +69 -0
  1448. vllm/transformers_utils/configs/moonvit.py +33 -0
  1449. vllm/transformers_utils/configs/nemotron.py +220 -0
  1450. vllm/transformers_utils/configs/nemotron_h.py +284 -0
  1451. vllm/transformers_utils/configs/olmo3.py +83 -0
  1452. vllm/transformers_utils/configs/ovis.py +182 -0
  1453. vllm/transformers_utils/configs/qwen3_next.py +277 -0
  1454. vllm/transformers_utils/configs/radio.py +98 -0
  1455. vllm/transformers_utils/configs/speculators/__init__.py +2 -0
  1456. vllm/transformers_utils/configs/speculators/algos.py +38 -0
  1457. vllm/transformers_utils/configs/speculators/base.py +114 -0
  1458. vllm/transformers_utils/configs/step3_vl.py +178 -0
  1459. vllm/transformers_utils/configs/tarsier2.py +24 -0
  1460. vllm/transformers_utils/configs/ultravox.py +120 -0
  1461. vllm/transformers_utils/dynamic_module.py +70 -0
  1462. vllm/transformers_utils/gguf_utils.py +280 -0
  1463. vllm/transformers_utils/model_arch_config_convertor.py +402 -0
  1464. vllm/transformers_utils/processor.py +424 -0
  1465. vllm/transformers_utils/processors/__init__.py +25 -0
  1466. vllm/transformers_utils/processors/bagel.py +78 -0
  1467. vllm/transformers_utils/processors/deepseek_ocr.py +438 -0
  1468. vllm/transformers_utils/processors/deepseek_vl2.py +406 -0
  1469. vllm/transformers_utils/processors/hunyuan_vl.py +233 -0
  1470. vllm/transformers_utils/processors/hunyuan_vl_image.py +477 -0
  1471. vllm/transformers_utils/processors/ovis.py +453 -0
  1472. vllm/transformers_utils/processors/ovis2_5.py +468 -0
  1473. vllm/transformers_utils/repo_utils.py +287 -0
  1474. vllm/transformers_utils/runai_utils.py +102 -0
  1475. vllm/transformers_utils/s3_utils.py +95 -0
  1476. vllm/transformers_utils/tokenizer.py +19 -0
  1477. vllm/transformers_utils/utils.py +112 -0
  1478. vllm/triton_utils/__init__.py +20 -0
  1479. vllm/triton_utils/importing.py +103 -0
  1480. vllm/usage/__init__.py +0 -0
  1481. vllm/usage/usage_lib.py +278 -0
  1482. vllm/utils/__init__.py +36 -0
  1483. vllm/utils/argparse_utils.py +491 -0
  1484. vllm/utils/async_utils.py +310 -0
  1485. vllm/utils/cache.py +214 -0
  1486. vllm/utils/collection_utils.py +112 -0
  1487. vllm/utils/counter.py +45 -0
  1488. vllm/utils/deep_gemm.py +424 -0
  1489. vllm/utils/flashinfer.py +602 -0
  1490. vllm/utils/func_utils.py +236 -0
  1491. vllm/utils/gc_utils.py +151 -0
  1492. vllm/utils/hashing.py +117 -0
  1493. vllm/utils/import_utils.py +438 -0
  1494. vllm/utils/jsontree.py +158 -0
  1495. vllm/utils/math_utils.py +32 -0
  1496. vllm/utils/mem_constants.py +13 -0
  1497. vllm/utils/mem_utils.py +285 -0
  1498. vllm/utils/nccl.py +64 -0
  1499. vllm/utils/network_utils.py +331 -0
  1500. vllm/utils/nvtx_pytorch_hooks.py +286 -0
  1501. vllm/utils/platform_utils.py +59 -0
  1502. vllm/utils/profiling.py +56 -0
  1503. vllm/utils/registry.py +51 -0
  1504. vllm/utils/serial_utils.py +214 -0
  1505. vllm/utils/system_utils.py +296 -0
  1506. vllm/utils/tensor_schema.py +255 -0
  1507. vllm/utils/torch_utils.py +781 -0
  1508. vllm/v1/__init__.py +0 -0
  1509. vllm/v1/attention/__init__.py +0 -0
  1510. vllm/v1/attention/backend.py +736 -0
  1511. vllm/v1/attention/backends/__init__.py +0 -0
  1512. vllm/v1/attention/backends/cpu_attn.py +501 -0
  1513. vllm/v1/attention/backends/fa_utils.py +126 -0
  1514. vllm/v1/attention/backends/flash_attn.py +1092 -0
  1515. vllm/v1/attention/backends/flash_attn_diffkv.py +277 -0
  1516. vllm/v1/attention/backends/flashinfer.py +1713 -0
  1517. vllm/v1/attention/backends/flex_attention.py +1024 -0
  1518. vllm/v1/attention/backends/gdn_attn.py +382 -0
  1519. vllm/v1/attention/backends/linear_attn.py +77 -0
  1520. vllm/v1/attention/backends/mamba1_attn.py +28 -0
  1521. vllm/v1/attention/backends/mamba2_attn.py +256 -0
  1522. vllm/v1/attention/backends/mamba_attn.py +313 -0
  1523. vllm/v1/attention/backends/mla/__init__.py +0 -0
  1524. vllm/v1/attention/backends/mla/aiter_triton_mla.py +66 -0
  1525. vllm/v1/attention/backends/mla/common.py +2156 -0
  1526. vllm/v1/attention/backends/mla/cutlass_mla.py +278 -0
  1527. vllm/v1/attention/backends/mla/flashattn_mla.py +348 -0
  1528. vllm/v1/attention/backends/mla/flashinfer_mla.py +175 -0
  1529. vllm/v1/attention/backends/mla/flashmla.py +321 -0
  1530. vllm/v1/attention/backends/mla/flashmla_sparse.py +1021 -0
  1531. vllm/v1/attention/backends/mla/indexer.py +345 -0
  1532. vllm/v1/attention/backends/mla/rocm_aiter_mla.py +284 -0
  1533. vllm/v1/attention/backends/mla/rocm_aiter_mla_sparse.py +321 -0
  1534. vllm/v1/attention/backends/mla/triton_mla.py +171 -0
  1535. vllm/v1/attention/backends/registry.py +258 -0
  1536. vllm/v1/attention/backends/rocm_aiter_fa.py +1000 -0
  1537. vllm/v1/attention/backends/rocm_aiter_unified_attn.py +206 -0
  1538. vllm/v1/attention/backends/rocm_attn.py +405 -0
  1539. vllm/v1/attention/backends/short_conv_attn.py +26 -0
  1540. vllm/v1/attention/backends/tree_attn.py +430 -0
  1541. vllm/v1/attention/backends/triton_attn.py +578 -0
  1542. vllm/v1/attention/backends/utils.py +978 -0
  1543. vllm/v1/attention/ops/__init__.py +0 -0
  1544. vllm/v1/attention/ops/chunked_prefill_paged_decode.py +459 -0
  1545. vllm/v1/attention/ops/common.py +469 -0
  1546. vllm/v1/attention/ops/flashmla.py +254 -0
  1547. vllm/v1/attention/ops/merge_attn_states.py +47 -0
  1548. vllm/v1/attention/ops/paged_attn.py +51 -0
  1549. vllm/v1/attention/ops/pallas_kv_cache_update.py +130 -0
  1550. vllm/v1/attention/ops/prefix_prefill.py +862 -0
  1551. vllm/v1/attention/ops/rocm_aiter_mla_sparse.py +210 -0
  1552. vllm/v1/attention/ops/triton_decode_attention.py +709 -0
  1553. vllm/v1/attention/ops/triton_merge_attn_states.py +116 -0
  1554. vllm/v1/attention/ops/triton_prefill_attention.py +272 -0
  1555. vllm/v1/attention/ops/triton_reshape_and_cache_flash.py +395 -0
  1556. vllm/v1/attention/ops/triton_unified_attention.py +1088 -0
  1557. vllm/v1/attention/ops/vit_attn_wrappers.py +185 -0
  1558. vllm/v1/attention/selector.py +145 -0
  1559. vllm/v1/core/__init__.py +0 -0
  1560. vllm/v1/core/block_pool.py +489 -0
  1561. vllm/v1/core/encoder_cache_manager.py +402 -0
  1562. vllm/v1/core/kv_cache_coordinator.py +560 -0
  1563. vllm/v1/core/kv_cache_manager.py +485 -0
  1564. vllm/v1/core/kv_cache_metrics.py +96 -0
  1565. vllm/v1/core/kv_cache_utils.py +1642 -0
  1566. vllm/v1/core/sched/__init__.py +0 -0
  1567. vllm/v1/core/sched/async_scheduler.py +66 -0
  1568. vllm/v1/core/sched/interface.py +205 -0
  1569. vllm/v1/core/sched/output.py +261 -0
  1570. vllm/v1/core/sched/request_queue.py +208 -0
  1571. vllm/v1/core/sched/scheduler.py +1936 -0
  1572. vllm/v1/core/sched/utils.py +64 -0
  1573. vllm/v1/core/single_type_kv_cache_manager.py +926 -0
  1574. vllm/v1/cudagraph_dispatcher.py +183 -0
  1575. vllm/v1/engine/__init__.py +224 -0
  1576. vllm/v1/engine/async_llm.py +874 -0
  1577. vllm/v1/engine/coordinator.py +396 -0
  1578. vllm/v1/engine/core.py +1614 -0
  1579. vllm/v1/engine/core_client.py +1422 -0
  1580. vllm/v1/engine/detokenizer.py +351 -0
  1581. vllm/v1/engine/exceptions.py +18 -0
  1582. vllm/v1/engine/input_processor.py +713 -0
  1583. vllm/v1/engine/llm_engine.py +415 -0
  1584. vllm/v1/engine/logprobs.py +245 -0
  1585. vllm/v1/engine/output_processor.py +715 -0
  1586. vllm/v1/engine/parallel_sampling.py +150 -0
  1587. vllm/v1/engine/utils.py +1086 -0
  1588. vllm/v1/executor/__init__.py +6 -0
  1589. vllm/v1/executor/abstract.py +352 -0
  1590. vllm/v1/executor/multiproc_executor.py +888 -0
  1591. vllm/v1/executor/ray_distributed_executor.py +8 -0
  1592. vllm/v1/executor/ray_executor.py +623 -0
  1593. vllm/v1/executor/ray_utils.py +468 -0
  1594. vllm/v1/executor/uniproc_executor.py +186 -0
  1595. vllm/v1/kv_cache_interface.py +485 -0
  1596. vllm/v1/kv_offload/__init__.py +0 -0
  1597. vllm/v1/kv_offload/abstract.py +161 -0
  1598. vllm/v1/kv_offload/arc_manager.py +237 -0
  1599. vllm/v1/kv_offload/backend.py +97 -0
  1600. vllm/v1/kv_offload/backends/__init__.py +0 -0
  1601. vllm/v1/kv_offload/backends/cpu.py +62 -0
  1602. vllm/v1/kv_offload/cpu.py +109 -0
  1603. vllm/v1/kv_offload/factory.py +58 -0
  1604. vllm/v1/kv_offload/lru_manager.py +139 -0
  1605. vllm/v1/kv_offload/mediums.py +39 -0
  1606. vllm/v1/kv_offload/spec.py +70 -0
  1607. vllm/v1/kv_offload/worker/__init__.py +0 -0
  1608. vllm/v1/kv_offload/worker/cpu_gpu.py +287 -0
  1609. vllm/v1/kv_offload/worker/worker.py +163 -0
  1610. vllm/v1/metrics/__init__.py +0 -0
  1611. vllm/v1/metrics/loggers.py +1320 -0
  1612. vllm/v1/metrics/perf.py +1244 -0
  1613. vllm/v1/metrics/prometheus.py +82 -0
  1614. vllm/v1/metrics/ray_wrappers.py +194 -0
  1615. vllm/v1/metrics/reader.py +257 -0
  1616. vllm/v1/metrics/stats.py +440 -0
  1617. vllm/v1/outputs.py +242 -0
  1618. vllm/v1/pool/__init__.py +0 -0
  1619. vllm/v1/pool/metadata.py +124 -0
  1620. vllm/v1/request.py +281 -0
  1621. vllm/v1/sample/__init__.py +0 -0
  1622. vllm/v1/sample/logits_processor/__init__.py +352 -0
  1623. vllm/v1/sample/logits_processor/builtin.py +278 -0
  1624. vllm/v1/sample/logits_processor/interface.py +106 -0
  1625. vllm/v1/sample/logits_processor/state.py +165 -0
  1626. vllm/v1/sample/metadata.py +44 -0
  1627. vllm/v1/sample/ops/__init__.py +0 -0
  1628. vllm/v1/sample/ops/bad_words.py +57 -0
  1629. vllm/v1/sample/ops/logprobs.py +25 -0
  1630. vllm/v1/sample/ops/penalties.py +57 -0
  1631. vllm/v1/sample/ops/topk_topp_sampler.py +388 -0
  1632. vllm/v1/sample/rejection_sampler.py +822 -0
  1633. vllm/v1/sample/sampler.py +319 -0
  1634. vllm/v1/sample/tpu/__init__.py +0 -0
  1635. vllm/v1/sample/tpu/metadata.py +120 -0
  1636. vllm/v1/sample/tpu/sampler.py +215 -0
  1637. vllm/v1/serial_utils.py +514 -0
  1638. vllm/v1/spec_decode/__init__.py +0 -0
  1639. vllm/v1/spec_decode/eagle.py +1346 -0
  1640. vllm/v1/spec_decode/medusa.py +73 -0
  1641. vllm/v1/spec_decode/metadata.py +66 -0
  1642. vllm/v1/spec_decode/metrics.py +225 -0
  1643. vllm/v1/spec_decode/ngram_proposer.py +281 -0
  1644. vllm/v1/spec_decode/suffix_decoding.py +95 -0
  1645. vllm/v1/spec_decode/utils.py +109 -0
  1646. vllm/v1/structured_output/__init__.py +337 -0
  1647. vllm/v1/structured_output/backend_guidance.py +291 -0
  1648. vllm/v1/structured_output/backend_lm_format_enforcer.py +177 -0
  1649. vllm/v1/structured_output/backend_outlines.py +324 -0
  1650. vllm/v1/structured_output/backend_types.py +136 -0
  1651. vllm/v1/structured_output/backend_xgrammar.py +378 -0
  1652. vllm/v1/structured_output/request.py +91 -0
  1653. vllm/v1/structured_output/utils.py +457 -0
  1654. vllm/v1/utils.py +466 -0
  1655. vllm/v1/worker/__init__.py +0 -0
  1656. vllm/v1/worker/block_table.py +343 -0
  1657. vllm/v1/worker/cp_utils.py +42 -0
  1658. vllm/v1/worker/cpu_model_runner.py +122 -0
  1659. vllm/v1/worker/cpu_worker.py +192 -0
  1660. vllm/v1/worker/dp_utils.py +240 -0
  1661. vllm/v1/worker/ec_connector_model_runner_mixin.py +85 -0
  1662. vllm/v1/worker/gpu/README.md +4 -0
  1663. vllm/v1/worker/gpu/__init__.py +0 -0
  1664. vllm/v1/worker/gpu/async_utils.py +98 -0
  1665. vllm/v1/worker/gpu/attn_utils.py +183 -0
  1666. vllm/v1/worker/gpu/block_table.py +222 -0
  1667. vllm/v1/worker/gpu/buffer_utils.py +224 -0
  1668. vllm/v1/worker/gpu/cudagraph_utils.py +264 -0
  1669. vllm/v1/worker/gpu/dp_utils.py +31 -0
  1670. vllm/v1/worker/gpu/input_batch.py +526 -0
  1671. vllm/v1/worker/gpu/metrics/__init__.py +0 -0
  1672. vllm/v1/worker/gpu/metrics/logits.py +42 -0
  1673. vllm/v1/worker/gpu/mm/__init__.py +0 -0
  1674. vllm/v1/worker/gpu/mm/mrope_utils.py +127 -0
  1675. vllm/v1/worker/gpu/model_runner.py +1005 -0
  1676. vllm/v1/worker/gpu/sample/__init__.py +0 -0
  1677. vllm/v1/worker/gpu/sample/gumbel.py +106 -0
  1678. vllm/v1/worker/gpu/sample/logit_bias.py +270 -0
  1679. vllm/v1/worker/gpu/sample/logprob.py +167 -0
  1680. vllm/v1/worker/gpu/sample/metadata.py +79 -0
  1681. vllm/v1/worker/gpu/sample/min_p.py +58 -0
  1682. vllm/v1/worker/gpu/sample/output.py +14 -0
  1683. vllm/v1/worker/gpu/sample/penalties.py +155 -0
  1684. vllm/v1/worker/gpu/sample/sampler.py +88 -0
  1685. vllm/v1/worker/gpu/spec_decode/__init__.py +18 -0
  1686. vllm/v1/worker/gpu/spec_decode/eagle.py +566 -0
  1687. vllm/v1/worker/gpu/spec_decode/eagle_cudagraph.py +115 -0
  1688. vllm/v1/worker/gpu/spec_decode/rejection_sample.py +71 -0
  1689. vllm/v1/worker/gpu/states.py +282 -0
  1690. vllm/v1/worker/gpu/structured_outputs.py +100 -0
  1691. vllm/v1/worker/gpu_input_batch.py +1030 -0
  1692. vllm/v1/worker/gpu_model_runner.py +5761 -0
  1693. vllm/v1/worker/gpu_ubatch_wrapper.py +475 -0
  1694. vllm/v1/worker/gpu_worker.py +968 -0
  1695. vllm/v1/worker/kv_connector_model_runner_mixin.py +300 -0
  1696. vllm/v1/worker/lora_model_runner_mixin.py +225 -0
  1697. vllm/v1/worker/tpu_input_batch.py +574 -0
  1698. vllm/v1/worker/tpu_worker.py +18 -0
  1699. vllm/v1/worker/ubatch_utils.py +112 -0
  1700. vllm/v1/worker/ubatching.py +242 -0
  1701. vllm/v1/worker/utils.py +400 -0
  1702. vllm/v1/worker/worker_base.py +372 -0
  1703. vllm/v1/worker/workspace.py +253 -0
  1704. vllm/v1/worker/xpu_model_runner.py +48 -0
  1705. vllm/v1/worker/xpu_worker.py +174 -0
  1706. vllm/version.py +39 -0
  1707. vllm/vllm_flash_attn/.gitkeep +0 -0
  1708. vllm_cpu_avx512bf16-0.14.0.dist-info/METADATA +348 -0
  1709. vllm_cpu_avx512bf16-0.14.0.dist-info/RECORD +1712 -0
  1710. vllm_cpu_avx512bf16-0.14.0.dist-info/WHEEL +5 -0
  1711. vllm_cpu_avx512bf16-0.14.0.dist-info/entry_points.txt +5 -0
  1712. vllm_cpu_avx512bf16-0.14.0.dist-info/top_level.txt +1 -0
@@ -0,0 +1,1712 @@
1
+ vllm/_C.abi3.so,sha256=vsL3bNe2qtU7wvUwa7w4cLTR1-k8vvwm5PEY7XTR5no,102459192
2
+ vllm/__init__.py,sha256=xSE2I9WhdAKvVQw2EPoRoyah9Z3ETDTul7kg-YAF6eQ,8548
3
+ vllm/_aiter_ops.py,sha256=g6xpKcMar4yJSCN2bwqOcWfDSXTJ2Kj1z6Be5r4H0j4,47461
4
+ vllm/_bc_linter.py,sha256=2F7ZE_cba80XNDfbrZKVBunazE7ZDxVMtpOUdEFdH3w,1105
5
+ vllm/_custom_ops.py,sha256=ANnB4CesahaPounw4zvhZ9wzzGN85qRWMMEvv22RWJ8,95424
6
+ vllm/_ipex_ops.py,sha256=adGstDfkADoKtXgtllXGq9yAP8eblDzO7aTue21KPt4,14627
7
+ vllm/_version.py,sha256=Byw420VruQzJ1exmj6PcZ9zpcSTgfBRBp5ZU4O6rwSc,706
8
+ vllm/beam_search.py,sha256=XUQRXltedVFtJRp43dKHKn87VqKeG5tr494D0yHemHM,2593
9
+ vllm/collect_env.py,sha256=7peWZtL6DVINkwdvI59rI7mHs0WfT3WEvlbsSjzeNow,28050
10
+ vllm/connections.py,sha256=LpQUe9gGRiBCIGY6RWUGi_7d8ql6tO2jYNecU1EJR6c,5350
11
+ vllm/env_override.py,sha256=Yg10EBdFOX1G8tO0_u4SMjhhTI6EiFAnsgkAx7u65EQ,14862
12
+ vllm/envs.py,sha256=7bxaifRWpZ9Bc8rw6rg4uNPsw-WQFio4Wgk5BG3M2dc,80982
13
+ vllm/exceptions.py,sha256=AtRlqcG-WMiNYd_W1uJsbHdRoJusuBTWHAfpUru1NkQ,1067
14
+ vllm/forward_context.py,sha256=g9dT7r4tTk4w7C_K63yHpBfrSwpVTuFDxf2-h8YR7c4,14102
15
+ vllm/logger.py,sha256=MKTGXLH3ench_iMRlNAa8jh5eZPYGZ87nOQpKaSz05M,10519
16
+ vllm/logits_process.py,sha256=LrREP4uv0gPh2VQcG4t-4hedJoRoJWkywUAMOIrG-VE,4340
17
+ vllm/logprobs.py,sha256=uHUJbySQJ02OFp-kgr0gB_ZXnfuAm6SDHwHZ-rRQlqI,7907
18
+ vllm/model_inspection.py,sha256=99U1s9FBinjggNPt5NvHvabMcIh3IK_dnXLgbFYC_jc,4743
19
+ vllm/outputs.py,sha256=O6CiZA6IhmxLh-y3HGqwz5L7RFfcpokZdWmT9MvIY9Q,12651
20
+ vllm/pooling_params.py,sha256=dMVNQW0-pE8Wcg--JLzZ7e5cndkK_2AZqETvM_JbkWQ,8723
21
+ vllm/py.typed,sha256=F5LUrt0voM87SNuuOky2X9veCVDqJUgRg_VohYqDigY,65
22
+ vllm/sampling_params.py,sha256=ecXiYY3BRdZEuOZjKRB9Z3FyW9qgAlI-mv1DI-30FC0,25795
23
+ vllm/scalar_type.py,sha256=s8CZpZru6-4vEexIofKsJzhw5OBjVuvueG6b6yb6A94,12573
24
+ vllm/scripts.py,sha256=d2RU3e6Qi_xY7QUD44uqsdz8DdBR-_zQnFf4rYUW_iw,504
25
+ vllm/sequence.py,sha256=q10MDnLiFsnhKuuKBeIrQ6Pyj9LpGzVcHKnm-1uK0YI,2173
26
+ vllm/tasks.py,sha256=sCAS2Xy9YoGCC1VRL3j1nxnyVEQ6N0FIDh9j9i2t50c,490
27
+ vllm/tracing.py,sha256=BaBpIGie6_A-ee_XEzu_-aGWkGt_stgeq_b1M3Q8kb0,5043
28
+ vllm/version.py,sha256=vXpCd2tjC2EeL1-kaYvJfh9PJYPDXMskbsLnvUPIMxM,1339
29
+ vllm/assets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
30
+ vllm/assets/audio.py,sha256=gDEsheV3FDEIX9U5xGdllwMYB1qF5_QYpU8Fj36zkP4,1185
31
+ vllm/assets/base.py,sha256=SErfS4p7zJUe_sJBBwR539_1dy49vsBwl0tAi5aPRHY,1215
32
+ vllm/assets/image.py,sha256=-iG11Cmp12EOsUKN4wTrkHm5sHQojMQO3Cg9RolzfT0,1576
33
+ vllm/assets/video.py,sha256=7ulapb3jq2MqKxEVrhzPWgIbcv-CDEfjYMA1cSWPa4E,4487
34
+ vllm/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
35
+ vllm/attention/layer.py,sha256=rAnGeZSK1w2KQ_qQo1cd7nHbASIr85c7NL_S4IADhqU,33812
36
+ vllm/attention/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
37
+ vllm/attention/utils/kv_sharing_utils.py,sha256=o4YaEd_bjYU6fQq0L5dEdhz9r4aZP1uJ6RBrVwtdX4M,1615
38
+ vllm/attention/utils/kv_transfer_utils.py,sha256=-dUtRw8Zu1hBTcMuemUe3zQjzjQ5UeN2gndokVENtuU,2009
39
+ vllm/benchmarks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
40
+ vllm/benchmarks/datasets.py,sha256=kwUNYwtn4Iw0rj_lloMf4ZGGAE9F8oZb9IEOmqesN3U,122143
41
+ vllm/benchmarks/latency.py,sha256=S-LAXVvNOdfRJRVj4KtX0WVRIdyD6-l7BOnzCfkB_1I,5837
42
+ vllm/benchmarks/mm_processor.py,sha256=0sOor_DWpnQu_C2XDV5hHVzfFvX3IQ-OWpujNHc4ZXA,10959
43
+ vllm/benchmarks/serve.py,sha256=nNtarTbE2OM_-22ULx_nOySiX5mWyDq3fB6L-hVyXpk,65199
44
+ vllm/benchmarks/startup.py,sha256=LdKXMn38Iv0EsUc80aYH9fYpB_h9nXyuhc7RzPtQ_IE,11735
45
+ vllm/benchmarks/throughput.py,sha256=Kp14mTYV8cf1vcabXar15tWlCfRG5KdQ3HM3vJocwPE,34962
46
+ vllm/benchmarks/lib/__init__.py,sha256=BlbNrv7ga0LXYeHLKKiey2woiGh5MkW36g7QG6L6BN0,142
47
+ vllm/benchmarks/lib/endpoint_request_func.py,sha256=6JoTGH3VnTu6IaFusduLvZhBS8dQcnkQmwlxM7ojbQQ,26362
48
+ vllm/benchmarks/lib/ready_checker.py,sha256=QXyydJaq4m1EFdHtpuobeHykIKnwgOawe-ZZbS-jweM,2346
49
+ vllm/benchmarks/lib/utils.py,sha256=YMFxp0A81__5oZJ8wp-PyqOlbYGuxovcVMZzR6v9XJo,2449
50
+ vllm/benchmarks/sweep/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
51
+ vllm/benchmarks/sweep/cli.py,sha256=bqyJ0NJrCW46-ENf_XHHdXtR0tyKkVdI-yIyIZ5L76g,1337
52
+ vllm/benchmarks/sweep/param_sweep.py,sha256=7fOlYnrpnZc6kMxfAW203AFHADSugT-wlR3ajaRuWls,5594
53
+ vllm/benchmarks/sweep/plot.py,sha256=tTdrMIbQGoEupWq_HbS3Ogq_BJo0DqauN2crcCB_iDs,19677
54
+ vllm/benchmarks/sweep/plot_pareto.py,sha256=MnyM4Lyw-eWe9bIkWXH9Bmgy3gBAkY63JYfhrNVfbU8,10959
55
+ vllm/benchmarks/sweep/serve.py,sha256=tzubjp_CNwpwvWYUEKqPXTRwuzTkce0D-xRTK-hn_wM,13180
56
+ vllm/benchmarks/sweep/serve_sla.py,sha256=tNVsZesRcxzcg2UCSQS1LtQk3U_WgMhtRlgtSdU_wJ8,13553
57
+ vllm/benchmarks/sweep/server.py,sha256=QAT4ixDPla1lCbWcKMPksQj5fM5uiAOq7HWsrU94Bpw,3588
58
+ vllm/benchmarks/sweep/sla_sweep.py,sha256=a3BeHW0weUk-Jo7LOJz9eBBBnbNBgMEZq_qvLAxCXF0,3915
59
+ vllm/benchmarks/sweep/utils.py,sha256=YzhiqE4jmEN7TzUnzQXnlm8TLERkNjgoQ_SF6jJ8hB4,232
60
+ vllm/compilation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
61
+ vllm/compilation/activation_quant_fusion.py,sha256=YIlNxG2qc4jVaX0BGsNYmxjXsOLMr2zM4be74c_f9r8,6867
62
+ vllm/compilation/backends.py,sha256=HgMM5Gi7DWS6yUiAQvItX55o4YhLSJC-tjdjf_2HiAQ,32407
63
+ vllm/compilation/base_static_graph.py,sha256=XP6OBtuEqkLNQc3ZPr6TrwCzokLIARBCBXUw4pIrUjo,2007
64
+ vllm/compilation/caching.py,sha256=5uTr0gMk9eRKA_CE3-ltitc3UT1PF4kK2WnNAQRRi9E,7421
65
+ vllm/compilation/collective_fusion.py,sha256=WceelKpEnulgfKRMsndJ56Y0TWGEFnmIdhoSUxmeEFg,44669
66
+ vllm/compilation/compiler_interface.py,sha256=mRuOcYX10ImBMRAxTvec65JhM8ASYRt6rPq63nCkM-g,24788
67
+ vllm/compilation/counter.py,sha256=WiKJRLbgqBchplITJ7FrpZ54f6A87829K8VJa1un6hA,1735
68
+ vllm/compilation/cuda_graph.py,sha256=H--9XKsA_qn9e6fO2geIlNwwU_8mlYibyf3Rups1DJ0,12146
69
+ vllm/compilation/decorators.py,sha256=k7w4RdX24WxuEzupfmVo4c2dMAdO3uN0H2EIX48rDf0,26075
70
+ vllm/compilation/fix_functionalization.py,sha256=a1RQJZLKZ8NOdnmG3lCBJrV2acYSQqQHn6wD7xezCFo,11108
71
+ vllm/compilation/fusion.py,sha256=NvFKNzFo4AsiK2IqQsIoBsbm10TYDkGchhsY9izblsg,19979
72
+ vllm/compilation/fusion_attn.py,sha256=UXeZfcB4r0Ju8uVPnfy0fcF5pIxvVhnqaApKPkdwjbg,12649
73
+ vllm/compilation/fx_utils.py,sha256=kdt_INA40pcxQFwsZijBYE344i-8Wo1sMtoJp3LI188,3195
74
+ vllm/compilation/inductor_pass.py,sha256=jTWO7vY8lCqscpGGB43aX58KezeH2dnZmApasakK4jQ,4361
75
+ vllm/compilation/matcher_utils.py,sha256=aRqbZQxt-3UE8CNcrA6LC57Y6pnuxBnjte56OEZcQCg,14892
76
+ vllm/compilation/monitor.py,sha256=96N-Qq15Bwrrl6q2M7RgGRnSV2TLVRyBr1VxvycDcHY,2132
77
+ vllm/compilation/noop_elimination.py,sha256=_7WGrP8Nq5cParkCYCuGkesAXN3AZvTafON7vHFi5us,5285
78
+ vllm/compilation/partition_rules.py,sha256=hX0vsG3IceodNxfNAfvU5SBZhBANmLe3Kikz1v8c-k0,2296
79
+ vllm/compilation/pass_manager.py,sha256=AmCB4zHTcBYEPfJIhoT5_mNtsasGYeUKdpYx03VeGts,6140
80
+ vllm/compilation/piecewise_backend.py,sha256=KTCI_0dEodOu3SOiJ5hNZN6A6j-9Xe4UHaY1kefYBDo,7679
81
+ vllm/compilation/post_cleanup.py,sha256=z0Jbq_dQDFzRTrUZUcvE5prvDUxQ7ItogQrEnYdxVzE,758
82
+ vllm/compilation/qk_norm_rope_fusion.py,sha256=gT8ab-MCtuztGAmnxurq2o3SAg6PXH3UESd5FO0pTbo,8878
83
+ vllm/compilation/rocm_aiter_fusion.py,sha256=SDGd9FMR1dSIV1Sua-uMJOuPW-J4xfkyj2cut9KlhJs,13363
84
+ vllm/compilation/sequence_parallelism.py,sha256=yzclZxDS0KO4de2ytkXuF_P5fXLnjB22HxCu2ynU05Q,14640
85
+ vllm/compilation/torch25_custom_graph_pass.py,sha256=YauSt-1iZFoCjl-vxHA_q0ZK0cX1dSqs8v6UXNlXhDY,1454
86
+ vllm/compilation/vllm_inductor_pass.py,sha256=JcsztOiPeFIIdSeiKesbcsQBfbqnOt5mNqf9BKCXDpM,6783
87
+ vllm/compilation/wrapper.py,sha256=en_FPtoWpwHKDPHHPgEfH5DyUivNTW3NdRGjV7u9MNw,13434
88
+ vllm/config/__init__.py,sha256=-DLv5RNr9iWlRxkuxDGIgZlT3gcpguy-MAUAMWW-D4w,3348
89
+ vllm/config/attention.py,sha256=Ze0eRA7KuJHLVyI_fdrm9h4gJxGy7q84gFSNm5JKu-o,4436
90
+ vllm/config/cache.py,sha256=tetNdE-w6IAtGhRpfu6ELLm-8csQOuMmFfUt4x45ZWo,11099
91
+ vllm/config/compilation.py,sha256=BbgF3SYhmKiWNfjHvxbQt3hg3zwT7dy07ExADPeEPUc,48579
92
+ vllm/config/device.py,sha256=Ilhly88mxXGjDAD6iDRqg4pbBEJKX8OSu-IKqi3RyCc,2773
93
+ vllm/config/ec_transfer.py,sha256=_D5VNYNy8CU7IrTkDm9IB5PF9Y4CBCqzyijl-kYgWpk,3863
94
+ vllm/config/kv_events.py,sha256=-JSREpsV49ohD7songzjiHiLhJguL2v1r4_cx7po--0,1645
95
+ vllm/config/kv_transfer.py,sha256=KK29k_JPFjzAFMCIhXdiiV6t1LBux-05BKlcxI9TF6Y,4314
96
+ vllm/config/load.py,sha256=B3pHwaKzjaIDKXvXr5JLNHsoL0lHCx2xXN5GQ2anJN0,5751
97
+ vllm/config/lora.py,sha256=UVZFR1WPRY_z2f5w4Yp3PRCQ7UAfXKIVEX9zqYi1Yjc,4077
98
+ vllm/config/model.py,sha256=u4piklS3VvAwzLGAj3LfCp5TfiKuNkUhBEmTRI2WDJw,81827
99
+ vllm/config/model_arch.py,sha256=Z10j3I3r851inz9mivcErhNMtINjAMMGpaMpb318PKQ,1658
100
+ vllm/config/multimodal.py,sha256=1gESUs41ztPxawuAqkh-whZhi_Nipf-U2LNW_yZ4ZR4,9991
101
+ vllm/config/observability.py,sha256=KEmGqoRZlS8mX9euM9xnDWOU5zjIlfxCL-hYm54GtZw,6544
102
+ vllm/config/parallel.py,sha256=BnOBHU83BY0Pm-FDzhE7Ma1H6QvXTBrtrVHPp8xE1s0,29418
103
+ vllm/config/pooler.py,sha256=J-OQfSdBL4no-cnRErGg6zmDFs38WqOYDeSkRMwA3IY,6659
104
+ vllm/config/profiler.py,sha256=loMUwc2QGZ2IDkg1GJBN8aybU36YjJDrDEMqFi63Z1w,7600
105
+ vllm/config/scheduler.py,sha256=aq7PaTv5ZpW_P7q2bTFMo9SVC-TjRLKF08KutdUTV1g,12509
106
+ vllm/config/speculative.py,sha256=LZn_YMmYy83tN5X7rcekwAGwbFdHUamiqI5X0Bce0oE,29245
107
+ vllm/config/speech_to_text.py,sha256=QSVuEYFSu8vC5mzYB7PTRIOW9ylxMo8TrLg__avSTj4,1541
108
+ vllm/config/structured_outputs.py,sha256=4LSQVBGKoh7-vTN64z0rWHKHgkU9l9Yb5pYVP11lVck,3350
109
+ vllm/config/utils.py,sha256=1YUZXk3-Dx4U1FQlTYsPJzi-Ig3jfoMOtf57mE5JcBM,12651
110
+ vllm/config/vllm.py,sha256=k3v9NG8mKjSy4uPGDvjAzgSQfHu2xG5gpn__FakTHlA,64213
111
+ vllm/device_allocator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
112
+ vllm/device_allocator/cumem.py,sha256=2itL8dIqAIY8tkeNvFh6jHRqN6aZuYKXhJ4d1THDvxU,11525
113
+ vllm/distributed/__init__.py,sha256=l_KMMLMmYq-MqxY5OeTuQjA38RYwdS4TtVy8JafQq3E,191
114
+ vllm/distributed/communication_op.py,sha256=PD-Kxg2zjs6JHTncHi9vGUetQ4aFiT0uV3fQcjIL0bg,1323
115
+ vllm/distributed/kv_events.py,sha256=3bmlAbLZi1BHvRb-QqMDx2ziBVFLy3ABV3urjNohaMo,16094
116
+ vllm/distributed/parallel_state.py,sha256=x3WU4IJOyMMA1J56McgrmHeolIfp14B5IY7PKeJXBTs,65970
117
+ vllm/distributed/utils.py,sha256=Q9_wTnhTgMQWk3cPYdGFQJdg4B6VyFVeoCPigIKPfXs,20792
118
+ vllm/distributed/device_communicators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
119
+ vllm/distributed/device_communicators/all2all.py,sha256=1sXwMFxSRQhArct-1PVUYoXVNPzszYu6RpbbAsq94eo,16996
120
+ vllm/distributed/device_communicators/all_reduce_utils.py,sha256=FXN49WKCqJM3WKxMlQntN1xVwrlss5IjrGRXjfIaoYY,12324
121
+ vllm/distributed/device_communicators/base_device_communicator.py,sha256=HHXFXHxxV056E47aZZk0DiCjiVhm4qkQvPt6dwFT9P8,11027
122
+ vllm/distributed/device_communicators/cpu_communicator.py,sha256=IyRrYtDIw9suqbBxpKBYgvKOKdEk7egpnOeQtk3keQ0,6966
123
+ vllm/distributed/device_communicators/cuda_communicator.py,sha256=UxufdOVffylDff6HFrNM6D9ML1Fj1_lXWocWRCikdDM,13652
124
+ vllm/distributed/device_communicators/cuda_wrapper.py,sha256=N1znzgx_UgCm5XLXVnKdtmtMcguhmFE0B6lxCPoVcGY,7483
125
+ vllm/distributed/device_communicators/custom_all_reduce.py,sha256=qwIMODFiNFmXGFWjr9wyzXZ6dl6WASbya1wEqAEmXP0,12857
126
+ vllm/distributed/device_communicators/mnnvl_compat.py,sha256=A5UvRWaIyPRQkw4dSd4Mq6sy2I655Wf0bHkKM7aPMZc,830
127
+ vllm/distributed/device_communicators/pynccl.py,sha256=IZRiSwMlWK-yS5cwGBPr7kn4Ov4XSVhA61aVP5ggpxs,13902
128
+ vllm/distributed/device_communicators/pynccl_allocator.py,sha256=D4IyD8MX76loodZhzbsHSmtT0LLoyhcZbIMFN_BZVMU,6260
129
+ vllm/distributed/device_communicators/pynccl_wrapper.py,sha256=u77fixgqULrkTkPibJwClzPJEBJvyuq3OfEediA-Ak0,18959
130
+ vllm/distributed/device_communicators/quick_all_reduce.py,sha256=BU5G_-FaMmper_qOYtsA8ViItWNE0u8XUlwoORUX1cw,10903
131
+ vllm/distributed/device_communicators/ray_communicator.py,sha256=Myw39lSVtgVk1h21m8LTDKAjatwzRC0BRkeQvemuyJc,9122
132
+ vllm/distributed/device_communicators/shm_broadcast.py,sha256=GWRAf6JMUeQnUwopegfKNUoFbhQqM-4cMdsVoT-IgxM,32448
133
+ vllm/distributed/device_communicators/shm_object_storage.py,sha256=4OET8UnO1l2u24FmndJS9JEqnp30gs94lpO3S60Se4g,27538
134
+ vllm/distributed/device_communicators/symm_mem.py,sha256=fgc15QF836cFul6AQ8dJDI-xw8P5_wK8qLnczYOoHV0,5395
135
+ vllm/distributed/device_communicators/xpu_communicator.py,sha256=B4muxSL7kFxv5P2igHTp_T6GxpHuLtNSQAjr1qnV4vA,3542
136
+ vllm/distributed/ec_transfer/__init__.py,sha256=TfKcHCVJ27cpYAxvVMFyrBZe40qJfxEX6GeWdCOcIoc,348
137
+ vllm/distributed/ec_transfer/ec_transfer_state.py,sha256=60Iu-N4qVnjSa2kXaysANPa77HX-cYomPTu7GRk5Evw,1152
138
+ vllm/distributed/ec_transfer/ec_connector/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
139
+ vllm/distributed/ec_transfer/ec_connector/base.py,sha256=L6ZTjzL6kIXUyRVsA6ldI4AahpRSbEL3NAMTqwJJf60,8029
140
+ vllm/distributed/ec_transfer/ec_connector/example_connector.py,sha256=2caIwQEovSjVAdjB1cqXXh4US54H5yfsgkOjVTrzmyY,7345
141
+ vllm/distributed/ec_transfer/ec_connector/factory.py,sha256=LRo-mSc6_mm5a9WjcHTxzSO7Lds7HrLHYLdkCpWfmKs,3070
142
+ vllm/distributed/eplb/__init__.py,sha256=G5wu4iq7WIjDVMWqAfCUTyU-XiThNdAZd4OYu-SVpig,154
143
+ vllm/distributed/eplb/async_worker.py,sha256=79rQX-RPHMpkjLrAzE8xdd3f5HC-yD3RDpJhTDuj3Tc,4208
144
+ vllm/distributed/eplb/eplb_state.py,sha256=OmvWtUPa0FHqy40sUUrQKB6TSsEvisxv5UfGyOJQvlo,46963
145
+ vllm/distributed/eplb/rebalance_execute.py,sha256=vHAVgmQ33EwKXFZa-MbVPKyHig0autfONAHJef0X9yw,27949
146
+ vllm/distributed/eplb/policy/__init__.py,sha256=2usmbIhEKDKxq4yMTMBkiRs4uem6AK6jJPkmyH3G034,542
147
+ vllm/distributed/eplb/policy/abstract.py,sha256=xkphHsTmcIZSkrw5_CbMhxDiZsDMSEYqVGL9QW4jHcE,1624
148
+ vllm/distributed/eplb/policy/default.py,sha256=TOe_1Vy5dxCau9rVn3uH9RQP7UXJJ2KjA8Ya0m9tDIs,16382
149
+ vllm/distributed/kv_transfer/README.md,sha256=cKIw6vXYSxBlf0wWwO7haP82CX2oB2QzW0-RxZE5mT4,2007
150
+ vllm/distributed/kv_transfer/__init__.py,sha256=wb5OWOxpI7rmB6NVrSKJHHQPBWpp_3NYseEOo_0mgOo,552
151
+ vllm/distributed/kv_transfer/disagg_prefill_workflow.jpg,sha256=fOFUEx-2Fm1uxHCGopvCREaRqdvR87Z7C0bMqEVH3Iw,142656
152
+ vllm/distributed/kv_transfer/kv_transfer_state.py,sha256=jFrtqPkifgETZZpoqUzdJhK74GMRWnxRCv_mZC4C99w,2290
153
+ vllm/distributed/kv_transfer/kv_connector/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
154
+ vllm/distributed/kv_transfer/kv_connector/base.py,sha256=KuKixI9XMfNTMWanVED-kedkMyMFtdcT34QO26lweJ0,370
155
+ vllm/distributed/kv_transfer/kv_connector/factory.py,sha256=Cbh8Dke2GKseifm9lKCYiQ97iQhvlc294WdZTUDhtIo,7249
156
+ vllm/distributed/kv_transfer/kv_connector/utils.py,sha256=BdRmJ3I2hUnfyGPfaywHOmwcrq0_9EES-Yy29nJb1m0,17293
157
+ vllm/distributed/kv_transfer/kv_connector/v1/__init__.py,sha256=XGVYgVwmenrlulLD3EgNx0CglBC1YgbOFRPKN-cB7yA,508
158
+ vllm/distributed/kv_transfer/kv_connector/v1/base.py,sha256=APxSnfbclE8BvPCgVzQ0xbI4jfTyaz9kKKGC0bAotxw,21250
159
+ vllm/distributed/kv_transfer/kv_connector/v1/decode_bench_connector.py,sha256=7vLp3BO3u79qid8sa5e1qCNB05m0_Ji6OrYialeHZxU,15544
160
+ vllm/distributed/kv_transfer/kv_connector/v1/example_connector.py,sha256=TcYDM1xoqavFzmG1r_7TitbD3dxOGnu8eiGM5t-Nb30,17075
161
+ vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py,sha256=zDBxiFNCjg5kX1XKYXmMfRze0iLidEJaIXIEEFBE1iw,12005
162
+ vllm/distributed/kv_transfer/kv_connector/v1/lmcache_mp_connector.py,sha256=RSz60vnQ9IcsG3iRvzvRgGHFg7Dr_5UdC-bs_9VpGaU,33633
163
+ vllm/distributed/kv_transfer/kv_connector/v1/metrics.py,sha256=oU9wXPoT748mueVnt6HVsL-fAemiglRONA19IkcCHC0,6887
164
+ vllm/distributed/kv_transfer/kv_connector/v1/mooncake_connector.py,sha256=3X1gByv9ZLrT6JkU47UdNNT3j5sy_yDh9vdfKhJKqls,34499
165
+ vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py,sha256=qdBrNu1ekfijdXMRNsS5cjGoWCtaqbLr91TrBFviRn8,18745
166
+ vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py,sha256=vPiYCnPCOUUetfP7h67M03uuOyEJmpXgL3RJMq1a-Zk,111994
167
+ vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py,sha256=U-pOAsFwQ_N9VKFpCu2m-IAV5lJIWfzUO-KBK-NVbxQ,21886
168
+ vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/__init__.py,sha256=k3tOaUj8P0IjtWcZ0CGxO3iE8IuALduzLpW5ejYJAFE,426
169
+ vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/multi_process_adapter.py,sha256=4SwDxH4ZVBN1wz_ngNn2pvA9TMLyPSAMP1SIndTFhSg,13055
170
+ vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/utils.py,sha256=hl401RmTVBPSfutf-MTgsGv9DRBbEhWmi08_KRv7LXE,7625
171
+ vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/vllm_v1_adapter.py,sha256=UsnlQpnxivqut5EMa_oKtPfuNsgRM6i1i9FitmPa5as,52755
172
+ vllm/distributed/kv_transfer/kv_connector/v1/moriio/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
173
+ vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_common.py,sha256=C9kFZkijnkWyfTZDVrgzol31AyYUAFAm8bq-wh0P-Bs,8911
174
+ vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_connector.py,sha256=Hcnr7hTyiZg8-L0BjMXXRG6OC-u9RGSDLBZ0N2ZNeIg,59078
175
+ vllm/distributed/kv_transfer/kv_connector/v1/moriio/moriio_engine.py,sha256=dwqWuDcJyaDdzW3BlNiyPYZrbQNxgbhkYm9nTx0jw2w,21319
176
+ vllm/distributed/kv_transfer/kv_connector/v1/p2p/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
177
+ vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py,sha256=JM4ZbPOf2tr1VsxJesDqTKDPTAYDpxp6_3cxUQWkh-Y,19301
178
+ vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py,sha256=gdHYw55Qm1z8cz5cWoq76siI8tL6tewzYldcxNCG2s4,23390
179
+ vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py,sha256=A2mMTFKJ1zBYEo0gPhe166-ms1S_gAaL4Zs9tULMbTc,9225
180
+ vllm/engine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
181
+ vllm/engine/arg_utils.py,sha256=oHVGzXKjkGv6D14SPhzsfXEC4Dlr3oGYofkTfR7TJl0,89370
182
+ vllm/engine/async_llm_engine.py,sha256=B4Xf26qGXnF7yc06F_OM2CH8k5CLUU34tjUEafnIg2U,197
183
+ vllm/engine/llm_engine.py,sha256=h0FBz_1vf8ThMr1PHUQVus1sEQH-N8XZsiQwNZrs1W0,212
184
+ vllm/engine/protocol.py,sha256=dhUkjCf04ZAs2IZdPnkXxKXJVk_CQoWeo4FUNO_7Ygg,5633
185
+ vllm/entrypoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
186
+ vllm/entrypoints/api_server.py,sha256=JUM2xq5yDLIVY6lDfhEtY002kQBo_YomSfmrrRzu7cE,5902
187
+ vllm/entrypoints/chat_utils.py,sha256=LgdvkdNUivXR7z7ucFKlEcCawiBcZfT-FZNj4IDjbh8,66832
188
+ vllm/entrypoints/constants.py,sha256=7rJGI5ZxBEJr2_7YjIJHzVaRX_9PChU7aOSYp95v6tE,356
189
+ vllm/entrypoints/context.py,sha256=3YGIUA0J8j83jsE3Ya20uyNubXaVD3dsKU3UZxYqPOM,34204
190
+ vllm/entrypoints/grpc_server.py,sha256=4J3dsAaKvvv38wYjdzv-VsAQZCJxLDnIuEeuXFWYlfQ,17592
191
+ vllm/entrypoints/launcher.py,sha256=AKCjD0uDH5IHLEnyUI8qjhihRIowyMJ8k77rvUmtiZI,6064
192
+ vllm/entrypoints/llm.py,sha256=IRBs9uWaM6NTqAbyyrwhXkd9nk3fzi0E5XTXYtEAlxI,76403
193
+ vllm/entrypoints/logger.py,sha256=GeSbm6Y6FndcA5HU_PYmlFC-6xFe2oGmegmNUgcHMKA,2659
194
+ vllm/entrypoints/renderer.py,sha256=JLM0NWt0O6eWfSJxg7IMA_TjmS2gcg-Qe8QO3nx1W78,15179
195
+ vllm/entrypoints/responses_utils.py,sha256=XBJP6KMUft2ykgA-MFcF_9sjcSgRB8QL2Vi0xSnyz6U,7458
196
+ vllm/entrypoints/score_utils.py,sha256=LRklLjVrEhsGXRxwC73ahyi0ADaZ-zDU4nZqqxspQwY,9273
197
+ vllm/entrypoints/ssl.py,sha256=P6ApVGAQFLHERnJeoLNpZk-HQI1nNqWdlF8UAQpnC48,2712
198
+ vllm/entrypoints/tool.py,sha256=HQfC9jB_6BIGq8J7nsY0DyTSZL_r8weKXhsyOpfWdFg,6242
199
+ vllm/entrypoints/tool_server.py,sha256=GbGIKW3-kQZ-o9xKWGKlAQd3oWPLHh6kMQj7nKHd-cg,7692
200
+ vllm/entrypoints/utils.py,sha256=mJHuSSnd0Eb-Tv_k8fVDCAqH4KySfkkovkL4lbymprc,12689
201
+ vllm/entrypoints/anthropic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
202
+ vllm/entrypoints/anthropic/protocol.py,sha256=nGkTR2TQtcy52uJJM8cJNSQtASDCChhgpQ6_-z_A59s,4284
203
+ vllm/entrypoints/anthropic/serving_messages.py,sha256=prvURUXlj96lIEYaAfmQlITeT26RHOFC9MLCRRj5saQ,20377
204
+ vllm/entrypoints/cli/__init__.py,sha256=-dU_jpAUU9ksRsxbw8Leuhy-wPcRTp7YQp_q5-tQM1Y,828
205
+ vllm/entrypoints/cli/collect_env.py,sha256=H9qpqasc2FRmAQUvmRV5WuCxJqdj-ouYAQ2CMpN_ihk,1106
206
+ vllm/entrypoints/cli/main.py,sha256=vHRDDzGjKK2ZE9EWyGn--jpfBWewDtiYFDab9srDc78,2468
207
+ vllm/entrypoints/cli/openai.py,sha256=CWzTEwp_nLWLXEPpvKlw7rZjiM-CSEnMaxic9s8IpIc,8134
208
+ vllm/entrypoints/cli/run_batch.py,sha256=8ChYNc3UbbCVEbtp_tTbgR32_jVq3WRJgO1RzGhP8yI,2242
209
+ vllm/entrypoints/cli/serve.py,sha256=mMcZqdgINWBYwT30J6lqstdV_d6MTVUy6mAbqFYT0BA,9140
210
+ vllm/entrypoints/cli/types.py,sha256=On70PbJbmYXWTQZaL3EbI7I-fd1eIE21FAhKuHnTcfo,812
211
+ vllm/entrypoints/cli/benchmark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
212
+ vllm/entrypoints/cli/benchmark/base.py,sha256=3KVCkfdN9VsNhP4RniGqJi02pzIEW4IMIktMFgwU1Y4,674
213
+ vllm/entrypoints/cli/benchmark/latency.py,sha256=ruUvsQxW_zv19NxZe4dhdVRjmBl2Gipa7o0aGp3VN-I,653
214
+ vllm/entrypoints/cli/benchmark/main.py,sha256=wmNjxthewFX_5aGtUPHgBrg8zYa5Ix7j8rqwEtGUI40,1875
215
+ vllm/entrypoints/cli/benchmark/mm_processor.py,sha256=aivtHrxDeIJHEB-KZQQ5rIllEamIU6jnhl5cNihgoUU,691
216
+ vllm/entrypoints/cli/benchmark/serve.py,sha256=v735WpqjlGE846KvCqAlrb6eAdysihhNZNX5SDL2Tac,635
217
+ vllm/entrypoints/cli/benchmark/startup.py,sha256=H8v9hSPhnE2mJnjE0RdgjLDpygdNvjOGCtkvvZXzExI,643
218
+ vllm/entrypoints/cli/benchmark/sweep.py,sha256=kHcCsBsGQwNC_bdhIdKs9ykJawLbRCrZF-HT4NFCjkE,629
219
+ vllm/entrypoints/cli/benchmark/throughput.py,sha256=Sb73dvXCAs_P7rk3sYkEbKIezlA8cCF7piMX1HA-xEc,652
220
+ vllm/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
221
+ vllm/entrypoints/openai/api_server.py,sha256=3Ma0bKhZB001tGhRm-z0JZn9q9_1OrUSx6JxXqnipbk,50219
222
+ vllm/entrypoints/openai/cli_args.py,sha256=_UlkZ3Go2iRv8udo8gXTrYrj-6fDyamv0FdcKFPRhnI,13828
223
+ vllm/entrypoints/openai/orca_metrics.py,sha256=qLJmaC4SWLSfvGtwOECR8DexnCXBVqYZuENYINORYgI,4509
224
+ vllm/entrypoints/openai/protocol.py,sha256=xwY7d2ptPgc7yqdmeQZwcvtwHyYnmayfMuuR4L2t2_g,91710
225
+ vllm/entrypoints/openai/run_batch.py,sha256=csh34wnhQ9LVeHBL8gGGdcUq2EkC_iqBWKdR13Oss7w,21569
226
+ vllm/entrypoints/openai/serving_chat.py,sha256=YWH9jsOiH3m_TV4BObH-mYl_igoAAtnCmS718XiP3fU,83658
227
+ vllm/entrypoints/openai/serving_chat_stream_harmony.py,sha256=0hBn2c2Sg9kzFRbMDRrfKCA7ENl89Bg4f5yFRj5SdMk,3406
228
+ vllm/entrypoints/openai/serving_completion.py,sha256=rBhr4KjaAAtZaAnSc7SBHmHFlxHI-9XOhNk6Ng4DbUI,30362
229
+ vllm/entrypoints/openai/serving_engine.py,sha256=IOGPHqFq3J_3ZGT5ybKSdgAmyfjctkQCOtxlsOM8Qe0,58452
230
+ vllm/entrypoints/openai/serving_models.py,sha256=CYi4YWo58nv1q0xWct-BQHS2WKfdZIPFrXxeaDm6nSQ,11517
231
+ vllm/entrypoints/openai/serving_responses.py,sha256=K2xaCpdd2SHylKkVaX4lNahDEhNdeNIdO2cSlgWFAb8,100399
232
+ vllm/entrypoints/openai/serving_transcription.py,sha256=YX736nt0BGXvMpj4lzypDjrAA8FBh2n3t5yFELASaWw,5986
233
+ vllm/entrypoints/openai/speech_to_text.py,sha256=ViF3TOwpfjS0P8eTrD7QLqv1rbezSlRlizCw7Lmnqzs,29393
234
+ vllm/entrypoints/openai/utils.py,sha256=GediW7ToZ71oiChH9nc6r7_XeTfuBo5K-yFDFWkYIA4,1608
235
+ vllm/entrypoints/openai/parser/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
236
+ vllm/entrypoints/openai/parser/harmony_utils.py,sha256=N-OeLXD7W7xpDmzBcur3-YCppokyHGB0NLAwxRCbsVg,29901
237
+ vllm/entrypoints/openai/parser/responses_parser.py,sha256=U-16wELbZ_U9O5IU6muboAdxMayQfJyWxFGu32mW8dI,6887
238
+ vllm/entrypoints/pooling/__init__.py,sha256=RKBcmpHb7TKxlpGmPQvC8FkTe-axbQmyjh7jYLRVhac,674
239
+ vllm/entrypoints/pooling/classify/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
240
+ vllm/entrypoints/pooling/classify/api_router.py,sha256=6XytRJFVNIJr8WXk90769B4u0eXAW9U_cH9WKqANSAQ,1692
241
+ vllm/entrypoints/pooling/classify/protocol.py,sha256=liPaeGzy_xnxr2w9wdcsgjOOpEY9MCSkp2NLd2QDf_E,5874
242
+ vllm/entrypoints/pooling/classify/serving.py,sha256=YIWSg3zjblrYSnnasS4HQU6mC8OfKzjQj-91ga07Jeo,8210
243
+ vllm/entrypoints/pooling/embed/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
244
+ vllm/entrypoints/pooling/embed/api_router.py,sha256=nkKtNa5WhwY5Ds2IRHbhwIaQOvnfimIHcwme7rw0kLg,2146
245
+ vllm/entrypoints/pooling/embed/conftest.py,sha256=d8y2xO7p_wBFm_ATBxjolPfYEYifutv0kSiEKKYMcZQ,991
246
+ vllm/entrypoints/pooling/embed/protocol.py,sha256=_tKvY3WonaRU9UfN53LzU_6UME2DueG07izBChh5hz0,7877
247
+ vllm/entrypoints/pooling/embed/serving.py,sha256=RrnGBzwSvlP89ttT6bqTdVBMgpVoNSEuDOvtSz16Npc,26610
248
+ vllm/entrypoints/pooling/pooling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
249
+ vllm/entrypoints/pooling/pooling/api_router.py,sha256=OHaZaLLZNA_B75c_P1C4IvM4LKI2ogq-DCfffTwgJSA,2151
250
+ vllm/entrypoints/pooling/pooling/protocol.py,sha256=ABp1Z9qT08nN7XixOhkFVBUnHb2PSOLdW5RjaI4PqIo,4655
251
+ vllm/entrypoints/pooling/pooling/serving.py,sha256=JyGkwi53eB03WNiNFbkRUh8_v8F9A8mtVHEuFbDLbyE,13331
252
+ vllm/entrypoints/pooling/score/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
253
+ vllm/entrypoints/pooling/score/api_router.py,sha256=_LSR7Pxgb8hiM9A4UjVYR43PwE4QQex6FApeKE10gQI,4673
254
+ vllm/entrypoints/pooling/score/protocol.py,sha256=39GVNxhiOivBsivCVw9MBgPbJaunJdyd4WCo-PIzeRI,4207
255
+ vllm/entrypoints/pooling/score/serving.py,sha256=ktqK_kJ_MsZeXtg1ZswwTy89oM0ZYXNL4UBJX_XYn-k,17435
256
+ vllm/entrypoints/sagemaker/__init__.py,sha256=Fh71s9Oigag26xVp42xT7JCAr_dvDRGnjoRhEV18cwk,155
257
+ vllm/entrypoints/sagemaker/routes.py,sha256=6dVezdr66WhqAGFGZqTo-JkQ5C33faszQKIEoVASF7M,4603
258
+ vllm/entrypoints/serve/__init__.py,sha256=8wJK0S0BmWKxbLv6NjtSJYK35p0dtlT8UbpXxaGFeTw,2389
259
+ vllm/entrypoints/serve/cache/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
260
+ vllm/entrypoints/serve/cache/api_router.py,sha256=PamwSo9LZcUToQP6hPdjmlg-_ZtAeExAfLm5aiLG77A,1703
261
+ vllm/entrypoints/serve/disagg/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
262
+ vllm/entrypoints/serve/disagg/api_router.py,sha256=CY8Ok_IK-FV3UfTHEiELe27W3HXqONsqB_DYdeNl_3I,3536
263
+ vllm/entrypoints/serve/disagg/protocol.py,sha256=jaOkDM48h3huidhjDp6Oxmq6XYmOMN5qe3APDUejLcI,3038
264
+ vllm/entrypoints/serve/disagg/serving.py,sha256=uPC_tQtjKJzEVvQ6OR0n2l98khWiRfp8eY6DEkfofQA,10587
265
+ vllm/entrypoints/serve/elastic_ep/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
266
+ vllm/entrypoints/serve/elastic_ep/api_router.py,sha256=Hvv2xDA6W9lydQ6i0dcmtw2GWIAZD-B_KtqrccfLekM,3053
267
+ vllm/entrypoints/serve/elastic_ep/middleware.py,sha256=RtpwW8Zfg8jj-D8rGYl3p3M-mzVc6gq2nYqI9DfH6R0,1448
268
+ vllm/entrypoints/serve/instrumentator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
269
+ vllm/entrypoints/serve/instrumentator/health.py,sha256=UmiFFKCjjcfL2hfHAYB9BwlerSuVh5ftmMgufWoPuHg,835
270
+ vllm/entrypoints/serve/instrumentator/metrics.py,sha256=2o8fVNvCSNN3DnvPh_CVcH_1Y-Aq1uP7JDmxNV4Xbu8,1534
271
+ vllm/entrypoints/serve/instrumentator/offline_docs.py,sha256=m5gKlST7xHrkTu-rrsrWB7RoBg65YrPICSvN8Shc_eg,1650
272
+ vllm/entrypoints/serve/instrumentator/server_info.py,sha256=i5LpYCTHMYAQxcvku0l3ZFloPhRzFkq8KzyH0ERrK3M,1543
273
+ vllm/entrypoints/serve/instrumentator/static/swagger-ui-bundle.js,sha256=cjwCMG26k_E_S2vDtsXg7HObuVIXeHRzSvXnThiuuPM,1510261
274
+ vllm/entrypoints/serve/instrumentator/static/swagger-ui.css,sha256=nldvgyITLHaUnaR_m7U8iRNzwwPqOnYf9Uj_yd5QqYw,177183
275
+ vllm/entrypoints/serve/lora/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
276
+ vllm/entrypoints/serve/lora/api_router.py,sha256=9_17KDOhMtVVyrHg7kbyHDFXm0cvUxRKl5AQpbZqugA,2494
277
+ vllm/entrypoints/serve/profile/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
278
+ vllm/entrypoints/serve/profile/api_router.py,sha256=uUPDoiARNOLQs4v6htAOi1aF9b5qVPbHF43ueEwbeOU,1470
279
+ vllm/entrypoints/serve/rlhf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
280
+ vllm/entrypoints/serve/rlhf/api_router.py,sha256=abl8IzmpfbtxNa4WCt7qxI7Tg7csdHIjGfUpbwgiz_o,3071
281
+ vllm/entrypoints/serve/rpc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
282
+ vllm/entrypoints/serve/rpc/api_router.py,sha256=hXijkDi63KhrEkwcI0SfzpMcr0TbBCKNm7F12uQaQc4,1946
283
+ vllm/entrypoints/serve/sleep/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
284
+ vllm/entrypoints/serve/sleep/api_router.py,sha256=n5aOITLM2Tx5lNdXfLPl2kRulJdfNsz00QqfYmDO6RM,1721
285
+ vllm/entrypoints/serve/tokenize/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
286
+ vllm/entrypoints/serve/tokenize/api_router.py,sha256=u12mtbAHckSlCcajK_LNMoUOWa-jUGH6v6zF2aQggIc,3634
287
+ vllm/entrypoints/serve/tokenize/serving.py,sha256=fYAO8kkkm50YhNi7NyJJu46RoCzlWs64UMvxJ_PMwTw,7475
288
+ vllm/grpc/__init__.py,sha256=leqIiw5daoeDRF-SfkvbfjNXiJVmEp4p0vZcsNyYOME,504
289
+ vllm/grpc/compile_protos.py,sha256=d423R6tn_2BR4DEuZbzkIcVg0dxIdg433IPuFXeMKgk,3276
290
+ vllm/grpc/vllm_engine.proto,sha256=FbL33rEzk-GeWkaKA3mS4wx8H9_ZEWXZlqQPLVB3VQ4,5114
291
+ vllm/grpc/vllm_engine_pb2.py,sha256=ywCbJ-1xYDPoyfP9toRynM0YTNoOTXo3ZpjHWB0S7Fw,8073
292
+ vllm/grpc/vllm_engine_pb2.pyi,sha256=tr_SkMWXSvkpW01P_Pg3AnACfbwDREeOxxqM9TX_CrI,10649
293
+ vllm/grpc/vllm_engine_pb2_grpc.py,sha256=KKB0EIQvnNQRSSlJNtnOmTvjF49sKjw9yTd1otJmfno,13161
294
+ vllm/inputs/__init__.py,sha256=mOYaFF0JBFeIgf4cs5_kS5d7zk4yA_TRBxhfOncKhGw,959
295
+ vllm/inputs/data.py,sha256=vCFClf9AbX4bNhc6_3jit-xg5rRbdRplEPaxxHloRcE,11465
296
+ vllm/inputs/parse.py,sha256=ZQUQNsUSkbNSfo_xXikx4NClhAK-LB88H5SAYx9UOTI,4657
297
+ vllm/inputs/preprocess.py,sha256=wNcjdnrQ9YKiVfhHkcehXwp8Y8OLafp3oRp1fIaAQDM,24794
298
+ vllm/logging_utils/__init__.py,sha256=Rup1dtcYw-n2RvQt0Ka37rCagFdvfmzx4UFOmi3XTpo,363
299
+ vllm/logging_utils/dump_input.py,sha256=jqfKTqU2b2O4g5I_P2snzPuuIFlSTYg33BjZ5P87-JE,2914
300
+ vllm/logging_utils/formatter.py,sha256=3tQ1N2oDuzXPRCcasRAIPJhz4SF3_gBEfXz8IcSuz9Q,4649
301
+ vllm/logging_utils/lazy.py,sha256=I5YcIP9S9ru8q5kC3h0Vqaf1nX9A9xxUSP6KTcvWxcU,508
302
+ vllm/logging_utils/log_time.py,sha256=ea9dQUzQAu_f5juFfGVeOX403d4yGVqiBmI35gmpqdQ,864
303
+ vllm/lora/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
304
+ vllm/lora/lora_model.py,sha256=EMmHscY4nTXTH72yaeDX6lJTvacqrpcIEddgHCVbChA,8670
305
+ vllm/lora/lora_weights.py,sha256=gmnlIUfNtzeoOvPBAVhI8r-qfCyPloTajp_PzklqQKs,6971
306
+ vllm/lora/model_manager.py,sha256=M82YKEAcK1uvFS69JaG4gtutNw4-mO6UnRDx6ObZ-Jk,34107
307
+ vllm/lora/peft_helper.py,sha256=rLbCLj-UsjXFD2wXD18hOAtzP_389FwcpozeItzgRvk,4678
308
+ vllm/lora/request.py,sha256=5qYqD59UYg7C8Z2WsxxqusCzI1SbggWfdjq2o72KdmI,1721
309
+ vllm/lora/resolver.py,sha256=SvNATAduYkVIuFA59Q5pPTuPjmLQCg-IH-_35u2mn98,2880
310
+ vllm/lora/utils.py,sha256=jlpTM49_WxAWrqxHsyXflr-J6fqCCyZBU3iO5j4DM-Y,9713
311
+ vllm/lora/worker_manager.py,sha256=uiVls8d1hGFEg9lW-f3bo9x9ezixgYuIkP9kODyiQAM,11119
312
+ vllm/lora/layers/__init__.py,sha256=YfzfxzQmwUdExDDBhV2S2KtSa3al3jCmladzkIaqf0o,1650
313
+ vllm/lora/layers/base.py,sha256=djqVQ30rFpuG71V8nIj4QARsbEDzjfeosBk9jTt98Ts,1825
314
+ vllm/lora/layers/base_linear.py,sha256=X97dwAD_mxxZEVDeRiHW6N501uNoSVUc4vAWcTXB_A8,6015
315
+ vllm/lora/layers/column_parallel_linear.py,sha256=4OHIu9At_tNoV1mV0lyMT17rn0Uu1fhom-9BzdETyPU,19929
316
+ vllm/lora/layers/fused_moe.py,sha256=4nQ2Nu_YcK_M0kilvxlug_D090t79hs_CJY4RBjP6bc,27349
317
+ vllm/lora/layers/logits_processor.py,sha256=1c3bDxki-82ZjotsTDTwWuooLnd2CqZQs7TKdjeH998,6447
318
+ vllm/lora/layers/replicated_linear.py,sha256=oswJbpelrd1Smiz1AV9zlLRcZb62XW700uporDliAJE,2205
319
+ vllm/lora/layers/row_parallel_linear.py,sha256=y6MpIbqGU3eSv50nlzuaSDRZdyUfwUJp66E6Fwct8GM,6187
320
+ vllm/lora/layers/utils.py,sha256=VjoFiTOfwIBtfPA5hiRoRJxyIUR8Fd5rlbWgJRsbf7w,3420
321
+ vllm/lora/layers/vocal_parallel_embedding.py,sha256=xznlBgx20SFUxFHr6nRgieJlg2uyVVSmc1X8thQvoA0,4944
322
+ vllm/lora/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
323
+ vllm/lora/ops/ipex_ops/__init__.py,sha256=GoE4WbwmiV3lmZ9BvAzF6HribyiAa62lEsRdAOORl3g,259
324
+ vllm/lora/ops/ipex_ops/lora_ops.py,sha256=sQTAhgirQaxWxhc3xTdSlDBfZKUUJaY4MwISeBBXOEg,1344
325
+ vllm/lora/ops/torch_ops/__init__.py,sha256=T8KI4Uy6j2AJOjjfe_9HYZmuSO9xp0G_GTCdvHyJiNE,426
326
+ vllm/lora/ops/torch_ops/lora_ops.py,sha256=M7wqynKevDeeFyXDwcqHDnCqOyePCtPSpiHm7I7pnCA,3888
327
+ vllm/lora/ops/triton_ops/README_TUNING.md,sha256=vRdibcgJphUomT22SAtQSrEf7LVROHwHgugGjqpBqY8,3078
328
+ vllm/lora/ops/triton_ops/__init__.py,sha256=-IQeOBrAW7uCUQQVUt5zjjL4PyqB1in1AJei7ezUpNM,598
329
+ vllm/lora/ops/triton_ops/fused_moe_lora_op.py,sha256=6w_LTasfXcHJ4D6M9zp1gJIaQL6yUEE8Ksu-2alHf2I,19940
330
+ vllm/lora/ops/triton_ops/kernel_utils.py,sha256=YiE1F7sojPFFF06QsVSeaDN19Fpo4X1MhFSoX4F8EXA,10375
331
+ vllm/lora/ops/triton_ops/lora_expand_op.py,sha256=sBLuBgoQqcosxcXAmnsvfJh9O00gDbi261dT4wm0KsY,9542
332
+ vllm/lora/ops/triton_ops/lora_kernel_metadata.py,sha256=_7kOuoEYIx7lGOzFPwp6idbExJm6tN__CBUATMr41JY,5407
333
+ vllm/lora/ops/triton_ops/lora_shrink_op.py,sha256=JfoH1p6rS4V1JyqbbrqrRVur6f9bsdvXZsX0AQEMxzM,8996
334
+ vllm/lora/ops/triton_ops/utils.py,sha256=xKR1_DqKTmeY5e095sZ_uMbtUdkbUpJefcS-bb5Cp8Y,10417
335
+ vllm/lora/punica_wrapper/__init__.py,sha256=A5cDJmdCPRBN23kwLfemRlWI4YA-t_7qIxeoeimCkT8,313
336
+ vllm/lora/punica_wrapper/punica_base.py,sha256=puiggPyTCXaKXmmrsYiiRiDnVym7Ig4BYjdlmnEXMaU,15734
337
+ vllm/lora/punica_wrapper/punica_cpu.py,sha256=qJLetoy4aPyQazVqbEq0pOOr848ox_hXvO3AOIH4XR4,10817
338
+ vllm/lora/punica_wrapper/punica_gpu.py,sha256=lRjcYVDeNarb4SqWj8EXdSyL_QJpPpMmyhWdaqcqnu8,12965
339
+ vllm/lora/punica_wrapper/punica_selector.py,sha256=-IyHqLvTPs5onKUXacOqS9J03otlfaT8J7yj4iD_YRs,818
340
+ vllm/lora/punica_wrapper/punica_xpu.py,sha256=tUpbNjlqObOWv3msA3ExE49xjjfx7FTYz_-LyDFJEtM,8770
341
+ vllm/lora/punica_wrapper/utils.py,sha256=omm684H29vAOXrC4ny19kmKFRk0_-pIAMTR87CmRMXw,5517
342
+ vllm/model_executor/__init__.py,sha256=rfqoeB5JCg57wsDNKLvrD4JDWUkm3zUiegVhQaD3WtI,256
343
+ vllm/model_executor/custom_op.py,sha256=d4eV9nLcxNMmnibnC519lJVPwLIGhRdw-0h9LT6ikhU,7977
344
+ vllm/model_executor/parameter.py,sha256=zo3JRXFPq62Dg8624hZygs3zAq-W8MwJirmY1qwHkTY,22854
345
+ vllm/model_executor/utils.py,sha256=v86yt7I8zSLlnX_C4wB-caSGf7ToHc-xibY9gc78BBs,4355
346
+ vllm/model_executor/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
347
+ vllm/model_executor/layers/activation.py,sha256=8zswJvA-kZf-mlLQYJpd21oPwMnRW4bUiv3gAVJbZ58,22460
348
+ vllm/model_executor/layers/attention_layer_base.py,sha256=T8X8sxru-eTivn94eWOVqjEosV6LNaJbpTrR8sOe1QQ,1015
349
+ vllm/model_executor/layers/batch_invariant.py,sha256=TI52RJXvQf0c1NKfmZlplZ-w9pDnlt2REuWM_oh7row,33587
350
+ vllm/model_executor/layers/conv.py,sha256=UVHGlHFBo56rLzFK7bOE22WkDEB4W3xpMJp4pYtxOjc,8152
351
+ vllm/model_executor/layers/kda.py,sha256=9gozc7-nXg7ubhTPk_CzE0c1oWVNGZcxlP6SaWepRyo,15497
352
+ vllm/model_executor/layers/layernorm.py,sha256=96ACWnNkwDI_cn4uNJ_4Y--j8NbCa9p7YB8kHtPdGZY,14076
353
+ vllm/model_executor/layers/lightning_attn.py,sha256=yknJVad9ilzRGFdFhvjkoe_xEiffNp_KopUsd32Qzf8,20864
354
+ vllm/model_executor/layers/linear.py,sha256=3lxaCRb1cF5zA39o72Gufxe4nSPf2U39N3MRa1yEWXo,58431
355
+ vllm/model_executor/layers/logits_processor.py,sha256=bqzxb8Ew4jEg764x8vm3cilMZVrPSGU3HeLuePjtOGQ,3911
356
+ vllm/model_executor/layers/mla.py,sha256=2A0hcHGrC1LlqBFHHEItWHdt2-TazJeP5QUlc1Kj8Eg,6457
357
+ vllm/model_executor/layers/resampler.py,sha256=kK_gbASYVbvMoPPN3petUTfNGK8DkdNdihYnFx-JLn4,9877
358
+ vllm/model_executor/layers/utils.py,sha256=FI3DqvZAPjDcmESgiQv5MHWDwx8Nw_x_nWmEehneprc,8024
359
+ vllm/model_executor/layers/vocab_parallel_embedding.py,sha256=nf9sq3wXeYmRzEjoVPJ1prWWzGN-VpTxZsIM3GjTGHk,22192
360
+ vllm/model_executor/layers/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
361
+ vllm/model_executor/layers/attention/chunked_local_attention.py,sha256=N3wF9yeLfkKT6orj5yqg0yb4ca_EEnOU5sLWLWUpPTs,4603
362
+ vllm/model_executor/layers/attention/cross_attention.py,sha256=H9ohdm3iP1bQNkm51s3UX9gQdMtbB94LsCevBv5EO7E,6394
363
+ vllm/model_executor/layers/attention/encoder_only_attention.py,sha256=EHKQfaWE4HJ4bw8t3L2z5Oo1rwHiZV1M3wof1EMO8uY,3069
364
+ vllm/model_executor/layers/attention/mm_encoder_attention.py,sha256=bvrPHGvsmnphmv6ldXEl9jIlWD0c0B9QsY9K7m8ROK4,7901
365
+ vllm/model_executor/layers/attention/static_sink_attention.py,sha256=RNBdpaGBAe7etpkZaaVd-9IYSE_mU96o3I7Oppa5KBI,8412
366
+ vllm/model_executor/layers/fla/__init__.py,sha256=Xbv6P8KG7bLpcOF17zPO5PYYHImweE9aiYYgGyMS9U4,391
367
+ vllm/model_executor/layers/fla/ops/__init__.py,sha256=Tx9ajmbsCCptuJofX-QpCC_Ut2SwZBTT56SUjGXGNs0,642
368
+ vllm/model_executor/layers/fla/ops/chunk.py,sha256=NJFnrsO_TdmXwAsyAmyUptSMxrVCH69T_xHjDp6DRko,8925
369
+ vllm/model_executor/layers/fla/ops/chunk_delta_h.py,sha256=rSBPoldJnPs9MHO_XOCw_E-fy-R5H8vA38zsSQjI9CA,11864
370
+ vllm/model_executor/layers/fla/ops/chunk_o.py,sha256=ucfFMons_gjoof5N36dImFVcWDZpeBjHVxdFMI1XOTw,5095
371
+ vllm/model_executor/layers/fla/ops/chunk_scaled_dot_kkt.py,sha256=_i7MMGO66MjD1RYQFDqNpa9yGknPyHBOTEDwChc9hFw,4653
372
+ vllm/model_executor/layers/fla/ops/cumsum.py,sha256=qhS_Lny-roiECMEDvtWBE2RpiFYDKjqWxwQONRdL2gA,8224
373
+ vllm/model_executor/layers/fla/ops/fused_recurrent.py,sha256=el8wvmFySZohR8TTZ6dvKmUItJ2cT6u-gbiokZSKzig,13065
374
+ vllm/model_executor/layers/fla/ops/index.py,sha256=cg2IV5Tn7cvDzPw8fTdI96sIYFy87tk960b0nPJFXSE,1221
375
+ vllm/model_executor/layers/fla/ops/kda.py,sha256=7eRv3Hs8oOWM1_nnrBC1kERDSUixaax_-RHDKjQz5xE,38297
376
+ vllm/model_executor/layers/fla/ops/l2norm.py,sha256=HfUKWKl1EvrUKcowbDu4E5QPQCgZbPFumK43eli0Q6Q,3978
377
+ vllm/model_executor/layers/fla/ops/layernorm_guard.py,sha256=nfQwy29Wu6Pt3X3ZL3oPVqxhzITarzf7AmxjBzaKDWI,12449
378
+ vllm/model_executor/layers/fla/ops/op.py,sha256=atkZKsyTmBUTa68GnRk0VfEVfKAbmRoFLYtQlf8_JBM,1712
379
+ vllm/model_executor/layers/fla/ops/solve_tril.py,sha256=ARfbUgKOHld2Zbq3VlgjP07bjczFSCCQc0MRLmABcV8,19385
380
+ vllm/model_executor/layers/fla/ops/utils.py,sha256=8RRhqjpzSTv0DUsZpUor_qzrBrX6FkFuOOpha_HpmGc,6374
381
+ vllm/model_executor/layers/fla/ops/wy_fast.py,sha256=TqyZCDUrAUo0ZFdtHPRY4ntUxavxsYsAGGj0m23oyiI,4372
382
+ vllm/model_executor/layers/fused_moe/__init__.py,sha256=VO8j6GgIL7o70xAOMaTY3OuILp0eukJ0_2iBN0a48lo,3528
383
+ vllm/model_executor/layers/fused_moe/all2all_utils.py,sha256=s943z_GBScf1wuTG3qz1UAUaaoTTzo9gYo8ohS8foaA,5999
384
+ vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py,sha256=bBFUmmKC-FT52tUspAtD5iAiHTKA6sWuowTjvDLuRE4,14966
385
+ vllm/model_executor/layers/fused_moe/config.py,sha256=9TymPS17RrYE-c6d-Jq_ZDxuGzoS3dwJbm_1ZfGuQzs,37277
386
+ vllm/model_executor/layers/fused_moe/cpu_fused_moe.py,sha256=t3HiL-1BUaVEqrGFw7klouw4z6m9PD_9lT1_LnK-IBU,14879
387
+ vllm/model_executor/layers/fused_moe/cutlass_moe.py,sha256=fu6SzkND73sTFPGshZkLr8OIiL2g6H6stJ-3l_4OOMo,36624
388
+ vllm/model_executor/layers/fused_moe/deep_gemm_moe.py,sha256=f_GW75HjiJFSKw_TqoX_FpKLYhQHn-VW9qDFoRRN0qo,12531
389
+ vllm/model_executor/layers/fused_moe/deep_gemm_utils.py,sha256=OZ5vnMME0tDx4xSaWTroxkaO3akmLyznT_VWs1IZ42w,13264
390
+ vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py,sha256=3jXq-FQ7m1aASduI-35O_isUZcPe-3jHtkbPv4h038s,14791
391
+ vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py,sha256=Ii69k-c4XseaJoPRLPSdigmxu2aN2vMAsB8LAI_HTnM,15090
392
+ vllm/model_executor/layers/fused_moe/fallback.py,sha256=ey7x-OiPJ1-U7nwjd4Xsd-BbylWo-KetRUsWs1hExtM,3858
393
+ vllm/model_executor/layers/fused_moe/flashinfer_cutedsl_moe.py,sha256=eMdpREk2vPKA5gOmFkg9SSRMouL-Sr-WhMKEy8VlKws,11774
394
+ vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py,sha256=WFgx8H4WoaWr3JkktHjqOm4Q53pONJok4FwQfEixPWg,10949
395
+ vllm/model_executor/layers/fused_moe/flashinfer_cutlass_prepare_finalize.py,sha256=dlvgHCnc4AtuMmc6ma4hCx1ktbs7ynJDjBlDxqEX2lo,12552
396
+ vllm/model_executor/layers/fused_moe/flashinfer_trtllm_moe.py,sha256=ddui2Ds7HlmDdLagKLcYkUwAejp828_HkA-GOREtIq8,6416
397
+ vllm/model_executor/layers/fused_moe/fused_batched_moe.py,sha256=WW1kaZVOrRU0cv8v8HpHTI5DPyAvNVGtyixtnlzku3s,32352
398
+ vllm/model_executor/layers/fused_moe/fused_marlin_moe.py,sha256=1O3p08A9mwk-K6t6otZNZsEVfd1TTr890wOcSxYet6c,28529
399
+ vllm/model_executor/layers/fused_moe/fused_moe.py,sha256=KaJ8FQ274X_d558ikEzgvPHk5_5WcTCgOpFTfISXaIM,89670
400
+ vllm/model_executor/layers/fused_moe/fused_moe_method_base.py,sha256=GF5ZqPDHInaD6DQ3GibsGJs-WhdXiN_Pk4zr86YM1VA,3664
401
+ vllm/model_executor/layers/fused_moe/fused_moe_modular_method.py,sha256=vIRlRtzbXmNEfpqFG978D58PHvh7RvChC8yVVh26kSY,3751
402
+ vllm/model_executor/layers/fused_moe/fused_moe_router.py,sha256=DlbIBHHQs-kqisruGPe7vKzN_UeTu4ogcC-K0t9WNro,1261
403
+ vllm/model_executor/layers/fused_moe/gpt_oss_triton_kernels_moe.py,sha256=Jyl8rfMcrlJLPoXk-MTv1Coy4ncxRRCEDyhQzOk5Ggw,17840
404
+ vllm/model_executor/layers/fused_moe/layer.py,sha256=3m78YBMSIGpbHG5IajHXRsDKhyfRdExbwn7m7ZaUiao,85570
405
+ vllm/model_executor/layers/fused_moe/modular_kernel.py,sha256=2OzcN1CuKnCzVM1DnqRhk6iRWD9cZqvOiSmu-aSJkFo,45084
406
+ vllm/model_executor/layers/fused_moe/moe_align_block_size.py,sha256=w_f8IIeDbwFgoyq5nOsdj26Hx5NnnaNN1nLiJct_oxs,8339
407
+ vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py,sha256=WftEGpSesMQmjg5sbvko3LGHuDl8EpySliW5X10Xiwo,8196
408
+ vllm/model_executor/layers/fused_moe/moe_torch_iterative.py,sha256=u_cFfZnz34AliNgZWfQUltCTXP_yTg4NjFxKb0r7zU4,2154
409
+ vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py,sha256=cEP8YRKHP4l4lcf2m-dNuQmgF5jCRIqEexp2aC44oe4,11776
410
+ vllm/model_executor/layers/fused_moe/prepare_finalize.py,sha256=uFU27BoNszH6Jwk4JhVanpA4w60Uye50GDYvvuNMSrk,3007
411
+ vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py,sha256=aHeuGBeIbrkHz1QbPnTNGndAwlzVilQ-lQ3Kl8SkFfQ,11881
412
+ vllm/model_executor/layers/fused_moe/routed_experts_capturer.py,sha256=ZHuUOiFDWLCDZgrpIcp-dQeNEc-t5JRGKkVwMgj-5BQ,10915
413
+ vllm/model_executor/layers/fused_moe/routing_simulator.py,sha256=TY1mPAGcG6SKjRh2kt-wvM1sn6Xd6bHmYmuXjAovBbA,10724
414
+ vllm/model_executor/layers/fused_moe/shared_fused_moe.py,sha256=iUpzSEBcCrqBPzvg7DsYRzyD6EXYuPxQs7bmZrz7JV0,3439
415
+ vllm/model_executor/layers/fused_moe/topk_weight_and_reduce.py,sha256=sLKn82zPW7Yij8Bcrt4sXW78SyuwIwDELfiqsXaTxsw,5801
416
+ vllm/model_executor/layers/fused_moe/triton_cutlass_moe.py,sha256=TUKlr0BnZzaQCsQjmUBsyuIsRZ022gCemwsg1cKr3pA,2449
417
+ vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py,sha256=9eVDqiRRJe8cRc-hYp6nNlCWIvNnUYRczVq7cTKuoYE,2488
418
+ vllm/model_executor/layers/fused_moe/trtllm_moe.py,sha256=lHnksassB2vzte50TrmsQUWZlDWbWiYrYRjlG4yod_E,4685
419
+ vllm/model_executor/layers/fused_moe/unquantized_fused_moe_method.py,sha256=sVJ_g0_TNPgNfdOIA-O1YSvPE5O4v7UinRxy-HHFdHw,15106
420
+ vllm/model_executor/layers/fused_moe/utils.py,sha256=keJkaLY4s2PAdDFsixy10tN5C0Uq53FbxSyyBxQjgSE,12523
421
+ vllm/model_executor/layers/fused_moe/zero_expert_fused_moe.py,sha256=4LiP1U9X2ESu_SOVdZ1SHrHZOe7XzdqBt2Ee0RDQPgM,7676
422
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
423
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=hH5rRN9Wtyv35azxMzyUMHWtiKgOHev5tNjIG8j6dsE,2751
424
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=qPumkNxaHMvVBnEjPe_Xiuz9ICb6Hqc-9I1DAR8s3gA,4130
425
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=s47lb8VLnyxMgWlqcIR4BdPBsjKWL4olXF49uZvygzQ,4140
426
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=SkuSt9_xoUgmwy-EIOMJ5DT3pEm7g4dMh78fZSyCaKU,3244
427
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=gzfjrYDcS0vsACq7ONGVkNA3FqVjr3e89q9fO9kokkg,4133
428
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=sIaUmqgtlHW1lvmycafqWUAKyyLuf1L4t_ixzOiVmlA,2744
429
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=yl2lRcoGAKs1OQVKR2JX2C0VkpwUiCXGc_BTvh6h-r8,4146
430
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H200,dtype=int8_w8a16.json",sha256=NZUb5kQi0HyBrzhRyPl6pdKwB4F6KqHcJepwHWbxsYY,3248
431
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=H0K4_O1CMbNLi-srcycT3lSl4JaBl3EGF89GY5Rj9MU,4130
432
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=arPqstZMzZjz8BNpY3alKT4vGCJyUj5I2hEeK02aq98,4152
433
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=XcoSAxPTaefnIozjfToNebc2wdctRQQRc0Ju0d-QglY,3243
434
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=wjnQ4v-dflJMR3iFDHBuZI_1R0xXjsNoWc2kHu6C8JI,4135
435
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=7WHPz_0fxeI3Ed0D9VIpZVoeN9RtJVVARvptfcmQu40,4146
436
+ "vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=KPpfnhkIzT9JiiHDLakJlQvoNIzmCCq5NLpoKjZxaOU,3253
437
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=2kWS9Qvy5Q3mvUFmbPVures5iZAriAXsy8WrtE5wu00,3727
438
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=D2dn9vXyN4FCKsZCf7VYgAWLedCx8XpPjbkQVVAvwAA,4737
439
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=2kWS9Qvy5Q3mvUFmbPVures5iZAriAXsy8WrtE5wu00,3727
440
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H100,dtype=fp8_w8a8.json",sha256=IAD1itR3hNQyHzj6AyfNj7G974sVQEaYafewGm_OKdU,2747
441
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=l3y3uQkhlA2_7cbrDHsRslWXR9NzgtkD_BEQckJ-Of8,2746
442
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H200.json",sha256=2j-E88dNQghnJuIrCLwUn7QfUI66tieoCt6TIYjMvHQ,2743
443
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=1856,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=mFxdW1jiRGxoW09LjL8rRHxgiJXXPgtGCCtjmj83UII,3272
444
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=1856,device_name=NVIDIA_L40S.json",sha256=-wcihTQoV82En7NC9eU2QNlm46fjjdAW9ywahwBLzus,3281
445
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=5QqFljwwA8OaPlFnXy1zogl5oi6aE0OqN39xk2IUC64,3245
446
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I3k416HbXU_rYb8scD8gAI4fuBlElHl06PM347Qa11w,3253
447
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20-3e.json",sha256=CoC3pMKx0vkjI9T6rqRLTIwbDskxljTj31fCHI34B5w,3232
448
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20.json",sha256=RgV8C4F1LO09h01YsgF_eqX6GNoBtC7ulPfJRUUbg_g,3241
449
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H200.json",sha256=nsNEuDNks0tVLfQfIm7xxFwEeptTfQcoa9fJy0NS8xQ,3247
450
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=352,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=LCN-mYQ8xqL_ewIGV95k6EC_dfJtcdfQZp8uZR9Air4,2721
451
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=PvRpT_brUV3Y3zMfWEcsXMmdrYKjiq2qI9iHejPhhsU,3743
452
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=MCTOhQ01id6YjPtWbG6Mw5dlU1xtilsiq3HAstGn36w,3258
453
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=3o_aYn580j2L0ZPdKSTLqrYnginfBOFNhCksS5qxeNA,3258
454
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qbqjisJ4oKmcYzumHPRk5UyOzsdi8J6xas82UWHMeAI,3263
455
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=PflsK6VWRhwGaDKSIQ9vD7NMHcKLg3B4wENarR0aIq4,3252
456
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e.json",sha256=gkimxy2r78McckKxx4U4R3xahTI1KMH2pMOdUFOUdu8,3234
457
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20.json",sha256=vS2DRIDOqWyiBvbG6H746ownfkD1F8Aj2YZ0ET9xll8,3232
458
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=MlpzcrkZo78kFYr6cqmh4lBdpxKcEvlzqvRf0bmeduQ,3264
459
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200.json",sha256=xqhl748it8GV2KXX0XixitE_ywnsKksqK8AGL7tAgT8,3254
460
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=UdtJCWc6Q1nCeY18s4pufHlf760NO6wxhmtclIwhDxE,3288
461
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=FsWbV4Q6AzAtgegVuENBDz2ZcSJsqNiwUIVfQbpP7hQ,3244
462
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=lvXUPgtRxDuNn7ESRNEzT7V2qStb5z8bAOGCOzP8q_U,3256
463
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=W8C1GtP4K43SK9128U52DD5WWofvPleAJE4us2Qju1k,3251
464
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ZrC8J_AmZWNx30UDrXG6sHWtFY6FNVPsNywLhEBQdi0,2530
465
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Workstation_Edition,dtype=fp8_w8a8.json",sha256=vaiXepgaaixIxU3_vVGcYsA18XAiC8V13phIN5niRrc,3250
466
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=rN55MyeJ8U6VGNRg7lwC3aa8BgjxdzVg-CofcZ7LTyk,3743
467
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI308X.json",sha256=SDxGApRr0Nl8Thz-99Y3vKEz2Aw60juCGo7zSQriMKg,5021
468
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HqskM2MV6SPZ5LskeOY50lOjFP0DFdYrgRpZFmTpWTo,3256
469
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200.json",sha256=-Qh18kY--uP_vewx5SsArsoSYpzVryYP9xk1Ur5p1Ts,3274
470
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=L7y3Ev8CbIF-68FWhoMvK9HH72bj6r6-09__zxK-fvo,3257
471
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=IuvyC8TNhCVAmUZfLSoETsyCKsmejKXrs_0zuwFLPAU,3265
472
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Nd2qn9-7yjO6vAQSHAuetP4ytysnd6UxekL8UADiLKg,3254
473
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json",sha256=10Ntu2aVD5vGLonx-jW0qNw-tgZWdZmzMGx7utDVeng,3237
474
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RFH5FcN2ZCPk6DsxviTti1Q8JU5jzBRFXvUQNgOvnmI,3265
475
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200.json",sha256=JraM-Nvbg5V_TJkSl6UPFYZN1zHHoIbr2pAcksenoTY,3248
476
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=bf16.json",sha256=PxeEH6PFy8bFefjyrPS1ikD_-kywMALWnSrGbpSjMQo,1804
477
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=-DrgCsN-PW9kWkr-bK4817zIuyxUa-CQxlONN1-QQAs,1798
478
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=928,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=iplHjPj366nNBu44ZHlCRe7aMaV2T4QthXINmkWi218,3269
479
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=928,device_name=NVIDIA_L40S.json",sha256=l59WyUnnymmJQykoJzEvvkzwlhIlmyEeVtvCFRzXGRM,3279
480
+ "vllm/model_executor/layers/fused_moe/configs/E=128,N=96,device_name=NVIDIA_H20.json",sha256=JtcHRlPz8xQEAqJ9EWI63oYvdmjQFG6VTHqtt85VOSA,3221
481
+ "vllm/model_executor/layers/fused_moe/configs/E=129,N=704,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Workstation_Edition,dtype=fp8_w8a8.json",sha256=vaiXepgaaixIxU3_vVGcYsA18XAiC8V13phIN5niRrc,3250
482
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=f3iM3xm8hGUirJ4ilAIPO6Pe9bs4sm3qaRKMswN9SKE,4731
483
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=Pux4G7sjfPL22uOJU6t35TXe-VU3OaoPA97TDj9_wZQ,3251
484
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200.json",sha256=he873aoOy7KfFg-uMoTFV4IP7Yk0Dk7mOTuLCTqwZZc,3250
485
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H100.json",sha256=Bq57MPQXuSib06u6OwiEmSzOr3XvPYoD6ohYDJaBnII,3244
486
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=95zLafBGPI4zCLqdsIjH7mgblYiBBTzGCItFRtKiQQw,2749
487
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H200.json",sha256=h63zG698KnzeDHL20MfxJ3cKiROnBd7GVZ-a6WgbcCw,2738
488
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=pCCKkdUzzuBVtljyk7AEIAbeDf12DUiieXaODZXzm5E,3254
489
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=trX2-c4N6hTTD6zFNi6A2bT3FkhxKjkM2rPl-o1K9ss,3250
490
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I4d56uD7E1JMXD9RAxq3FebdPquDsnNEkVaIY9Ctm9w,3246
491
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ypuAxMQ7JESPXLBltt68wly2wTrJzlnobhUMip6xAmc,2751
492
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=tUptlureu5QgyAEedtx5sm7CFudXAE6fIXepOb9gfas,2745
493
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=HUWDnLXTE_gHIeMSNJtgxrx5QK3ctTZYRtNim1TJUYg,2750
494
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=h57svdmDlZC_D8w9XWjPRS8ciYVkJiPEYfhrD2NRVVY,4127
495
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JmXhUnhX6YOy8RsmT0zFLGyNCpRBPV2q2Db9Y9ctZeE,4144
496
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=k7JkvPualha73fUM4GeVI822m-Zfl0P1c8DIw2b4R5A,3253
497
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=vvf0vmcIHMqctQ_X8j1LqlmkuImr46rDUCnl-apb6r0,3039
498
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=_4U3pXWYERfwF0Ig8UTSCmeEI1vKH2irHMEBov6ZNqA,2751
499
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=2048,device_name=NVIDIA_H200.json",sha256=Lc8Wquo4hmXGkUq_HCxkxW1fzDnvE6jHZSEc28-i7lA,2741
500
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=G4PKqWxh0MlBhg7QHKj0m--_fP3Ll0gs7VJaeg-NIDM,3254
501
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=bKX9AvcxN6k-i3RUmHSchZZ3rjoYRYb4iBqhCI4L3MY,3257
502
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=bWR6XBZ4nJ_ROg8rEgrQGc04I3BDbwILDHMZxATO-H4,2740
503
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json",sha256=iUuPfTcmuEDLjHm-lUfJp_-b0mhnf1_RxRglKLJ83Jk,3259
504
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=AP6-GeoO8OtIcGA2kvJseui10HsvmFSjg5bHAaZ_aQ4,2753
505
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H200,dtype=int8_w8a16.json",sha256=KVACMsHRnkumqwKwAGIFFvogtqoPZ7XC6iM5KOZD6uU,3248
506
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=_9HO7SaR6aQeh6vqCDpo3kjHnGJ9BVKLiMwYYgd3SmQ,2913
507
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=2ONiQSa9odzdPe1dIgBpP24l5z-5wB1eos06xOj0V_Q,2738
508
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=Twkm9DVNxijpowfvioJ_4cKwIIlAWdyNWO9TA3gxAHs,4149
509
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=1xLr3PpmuUJD912yjzGoMmgvJQlazSao0V4f8nIJBT8,3254
510
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=THQWP1o2bWhnJh0rq3ZIVvs_sagIJgoK4x3pJbiFbHk,2910
511
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=o1pR3rNpO1eW4BHOKpPIQLjviw4P2X5Fr4HQBcdHA-I,2747
512
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=iySqae0zI_PRBLqV-vfSCwDS4Jxcl5QjWa2NnhndL0U,2752
513
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json",sha256=tDqh_env5r2Z3r9WLMH8fJ1oCGb83L7RrHk2eoH02-M,3258
514
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Ha6zrvORRUe8TH4DmVVnHKQIbxX6BnUmPER5rtWJz-U,2748
515
+ "vllm/model_executor/layers/fused_moe/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ydsFUdXdVE_ZSScVhUxvxOFwKG-nkTraNeN69wqzxIM,2903
516
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=AMD_Instinct_MI300X.json",sha256=AFLeub_dwZHc4qEtvkQW03mfG9fdgeuqTTiP4qC8i1M,4767
517
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=AMD_Instinct_MI350_OAM,dtype=fp8_w8a8.json",sha256=RmeFztUNysKjmg89emtghZlGWl9uKqmlMupww44Q4j4,3735
518
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=TtDngG7ljrU5RtWZ7g-xxdBT3uEuawiKhP8EwPr97XM,3254
519
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json",sha256=ZjGBT7Z1rsdj0jn3WYR_TM_s7s3S6JSSIP_88M_pP_o,3278
520
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H20-3e.json",sha256=u09XGUdUQqSDasrUgOQeu7ydp5ft5US1oSM0iT-BT3M,3235
521
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=UVpaplev1WCtwa80V-InUtof7OuHfe9owQthaTfqK80,3299
522
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=320,device_name=NVIDIA_H20-3e.json",sha256=JBO_l8hfxCbiQ_PvoqS3Xxqlz9i5PP7QFfXjGKLf7bw,3237
523
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=Hjpi5BF5UjT0R0uuluIeZMWihlAM9zyWdV5Y2BJu0_w,3730
524
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI350_OAM,dtype=fp8_w8a8.json",sha256=KudLj1Md-XBFWsivs_7aGg-UQno7H6tzxyYqHQKoNg0,3734
525
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI355_OAM,dtype=fp8_w8a8.json",sha256=6QmGz-7RZzAT1-XS2twHGAbEpjm2Tpkn7qjfBMqm76g,3736
526
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json",sha256=jEkkKJeqWQ2SEqbs2rBy3LQbAXyKWssnpXvP3wPR3EM,3281
527
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_HrEta1vlWll_2c0v6RpEIUQirMD1QaOMU81VaJh9Nc,3254
528
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HvSQqJi8Lb7NBGmvp9YeF8k3nB0t94DJ-LvCX6Spjyk,3255
529
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=EZV3ffICZEq6X16UNFpHL7kOuV_qmj1L8fJu_F1c-DM,3260
530
+ "vllm/model_executor/layers/fused_moe/configs/E=160,N=768,device_name=NVIDIA_B300_SXM6_AC,dtype=fp8_w8a8.json",sha256=RpPXZ9BFciPWLuLVAVHKkVM-NzgRvoHyH4L5H_N01iY,3288
531
+ "vllm/model_executor/layers/fused_moe/configs/E=20,N=1536,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Server_Edition,dtype=fp8_w8a8.json",sha256=JrbI8lzY5deo9Lx1rw7noHf1jzPcOv9vcni__wDnZ5E,3288
532
+ "vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=rKQwdgkictjg9DjBFVzHq9LOMlX_Ul27jllTABjaUtU,3252
533
+ "vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qKcB2Ka8jkahKCNF215Ec6rCoy31OrElDL1ZHNgCs3M,3252
534
+ "vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=K1aeYxtOM4niB6auzCEBVudmKIKNzHPjMoFeQt_KD-A,3263
535
+ "vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=rtOl3v_tR1iCF-Em0KihtLFzK5qLtndPK-jKCERLbNg,3264
536
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325X,block_shape=[128,128].json",sha256=fT7fwjuit4HbbyREYV3ECJ9Rm88FW-V54e27nG9nA_Q,4741
537
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fT7fwjuit4HbbyREYV3ECJ9Rm88FW-V54e27nG9nA_Q,4741
538
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=HNvrgcXxV-eVMLwb7zY_R5KgJ7uBz-YIyQsKq1lWnWA,3263
539
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json",sha256=bHJEVy-CeImiY9JBRCMlHfHPAUi5xO7ENxgVVboN2Yo,3258
540
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=PnNmKSRFznCIUzZ4ZfaYTrMHeF2_kCQr4_bsEy_9Zu8,3259
541
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=0Vlxxzp4wrvkFj-NF4OAsJAaPkm-hhisJg0tgNl-W9g,3254
542
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0aSYzpv_cBAlpWCPrfGgNTCfae1KdKQnT56E8XFQl7A,3262
543
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Lqom_VMIPduSZTZQdeL2Wl_x3r9q6RmI9bojJrYwQZ4,3255
544
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fd2p65T9OboKIgw7MQc4IdKaJsoO73Nu3VQiKjV6Ffk,3261
545
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FUGuYbs_QhqKfErofvbTUplhAVN465A7NR_-ryXvebE,3741
546
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bpDPbTyrXLyCSy-o0diveVVeVUF_xj-fdSzCzWmEcKA,4733
547
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bpDPbTyrXLyCSy-o0diveVVeVUF_xj-fdSzCzWmEcKA,4733
548
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=skSJdv0Pr4rba5ODxp-fHZ6dpxn8KkvACGzNf74j81I,3257
549
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=wMt0NyoRSdACdmS1Qi3qFiu6GiFX-4lVvbGEno1W4zE,3252
550
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=mtm7RgEBEJJkHsOis9BtAFo1OCk3vBbt7l7eumDzd7k,3263
551
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kfEjBrcwt21QRzimrgY_SQ0syJVJzx0AcWQcKQ3j5sQ,3254
552
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Vz1g-YtTWcv573EYaR7LzhJlRyonaMsHPT2MMjuRJ9k,3270
553
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=JnqtO0t2HBcQECdYavi18mu9_MwblGr4zfRcW4zU7_c,3265
554
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=b9odBjWC1mjQRIIZIFV8UPMTVE4axTP8vkmOXfdUids,3296
555
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bpDPbTyrXLyCSy-o0diveVVeVUF_xj-fdSzCzWmEcKA,4733
556
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=inHFNgamaEPRIELrAr-Wz89KcJ8DajQvntdhsL8zk5g,3292
557
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=l8y606GTM4Xnd9CBdhjt7LuA_1KLQS41PInHKNfZAZM,3242
558
+ "vllm/model_executor/layers/fused_moe/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=rVORXxNsxy4WmO5SJR8Sd4k7vozKqhYf50wZNCMeQzs,3239
559
+ "vllm/model_executor/layers/fused_moe/configs/E=32,N=1408,device_name=NVIDIA_B200.json",sha256=PoVwSGuqyF_0DrRTrggdmlfhUn2dmSbc-pP4PjMEF4k,3278
560
+ "vllm/model_executor/layers/fused_moe/configs/E=32,N=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=r0vxILYelmq7KarzO-3yjv9fA0Z4ORzCo7u_UgWbdXQ,3292
561
+ "vllm/model_executor/layers/fused_moe/configs/E=32,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=IOYqUudflMQ7PBGNxFYihtuVqb-J4eVp5BmL_OnIFS4,3287
562
+ "vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ZvsFOizI7EY5V_V5gdjyTgbdJfeKrbxhISxcppSfduo,3255
563
+ "vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=1XFStvhg3yV7cMwJcpbLfaCY2B3nqZNrJgohJn0ma5g,3254
564
+ "vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=iXoa10iZi9EQ5jAiMIu3hCemsvjiWVBtn4rKVarVCCA,3256
565
+ "vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=BdVjlDZWnX6_rduBTQWfc6Gb4o9z8JRlI5XF00CnJC8,3255
566
+ "vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=KPI0AqxGlxtJ18tj-NiFjBleS_ihwmLSt5pg3GXGJ-c,3255
567
+ "vllm/model_executor/layers/fused_moe/configs/E=40,N=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=pwoiPdk-veNV7Um7os7sG5UrRjKgOsbyxMfQG4z4r9g,3285
568
+ "vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=S3nHQ7okmQlkuz7gQnHmZWcQQnFDacB4Lz1isbdZ49k,3258
569
+ "vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=86ajYfCiq1urzJxcPrvyx884njCMKizCrS6hfx69WPM,3252
570
+ "vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=86HDa0gqUZkPaOJLmuax-j-HBC7t5P48NuKMpH5Uj3g,3262
571
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=qZgSX927zWhvdQc7KjSBZt-Wk11LTwFIK8UtEU9AFJM,3274
572
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=wCHErv6EIufM5XNOchnO5haeXrkutooMxk8AIBGc7gw,3294
573
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200.json",sha256=NBj9yhhUWHpNcvwYhPtBKEn1It7BbrnRMRN6Ji2Iazo,3234
574
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json",sha256=XP1z8IdGklVXVkMIbCtAzWj8nUz65GIZaqZvBvD7v4M,3242
575
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=7FM4MDavNVOcEOFldsZs5H-E5O6EIAHDY9n-aiLY_Kg,3238
576
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H20-3e.json",sha256=DaChAo79RafXGjpAOeO1CQ9DazPk7Vazb5bAEyDOYSA,3233
577
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H200.json",sha256=BB3qPMREaACzWHmhvcETQHLDYGX7GXTKr1E5cm29uC0,3235
578
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=JTb9ox4ZrZIR1NmMPjvMWISVZbibaEBPdMH6EKe62wk,3297
579
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200.json",sha256=0avMzgfoHRzULbxIdzI1SVCWUSBP10kKvxy-3Mv_y_M,3243
580
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json",sha256=yIEwME0J6ZNfGq13Vj7OA9DmUyKdFZzFj8uaLVb2Yp8,3246
581
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=YopFXEwMf6qpCwrQ5OdJtGVsDvvaQFUcEuGGIFvmS4w,3286
582
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=pnK1HQ2B5ECqCBolRa5Yb4qAClVoJ2pidBnPy3GBLeY,3244
583
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H20-3e.json",sha256=q5AAAH8gIaU--3mXhSF1VdFTFHNAy5c-gUvYcm9qhEg,3235
584
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H200.json",sha256=he8rleYTT40kpshJW1FsdiyR0nRU367CqytS-9-UZNs,3243
585
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=rJdA9D1Wrwh9qqcmyHqG8n0L4Id1aYWmMOjqKEEmQno,3294
586
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200.json",sha256=LcMD2JddiX488ddRCsh0cXaf3my0VT0IweqQDyTWZwc,3245
587
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json",sha256=44VdfyrLo-gl23cMeSqSfoGrsqWcjv5-lXwU5y5spE8,3250
588
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=SyMqNl2wL11cbj95x14YynB4YwyQlaOf1yPPIK0jcJQ,3249
589
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H20-3e.json",sha256=npr855kvWlHILzi5M0sjYjofPAO9bf6WCF2oZZ4u3to,3236
590
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H200.json",sha256=xR_v4wy8_ae9fGyuTnhWY0d29NwC9ChPKvdCK5_PS2Y,3244
591
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=9M3IlMbbIrCvfhQQHsY08NAOoaR8pdd57E30JYPKlRk,3264
592
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_B200.json",sha256=femFBZsNptZ6DlQ32dpBu4zhFxaG-kcs4MFPTxipui0,3234
593
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H20-3e.json",sha256=iVnryOC43Rirq38PwPxzIHrWvf6pA4wHZtf1HOgGtlI,3232
594
+ "vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H200.json",sha256=K1HkIsowgSbvwtAppZZPudYIIni_waoSxDkARTCEQso,3238
595
+ "vllm/model_executor/layers/fused_moe/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json",sha256=4UXbsSNHmrSWnD85SdRMLp4cFGRufndzJjB6hoQPclU,4736
596
+ "vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json",sha256=p6TKUp-KDeLB9E9LqThR1e7J2-ogSXPJojISdHgCxaY,4727
597
+ "vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json",sha256=gHxtmO_uvpueLVlsJgXBVE3_pS1S9EeRxNmHG_ZQszg,4729
598
+ "vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json",sha256=tVdpbIU1scsylx6oz3IADhkcwvZaNqw-_QVb7a6oVX8,4732
599
+ "vllm/model_executor/layers/fused_moe/configs/E=62,N=128,device_name=AMD_Instinct_MI300X.json",sha256=_Mn_3ZuKGqNnXtcUUZA0rr29c_lcp-b32uw57oYHgVM,4721
600
+ "vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=AMD_Instinct_MI300X.json",sha256=2eFdAHTU_YTTVad_OEcYZcSbtm5gtlHg4ChxU_v1a_k,4725
601
+ "vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=sCmfFCa-I5Nft9ap-ScL0PVEKZFibkhtVslbFs_NLQ8,3234
602
+ "vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=AMD_Instinct_MI300X.json",sha256=kKu6HpksA-NKVS4CA2ivjlAQEshl1HEufQ0Qt-lTZGM,4732
603
+ "vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=KmYAPOgz-2qn2c5lY8u9XRy8i8HNkmOR5m45TIuwt4s,3235
604
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=6QPLhZurIqcMVdy3w0Dd7gLViKxsyJRBz-qd8agpi6Q,3248
605
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=WPu80-OWyEJBy1hdnewLN1H1neFW8UVJrqyeDGegXc0,3250
606
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=PaFLbT5ftJiiVSOVkq_DH01EcbIs0sBVkCd9PdYYmw4,3253
607
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ozS2ECxk-Dsd4Y9DgCGGwDwJlCf5T20ANf5gnTUMuSc,3252
608
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=KEN6xt8pgPH_FbLT2fsAD4s03_V-Z9GXuEC4IKe3cPg,3262
609
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200.json",sha256=w18R3eHB4oUhfbcCXjHyDvp0RiDSeCrfM-VFESim2hQ,3253
610
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=1408,device_name=NVIDIA_B200.json",sha256=4MqYiUxVPLgkiaTl1vZ5Q5wCwsLYNp7O2-kbOSYmKjI,3277
611
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=Nm3LPD8JxBYGflI42Cy-xyxZlBLrGvVbnkf9NUmx92U,3250
612
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=iz4W1UAV1fcz1ZFh4hNQSLJ_F1MdXW-V3msy7t0WrRM,3262
613
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=dYpKgvuG7Jji0W0zg_E9NfIojStBAdBcKd4B3nhimqk,3263
614
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200.json",sha256=CXiHlGpea5cEGmFi28Jec34uxEZITF2XldVFcJteZX0,3251
615
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=hLFfmEnpHDZlwBlx7TzfxbjCEywqHEuhjllVR7g9yMY,3259
616
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20.json",sha256=g3M9w0Noi3DyQB7fcr3jUM62_LKZvTwbY2GtzDGd9_o,3251
617
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=W1q4PfievvgJ_SiPsDhOsR0Q0eJKb4o8JZhMcVhC-_4,3264
618
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tku4-yTbIr0H5TNrm1Pq3tJJFYTXqHpdzJDSEF3bk9A,3238
619
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=HJcV-Tzt-yojzNQkPCgi84B44F_RppXxOIicRyg20-U,3264
620
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200.json",sha256=bM9g-XpirsThO3Q2x8ChSx3PPtHuHRXLvVMnTWt8jLI,3243
621
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=9vB_5KLq88zBCNpyz6LE7qAo2eS_sgTNsOh6awGnjT0,3235
622
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20.json",sha256=b6lqVlPt68GZ1wlYu3UtC6zkXnnnKwh4tKGltXNvTVY,3235
623
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qjGI3FK2We1bI9PGxIBqa6eGSjPXysUUgc7_Tzz3mPQ,3290
624
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=oxOKFDrgmw1YmgxTtRa1uoe3p09ylTLrkj_jOTqNh1Q,3249
625
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=-B6gZAEYLwMJZOnpO81pTxqs-YVKs_144Nn9BSLaMh0,3247
626
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=GPjPHicomrS7ntHu7nnvgNXcHCoUw9vhyTUewkXpppo,3252
627
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ObHUCUAgHTnld8Cq9Dy1n3ilmbBzyNC4jZcz6YYhMXA,3264
628
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=WegYsHl39QVlHu_4EZJSrgA4LQ5fYxSVNWFhoL6W2Rc,3251
629
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Hrlas0Nt7d3JMr1vTpI3OVgkzxqcRziSMfFf_U5pQ58,3267
630
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200.json",sha256=J59rmqF8NQWkqmay__ahA3t3IwaPXNu5AVNLnTaDfYA,3252
631
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H100_PCIe,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=d_tIZcrWnGVvgmXBpIbsFMAKKC9-1eP6nbZSqWgzOm8,3288
632
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=0bH7NZ6VmBBycMus6v7sDXCXtort9awuEpttLLMTZms,3242
633
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20.json",sha256=VptbMpckYKHKYMJZS-EaO9G0cSL6nciL9XyeHiZN4Fg,3237
634
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=896,device_name=NVIDIA_H20.json",sha256=GNbp4W4MBoHHN4-0sXJovY0lX6rHfZzGyKicrumupGQ,3225
635
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=bf16.json",sha256=AbwYfuQiAbPJb3Okwd-BCTWs2P2Ao9REEh2sFOkoMuo,1804
636
+ "vllm/model_executor/layers/fused_moe/configs/E=64,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=FiUQOl86K_LlCd_RmJR3BpDM8whX07CE6Q-6pp1rR9w,1797
637
+ "vllm/model_executor/layers/fused_moe/configs/E=72,N=192,device_name=AMD_Instinct_MI300X.json",sha256=r36dUUfR5rv7yS_I8W56z99VAa8LIfaNRQko_97R14c,4720
638
+ "vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=AMD_Instinct_MI300X.json",sha256=XMMCswkzdQxVfOBDM0KXG_ryA9JnX4hFKhF2QspifsY,4724
639
+ "vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=56iA4xNOSuaGWgz2Qg-NiROhpdoBMto4NVUnisUsyD8,3238
640
+ "vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=AMD_Instinct_MI300X.json",sha256=68SI7XVkxHS0k9ApTW1-nSnIqOtbe8rmatNexWRFyqU,4736
641
+ "vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ICdOnZoM8waiOVeVYP18QiPDSbtg9Q6yO-OrO0-2xtI,3242
642
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=X8FVPE7rLblDs_Dw_Iu-KDw9H7PaC417EHyVclYjfv8,3733
643
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json",sha256=FsIv5bqSpkWbxK2dBfg1N6tX9epZ55ZhgkJCD7hENlY,4733
644
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=CnjQX3SlQn6fIGsX6P_dbNO0TYgAd-sVUb1FfDcDFUo,3732
645
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json",sha256=fnO-v4YqBz0vUo0UtOTTD0n7VDG_ivczeQ1tR6Qm9f0,4734
646
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=V_sgDtEtGEuBsGVa0maYJHhhGqe1NE7l-1ek2ed9WP8,3082
647
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=QaITFIJU4UsrOBXaGdPYJwTmYJ0nT9kiiqeUiZzvd1k,3270
648
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200.json",sha256=CC_jsMhXzrYne7eIOroDa0fCBKNnffiaVW2TKd4P-ek,3260
649
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=LgHbxG1kQV36zZPkJcnurHYzwAjMh04lvEHEsfzS1t0,3732
650
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json",sha256=_fcdkmWvdMqHiH8ZAGke-zXhH7qVPQx5CmKELW5hRCA,4735
651
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=mVH8Rl4sLATinf7_0A9lTS83kv1E7Cm9oC0BL-pc9n4,3732
652
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json",sha256=JKYW21c0CzR0fgE5ZnYp6C1sY_tVRlm8L_lgak5V5zE,4736
653
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=yTf2R9cngSf4OafucAYlDDn4-bftaMFKaY7qhaBZPqQ,3739
654
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json",sha256=_1eVE7ok935L2V43-3D3bVNWSVaoViia19sh0VrXmXM,4735
655
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=5exlPUKvZxGDR0UT4_Dn5fp-_ZETJ6_Dbw_Vk1u8bbE,3735
656
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json",sha256=18v6YruKbQ95pXPV8ocV4VdM1zNw3aZFp3WByeUkNSM,4736
657
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=AffDc0_51ML8HiA3757zbD10TZJdUsUDIYIqO4g0yUw,3250
658
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=IEYBNjt9HGnzoOVSWvL0A0jUqq926QD0_BvVYR4RA1Y,3252
659
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=Ns9Y12aZbJnFhcG3nwb67bDqqiQAo9tdTAIe8K2Ajz4,3255
660
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=uGSLFPZXK_JQ3GTDUAEiIecDor1yjbC3bJvMolF0Xl8,3267
661
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200.json",sha256=8q6ol5JQBWj6yVfzFOn7Gz5MSXTaW9javL7qQmYVOwg,3245
662
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=6jRC0oOpVpq5c1xePFKNRy-Xtmb038i4LE9N2zao2W4,3730
663
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json",sha256=cFWeyNJtEbs-Bfohgzclxo1rcYGU863oV0BzJyQ4T0w,4734
664
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=SMtsqtQeqcyy8aNwl9hPxRvx_XQdT7I3SBDNJ3OIvwY,3728
665
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.json",sha256=ZyOFJB6GUgGZsAjjT43XJwG8P-QrZ5yTvmgzQP7ThQY,4734
666
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=HOxWmCI2ifHmWc0or2y8nEen86jDeLDov1-tuMzuhxo,3256
667
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=csHezh0HGWaNwrblGzMgcE95hqbqjWS8HImLRJYr_ts,3266
668
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=_5weLBinQCDzyV75hHKIT95Y0ce94KWft2_5BC6EkbQ,3254
669
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=BTpwe2RgMbzP9MTtbcJ16I1IAK0ghD0rauWEea8TOKE,3446
670
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=DlatRLPaSr8HJuO50gRZ2lzXoelx55EP3SDUdgIT2v4,3269
671
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200.json",sha256=TXSOoqvi-x8H13xPqrB9qz2T3opEGA-2D0v_4n5BEG4,3259
672
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ro3drDpWAdeXH7IjMvx8wYGhIuDPOl0bpbJaIB5Msns,3732
673
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json",sha256=w_R2LL8k5jNVUARcqvSgGLvNoQiQC0Mh73ciqSIAz54,4734
674
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=hjDoTXRmEFLKhhmBFEjPowQus_z23ISonxFljql3c9k,3732
675
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json",sha256=AdOTy7ASetdAXUhNM8buoU8_rLLjcUYF0m8RGFrLWRo,4733
676
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=Ru460ZgnUP4U8OsJfwF8n-AI-gfcolNR3_qzoxG6DtY,3254
677
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=K6BGrKw_oHTAtHjsZldcjp-BUM1dIecKXrrRn9OpRGs,3254
678
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=4aK_plqztXcJ-hs5_PsAvM0jclMzcO3hd3zTo0FhDro,3251
679
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=qqFoMaObuO8pFWcSb9q0wYsdC4eSCO7B-_ruQhR1N9M,3264
680
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=-5nkLIunjG1ghPoUEtt2AXEQw9oGiilP7K3UvQv9CqE,3252
681
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WKzddrIXo-KavpuXuouW3aLLAptu5Q4XJUb5K2PLgDM,3262
682
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200.json",sha256=ad1ZkkSyLJwRGb4Kf24qg5hW_DPmt0BXrKR85oAiV34,3257
683
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_L40S.json",sha256=qX5_yErBEwDRzhv2FvxrS3pEMa8zn0GHzLp5TUMX90g,3872
684
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ysRCWmxV20K2BYD9XEUtxwREFGtA3QHI191vHRA0k_Q,3733
685
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json",sha256=L8VA1sfygHoyLJ-Ybfs8DP5c0YWFmMkwxHT8yJ9PEFM,4732
686
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=FJWpDLr13XF3hHiHfJykpjbLiP7Ccu2en3U6BL-QwXw,3732
687
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X.json",sha256=FnVcfzf5gXkQRt0XgsRzIQVbDPaUDOwWJX_9qOlyvRc,4731
688
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=DxYu8regZOSFu8ugFGA_QbwWK4g8xwQUZF9a_nNY4Cs,3255
689
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=obzfE_9XgsbFNfC9biYOHxR-V_Bgc7PKT8qZZJaiJJc,3262
690
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=qwKy8oaMsd3QrXgQbM_x9xcfYiHK_Ou1CEwDPL5Gbgo,3259
691
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=qUifbWbE4cOKZbIHWmmLx68VRaslQX69eZHwRIQx-7I,3269
692
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200.json",sha256=JT-ZMLhAqqzSkqivOW5ATTKRlyyaFQkqQDnaPS4DE10,3262
693
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=QsR-Xr9vyuiArMTSo-dX-1DFgATfqwIGOzFuQJAuE_Y,3734
694
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json",sha256=EtVorGY4khTEuimlqZu0AAlPz84PH3ZkDZmVpxLtgQw,4735
695
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=D3wX0_s_ylo3nLIUfaWZmGYtMvX7oiieOLMdQ9k7mng,3734
696
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json",sha256=JPdO0azlh4yUvbpC9dEHYpRT11ELEr5LXBSb5XP4E_4,4735
697
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=BAJnXTZoewwCtzJLUPJ0oYuALv640MvDuLseGcsYaaw,3252
698
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=-Tj7ImS6ZFDof_0VTyq7kVm8XD9B54RD6CUOPSf3Jjg,3265
699
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tme0ydWzIxdABZLk4tU8G_X2dJUYGGZNkQzNGcmcvUc,3261
700
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=g6Ivy4wvadaCAMJ4ZElbUU-CwyTMdbaa49M7IVQhVjk,3273
701
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200.json",sha256=GstQosPPHUn_I2DV3eMGtn3xXOw6kl1hb8L0EvRsbEU,3261
702
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=kF4Fx0yHUmiMSLFNXT6xqAEA4AgCaHOoy_3irv4dNss,3732
703
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json",sha256=uOlVzTdJl_4VrRK4wmxIb8JKfveFZRjO9syjw_oEeL0,4732
704
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=plnx7r9jkcYXkhvapbeeNvUg3NMGdGsIgIPSrfVy2qU,3733
705
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X.json",sha256=UC-iTgh8_dUSXRaYHOIhDH31KOiJmcfqM_Bv_UBf3ks,4733
706
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=sY2nWMPh9lsIkhPCjkHO245wpnfFbrHmzdcZDVFPVww,3265
707
+ "vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WQLKugnKzlQ0avf1N-41lRHtG6wJ56DfVPv_nip6NBc,3273
708
+ vllm/model_executor/layers/fused_moe/configs/README,sha256=W2yIZkP9O8GGlg97We9BJfTtWUtPbuz5ZH3esrrjBX0,572
709
+ vllm/model_executor/layers/fused_moe/oracle/__init__.py,sha256=48Vcuw16i9R99vM3iDVkRkX107yJtFeTtdWgLQE-XFg,107
710
+ vllm/model_executor/layers/fused_moe/oracle/fp8.py,sha256=0txGLZ2yTLpespjL5U2U__UT_Y9mLDa1if8ZQnRwYNk,12753
711
+ vllm/model_executor/layers/fused_moe/oracle/nvfp4.py,sha256=epjQ6dzuGUE_dNgxBH79T5IkKLKlxnrwiFmuwx0pAf8,8483
712
+ vllm/model_executor/layers/mamba/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
713
+ vllm/model_executor/layers/mamba/abstract.py,sha256=5SvBvXKQpQ7n_jG3nelsun248Jj9-jHwn__103rYeOQ,2429
714
+ vllm/model_executor/layers/mamba/linear_attn.py,sha256=J00weDmLflZV1jshtA02XasPMHTrIYl5WYas5txSS4U,15254
715
+ vllm/model_executor/layers/mamba/mamba_mixer.py,sha256=8LOvKWA4j6OiXGBxCNRMCEHbOk2tY9Jc_0Lu7dW5IEY,20211
716
+ vllm/model_executor/layers/mamba/mamba_mixer2.py,sha256=4GdPQhFbvwrrcfPp1D5ku_Ass8RmnRdXeQYewmQmdfk,37646
717
+ vllm/model_executor/layers/mamba/mamba_utils.py,sha256=UevD33ksJN7oTSto0uUpHUZQfv2EVmMMW8YQgtKuoFA,7511
718
+ vllm/model_executor/layers/mamba/short_conv.py,sha256=XpyOx0Hy5L41P0OoBVrfqwF6FjOp5CJ-gWgV99hDxww,8392
719
+ vllm/model_executor/layers/mamba/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
720
+ vllm/model_executor/layers/mamba/ops/causal_conv1d.py,sha256=9OWA3FY6GnKUiuuNTnDeE1p-uIUdNxQtke9XELW0_f4,49543
721
+ vllm/model_executor/layers/mamba/ops/layernorm_gated.py,sha256=KA5JRI8jEStDEkN6U6dqaOBQSCWugxUelAhZISZyf7A,5228
722
+ vllm/model_executor/layers/mamba/ops/mamba_ssm.py,sha256=WFV7DyJ2OOTK9c8zbHC0AKcYcD4c1ZY1l-Af4bhmqjo,19749
723
+ vllm/model_executor/layers/mamba/ops/ssd_bmm.py,sha256=mlQ258Jsexnb5vHGh09YW0l-rF3SZM4H1R29o3hb2-s,6842
724
+ vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py,sha256=Yow2h10PSWWKvrwT3TRz7UZTCq--99j7MZToXN59aCc,15550
725
+ vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py,sha256=6-0Dl2-frs5av7ra-H0xHWPupVaSo0Vex4d5vZVq41Q,24226
726
+ vllm/model_executor/layers/mamba/ops/ssd_combined.py,sha256=oKPphPh0wjU3XT3k5U2t9cHb4jDLuYzIQuWK9w0sOcs,7353
727
+ vllm/model_executor/layers/mamba/ops/ssd_state_passing.py,sha256=OWIEJ6WjdYHbX_7HRzhPt50oejUjvzhBTST6bQPhjas,5275
728
+ vllm/model_executor/layers/pooler/__init__.py,sha256=AvMJtY1sQcP_n7SWB9Zp0F7dBfgNxKOpoUfjuZfP1_k,176
729
+ vllm/model_executor/layers/pooler/abstract.py,sha256=NjWccsWi35Pm2UMFctnJBOQkk1pXBqu16XfOgooKVpk,1090
730
+ vllm/model_executor/layers/pooler/activations.py,sha256=OW_v290AJ-bEW4MPQvjIv1FyXcEjDNscu62roVmzt8A,5269
731
+ vllm/model_executor/layers/pooler/common.py,sha256=OCBuSu0H7kJC8NvPWYIII3zQKjMchI-s3iAiogDBuQo,1037
732
+ vllm/model_executor/layers/pooler/special.py,sha256=Sf6yqLCJIJnNT_H6zmp-3J8vNHnJ2YHYavWrMxXZPtg,3918
733
+ vllm/model_executor/layers/pooler/seqwise/__init__.py,sha256=NOONa95ncmqfCNzBPzLwhkg7HWQUksRFPar4eDNVB3A,1059
734
+ vllm/model_executor/layers/pooler/seqwise/heads.py,sha256=6H96FusBpBUX3jhwe5L8660Ol9ZxrOtfwhdsaksotcQ,5111
735
+ vllm/model_executor/layers/pooler/seqwise/methods.py,sha256=vdyjzEQcbH9ze8fXNPJMWY7WUV8pEl7uSongnsZ-ek8,3067
736
+ vllm/model_executor/layers/pooler/seqwise/poolers.py,sha256=HR51qJYdh4uaiRgqDJJqNkPOacq13SjWffycxuRNaVg,3957
737
+ vllm/model_executor/layers/pooler/tokwise/__init__.py,sha256=x6seGnPDz8mz8MvMbdFA7vhv2kczv-quV3_2n5Ahwgk,941
738
+ vllm/model_executor/layers/pooler/tokwise/heads.py,sha256=CCwLTzPIZ_s344JSCPoZWNgX6iO-vWl03uB7AbBFTLo,4149
739
+ vllm/model_executor/layers/pooler/tokwise/methods.py,sha256=ewPD-pazZ_mxULxR5ZW1m-3tfHoHz8SKlu_OKlCEO7c,4240
740
+ vllm/model_executor/layers/pooler/tokwise/poolers.py,sha256=Kaa7HyWLRItejQTUgtwSUYVtprEAIr5wyyeNVVaXFes,3951
741
+ vllm/model_executor/layers/quantization/__init__.py,sha256=GGI8QB7TsJ2jnEvp9xOs6sTtkNkYoS4G4g4rSo_krI4,6054
742
+ vllm/model_executor/layers/quantization/auto_round.py,sha256=0c9XR0VoQGfKhBjF6lpS3MNDleM6J7FoSPV68P8WsaY,16826
743
+ vllm/model_executor/layers/quantization/awq.py,sha256=ndAuoaJlJI2cL-sTCDeT5LEanOXo_VhABBCyv1PLGtM,10022
744
+ vllm/model_executor/layers/quantization/awq_marlin.py,sha256=nLv8uf3X4OPwoDvF-iq7O7ae_tTjqrKJaiDvh8E0hnA,29704
745
+ vllm/model_executor/layers/quantization/awq_triton.py,sha256=fRH9rX5jDSqQtdmcrXwxtPtQEiKxTUdPkAJmtvW_zng,11620
746
+ vllm/model_executor/layers/quantization/base_config.py,sha256=1iCxfCdxsz4ZJ64SzDK6QUsDsW50jJgb8Q3K4K8C0yk,5765
747
+ vllm/model_executor/layers/quantization/bitblas.py,sha256=QGNzQWDLRRvohawjWVUVMLoK9_GyKDEEjVDm70qQLgY,17358
748
+ vllm/model_executor/layers/quantization/bitsandbytes.py,sha256=nxgtNgwUxdf0vAKT4lfkNfgoBM13PSIuIWPkccc3nKQ,21201
749
+ vllm/model_executor/layers/quantization/cpu_wna16.py,sha256=eZrcTDWFYGKZ4U_fIiV86BZG5AUBPxVflcw1a7zrhVQ,9729
750
+ vllm/model_executor/layers/quantization/deepspeedfp.py,sha256=f8fKA4ZPKhEFCuv7jcZIrC8IQd6wXDecddoWbMSkCzE,7278
751
+ vllm/model_executor/layers/quantization/experts_int8.py,sha256=jHg4YUU2yeiNj6qEslgd1I8XRDHxCENcRZLsc1FiVf4,7048
752
+ vllm/model_executor/layers/quantization/fbgemm_fp8.py,sha256=2SZDxFbn1T_FVhR6hGj-c-6oyGw7fJQqTHbpSkY4PCI,6621
753
+ vllm/model_executor/layers/quantization/fp8.py,sha256=vB0wBZ4PMSPTvlb6821HcsLy1V2IV9RDe9o0SFRbDwk,48313
754
+ vllm/model_executor/layers/quantization/fp_quant.py,sha256=lp6PRY-Hwu5QfUChi4yJ3z9shstEnQzUHLlkEnDNN6c,12858
755
+ vllm/model_executor/layers/quantization/gguf.py,sha256=Wn_59JULVmVCOvMFf46-iRWpmQ5RNlMxp-vYvWN0y_E,23487
756
+ vllm/model_executor/layers/quantization/gptq.py,sha256=ZuszLML4Og7f8eTZmdEEwCZAAeNj9YjA9wz46wIR46E,14814
757
+ vllm/model_executor/layers/quantization/gptq_bitblas.py,sha256=rPSt1jT8dyqdslSyGHd_hDB3uIUVRalCbA3SHMs0R3I,16626
758
+ vllm/model_executor/layers/quantization/gptq_marlin.py,sha256=J5krmM4eCvkXVgLkRvJOJJMCjBUMrQhzP1d-GVMZfJ4,35179
759
+ vllm/model_executor/layers/quantization/gptq_marlin_24.py,sha256=PNVtvV2PCMPU_J1UtXlzrZmeOMfEXEfR5_KSYLZlUoY,10559
760
+ vllm/model_executor/layers/quantization/hqq_marlin.py,sha256=XvtWwpRWWwXG-ihjyOD-jRi4MJhVnIybrm-H-DQAkec,12502
761
+ vllm/model_executor/layers/quantization/inc.py,sha256=mJJ0pQCm-rFafcbsv-0BBK9AooCtQ4nK5OdpPQfg2Ds,2252
762
+ vllm/model_executor/layers/quantization/input_quant_fp8.py,sha256=KIEsY--TK3c2rAomYluDMLVAOWHYJhcJjpJmlW7MMhI,7641
763
+ vllm/model_executor/layers/quantization/ipex_quant.py,sha256=ttJnBdmnMp_2m5iaV6xmUl12SVsSfIPVa-nGK9oTyIw,14891
764
+ vllm/model_executor/layers/quantization/kv_cache.py,sha256=Y_fltN3d68SQ-U9GBuhbNPcGJnwpbupGMO8N4K36F2Q,6504
765
+ vllm/model_executor/layers/quantization/modelopt.py,sha256=SLHkeLGYf7M2g510XLmqrBnFGmoMiI8-AMDi_s_TQCM,61305
766
+ vllm/model_executor/layers/quantization/moe_wna16.py,sha256=ZMLlsfy-71lT1Skzgku87m7rEZnmukFw3mW5QDVEe04,20458
767
+ vllm/model_executor/layers/quantization/mxfp4.py,sha256=6Kxslfo03haAtoLeFHNePcDvo5n2Ig4pnL-i07uaJaI,46332
768
+ vllm/model_executor/layers/quantization/petit.py,sha256=2HAoBRMEo8ycxaim16mX9myhN_4crVcnq_Z3J2Pt5K8,11560
769
+ vllm/model_executor/layers/quantization/ptpc_fp8.py,sha256=aj6FA_YG7TP-NUX_5fMi7Gq-_D-BAWJKsSaCeQKWm2s,5269
770
+ vllm/model_executor/layers/quantization/qutlass_utils.py,sha256=lLu6gVZoWiitJh0VXCPIAXpizT472Eyqi0GcSriVFx8,5641
771
+ vllm/model_executor/layers/quantization/rtn.py,sha256=5SRs2CpUnxFtPatkGRs_fjaX9w2516OekQV16FjxIHY,19975
772
+ vllm/model_executor/layers/quantization/schema.py,sha256=bOHc_0KCkTYR4BhpgGG6Sc1g0legFhDyt8S9HjjFItw,3807
773
+ vllm/model_executor/layers/quantization/torchao.py,sha256=y1F-T5v7SFyT7ktl9HH-q5rW92oa7DZY8Q2MK8CON_A,13454
774
+ vllm/model_executor/layers/quantization/compressed_tensors/__init__.py,sha256=PRLyXFLYk26eH3Y5R_HtJSmz_eK5Fw7C-1liuvMlz3I,108
775
+ vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=wL3xGG_08DiK4cieKbrCsGmJ-I90BTfkAVTvuuQ9bIc,38039
776
+ vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=8T2HdhbgDyGERJfueJCMq3fHh_pKNc8dJ25u_fIWVwk,90579
777
+ vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py,sha256=TkQU56VWuQL9mzvskUDn65wqCGo2jDDfHl3O-WSniK8,7113
778
+ vllm/model_executor/layers/quantization/compressed_tensors/utils.py,sha256=MGBWAxDxZxB37rkc2nvxCg-PPhz--akasm86cdODMcc,7563
779
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=7lubj-C9wshJ-qRHPmXEFUG8GyjqjmFnIuRc_cUAV0U,1487
780
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py,sha256=T9Q0a6UphFHPh1zD0SU2VFFuipS7Il0gAmIsPT6wyXQ,14327
781
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=UfHG3dCxyrZjzdqdgDkmlcsUkbKWqwmEzQrwWGAfq_c,1552
782
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py,sha256=p4tFtmPGqUj8UCMxn7r4VoO0UBXlSs8HC9PPR6bqUyg,5610
783
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_mxfp4.py,sha256=AOwLL8RBuHmPdxGJJ7KqN7Y0KbF20BbOdga61-8ItYU,3295
784
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py,sha256=jC7gNbR8kyKRCdyyayXx7FeoIfXy3osh7vMSmCTofjY,4263
785
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py,sha256=S1mVj-nFKK22Fl5k1hi_TXweUWcDGZ1ba0DaHxDBdWw,8044
786
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_fp8.py,sha256=GBoTrqpFqLwFFgezRV3KOKwC4S7y0sIxf_r0Q5xtID0,6090
787
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_int.py,sha256=RTtbNo3-YEN8AsLeoXSinr8PxJ1eKV2HGas7rVBRG1c,5153
788
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=iuFaXLeGOoPVyzGXX7ZgXCIs9BmcKXtkKOyg3Zn0NmY,4995
789
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=icISOknuk-sDTp9LhlLWdnrvl3RVQeZXslR_A0NfBrg,7387
790
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py,sha256=4C5gkE5jf1UGSxcFV6_3eYlmasxkXHG2VZ4bg-SKeW0,4534
791
+ vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py,sha256=wG6qzLXw7gljyzf9ytDaR1PvvhNf25L-I1GJIKkxnKE,7991
792
+ vllm/model_executor/layers/quantization/compressed_tensors/transform/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
793
+ vllm/model_executor/layers/quantization/compressed_tensors/transform/linear.py,sha256=5-7G8oPqHqKUB-rPxL6zJl4zxDBqp_42FeRJpwbczGM,9548
794
+ vllm/model_executor/layers/quantization/compressed_tensors/transform/module.py,sha256=J1QrXE8c4orA-UC3lhz8c9Qj85JT1-JfsI3Y9Qfn7aA,6277
795
+ vllm/model_executor/layers/quantization/compressed_tensors/transform/utils.py,sha256=zOt-O0AsZ978entPoKuAqg2gzEgMVK5FmW14GVBLfso,349
796
+ vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
797
+ vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/linear_qutlass_nvfp4.py,sha256=LeSahYO4dwi5fkLE-q-6-lZ4Uw7j8w4pzEae0uUpFUY,1877
798
+ vllm/model_executor/layers/quantization/kernels/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
799
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py,sha256=dvSBv9nYGrOiSEN3udSv2ElQYpf7vQorIjA61b32D2g,2825
800
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py,sha256=W3E4FMYzO9PeWCDy7YaW803nj2dmPxYaoxxcBwr4bB8,4078
801
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py,sha256=qzAUeUHkdQaV5AgjKZjbARrkHo8j9O1lGzkWUAg6jB4,4167
802
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py,sha256=Ur0Qfg5Eh1CUnIW9g8NvHAbvST-kFNyFfFyACJvwknA,12137
803
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/conch.py,sha256=hpCmB90lYFC2P-HTX-fznDIs_MbpYxhDEAw57Ky7mdU,3266
804
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/cpu.py,sha256=OdM7Q6LUYwfT4nyMtmZkQyiOeYiEnkT_o8NlYMytNFk,4345
805
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/cutlass.py,sha256=XPadfeGKzWZ9lWSudvFKq9rmE-UNAt9pfVz9bh2ijRk,4594
806
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/dynamic_4bit.py,sha256=HDtGt3LLwLkNFOsoYmhjnis5h7e-dGHPdCCeAY56-FE,3938
807
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py,sha256=9vy2P7jHm_bDNCDpiNkCH8wEg20_pwN4HLAhpHg-Org,6443
808
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py,sha256=gdBdme4JUaZ_YcrKTzJ1JfdoeX_oG9e0SSQa204AvTI,5726
809
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py,sha256=K9HDpxkAEuopvXCsExA8Gd7o3bwumkte9TzVTRkNUnc,7456
810
+ vllm/model_executor/layers/quantization/kernels/mixed_precision/xpu.py,sha256=j8NZdt1RV8PdGdn3hCA-gHkk5Ikuah_uWe6S_XrPnj8,3718
811
+ vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py,sha256=bkLygcEhOXlDUsvx1JcxhhMJgiBetlco8xjxof5AkWg,2107
812
+ vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py,sha256=wEC97FiuK5cuZhv6cJmnM9OtLTyLHPPgJeAlU3UpjaQ,2878
813
+ vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py,sha256=L0heV7B4tKqz6l5tq_-pRYT1UxYi97On2jtNvWBjkds,4956
814
+ vllm/model_executor/layers/quantization/kernels/scaled_mm/cpu.py,sha256=azbeuMu3S9lZ5Mv_RnRMPz6VQoqdFH23BNpsOyVwKgQ,8054
815
+ vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py,sha256=UAsjCcKIpFymLNmG74Gu00290Zhi9YzKslVpAdNUgVI,5812
816
+ vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py,sha256=-L_smXaBBFCs42FveVw5HO9OCw8NEpxQkYBVRpJwzaw,3116
817
+ vllm/model_executor/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
818
+ vllm/model_executor/layers/quantization/quark/quark.py,sha256=4CANVKK0o7R7SbA5EkUtfQSxsmeb9eg28DT3oqqAOD0,21482
819
+ vllm/model_executor/layers/quantization/quark/quark_moe.py,sha256=ucRjeTWGqwxsQoRytoEW6lG1dG5FSvsONWMyGj6Xw_U,31197
820
+ vllm/model_executor/layers/quantization/quark/utils.py,sha256=lOvhDC7p5Oe21iNAz2gAt2g_msZE9L7UhmPx7T_NIJY,3510
821
+ vllm/model_executor/layers/quantization/quark/schemes/__init__.py,sha256=A699VuIbNQcvuANSmPjZSu9SmSHuqKfSQhvn9Y7GlpE,343
822
+ vllm/model_executor/layers/quantization/quark/schemes/quark_ocp_mx.py,sha256=23bL0DQ4g_1B_t7RYtuoEuOMewkWcZQR2kDaXCwnnfg,12559
823
+ vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py,sha256=VMPNUJAQ6PqGlGmVD0wUx3a2NstTp2aC5Dx6w5ZTHn0,1516
824
+ vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py,sha256=AcxbIOddblmpdnjCd_xtexp9Ea8qnAz0K4C0LpR5LYQ,6757
825
+ vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py,sha256=147BnUsGz5tKSVecKUn9BxfA7aWc_UXGSaiIaqhGKXY,5036
826
+ vllm/model_executor/layers/quantization/utils/__init__.py,sha256=ifoIA36ObRUZOBfRBb2Y9xEGV5lLuc0xe_6HYLxV8Y0,232
827
+ vllm/model_executor/layers/quantization/utils/allspark_utils.py,sha256=-VRplxaZTs52TJRNpTtpjm0pp9f51_S1t1muD76v2bk,2285
828
+ vllm/model_executor/layers/quantization/utils/bitblas_utils.py,sha256=TiKCRtacJQAEroE63vfmeeaGFLEsVQnEtG5lOv16dlk,7640
829
+ vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py,sha256=KSYevn_9VISS5bH_9fVzW4ZYA2ar54wKtbEwyhfcHYU,18002
830
+ vllm/model_executor/layers/quantization/utils/flashinfer_utils.py,sha256=ivcLZG8Buyu1oqQCH6UKBBCDofzvLnwMjpKzikwFnds,13311
831
+ vllm/model_executor/layers/quantization/utils/fp8_utils.py,sha256=MFWDPdWCK7p3Up70-cibGgQzkvN7HPP8GOKFIo3o3r0,53408
832
+ vllm/model_executor/layers/quantization/utils/gptq_utils.py,sha256=-0GnKH51q6vGtt42RhlbGRkvDI4Yhta4QBG1FlWWV5w,5886
833
+ vllm/model_executor/layers/quantization/utils/int8_utils.py,sha256=JI0KrskdcFxZ073TZ-1iLMOgPWN6Gc-BZIA415T8q4s,14424
834
+ vllm/model_executor/layers/quantization/utils/layer_utils.py,sha256=CvEUZEj2ZFt7oxcDaRklOJo0IFc-llCiA2bVjybRKFc,1574
835
+ vllm/model_executor/layers/quantization/utils/machete_utils.py,sha256=Wv5uFC2UuuoBC_X1YGFOORBf23Zl_Yp5Ck_hFQIbRUA,1699
836
+ vllm/model_executor/layers/quantization/utils/marlin_utils.py,sha256=1mUItmG8P_TVllICw46UvApdFGbtjbgOAohtQKoi3dU,23540
837
+ vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py,sha256=mnBjXNV9b91Wpj9Jk07lu0b77R05y5sZYf0E0K3TgV8,19247
838
+ vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py,sha256=hTWQI-uXUawE3JQBLkBTwY3IfSQyydlk13xkFZbKpiY,13951
839
+ vllm/model_executor/layers/quantization/utils/marlin_utils_test.py,sha256=D8c0-obb1g9qQVAMptBTTF_2SzHzXR5sIV9ant1_-1M,7011
840
+ vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py,sha256=DXy1fCTnTEhQtMg7C-AKwL5oTDvwdDwM7iZjSZ1NbMU,17248
841
+ vllm/model_executor/layers/quantization/utils/mxfp4_utils.py,sha256=FT2k3ytJXPxijAc3MFEfQ2iQ7a64nEuoFBW9VKsj0bA,6369
842
+ vllm/model_executor/layers/quantization/utils/mxfp6_utils.py,sha256=3ccQ0AmjiDMVtIyZ-G5WZ778QDKbpbRqjv8vfNE9u5I,4533
843
+ vllm/model_executor/layers/quantization/utils/mxfp8_utils.py,sha256=KyD72E8jsbF-bHSHdYFkY6Aseqsa9aiTmlQfIjcnHnw,754
844
+ vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py,sha256=rFpYWNmA1DD4I536b0U0FgjB4zBVDSpN6cpeldjssvw,4633
845
+ vllm/model_executor/layers/quantization/utils/nvfp4_moe_support.py,sha256=j7GSrXDgbAoThCeAE4CAnKZknFO1oObZXp4Q6KCfm2o,2093
846
+ vllm/model_executor/layers/quantization/utils/ocp_mx_utils.py,sha256=WGqf-4DcMRs65l6wZsZNixc9KzRJSRl3fRpk_XIA4v0,1770
847
+ vllm/model_executor/layers/quantization/utils/petit_utils.py,sha256=8oiFeO9uCAaHeV0QrKPs-GbmJok66L9jylexITD7Xpk,3967
848
+ vllm/model_executor/layers/quantization/utils/quant_utils.py,sha256=nkitHNjj4K-qeMqhcN1TQMQv0cfj3xnDjLU7BVmnk50,24859
849
+ vllm/model_executor/layers/quantization/utils/w8a8_utils.py,sha256=PHoKD3dyp5tTthIDpNcvVzdEGeFmj-XywbPAU57x45c,17279
850
+ "vllm/model_executor/layers/quantization/utils/configs/N=10240,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=yi7jAKzpH-lsDg941APV4FXoYgssj7qBFhvbWl0iWXs,3270
851
+ "vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Szg1W2xH7h5U-UOH8vHbDV_xs1xO3AM_wITHbJtITgU,3264
852
+ "vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Ta8XgWb_aVhJwqJ59i1zzY45NhCGazJ75whDUmOfyVw,3259
853
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=t8TaODfMF2Nq0qg6KOc8NSTs7m90Jcu6Ih3BXUvFb04,3799
854
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=CNI-I9ncqHJ7ukpzgyxdJtz0bd29vsgC38tvMM6TV1U,3803
855
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=CNI-I9ncqHJ7ukpzgyxdJtz0bd29vsgC38tvMM6TV1U,3803
856
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=-j7Xyk4xFaiAD90FeH4AqRSnS82f4owKRGMHbObrrHQ,3250
857
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=sW_T-BdLbjJoFqlr-B5f9emF8E0IdKfy_1wUSIEi55g,3253
858
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=tkLjwLC_aVXhzuvo-2QHkojXZauPJsf3jNHFn1S7uRA,3244
859
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=akDNAjUZ3EXBznF9w6qUcpXxaLWq7oXnX5jy-R9cleI,3246
860
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=JAycl7EaUZtmCoXMjq4JwKXCeXxZ6S4Ts_DricRUw_o,549
861
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=q5KZyi9T-l07P3r1u9i6-Dpw89Upjw1gpTp3f1CluEo,3799
862
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RTnTPFQNg5JULbPLWJDTRNRZHI7FsrTxqSDkZfSbmzw,3806
863
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RTnTPFQNg5JULbPLWJDTRNRZHI7FsrTxqSDkZfSbmzw,3806
864
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=DLCfW5tQ9k74AGZ2yER1etP-HgUGglPp_woJiaPuxgQ,3249
865
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=8v9mdWPs1eXczo3iwFrNnRo2LF9wPU4Scm-r9bL7Fz8,3251
866
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Qoj9rLLRDbKM4IKBCXvN8RcxzSmNPd0TQUiM7CXDqHI,3241
867
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=7OFCbBqqEA7vQ1oiygfW-7Tqqx8OJATaLujtcQIgyTU,3247
868
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4D3Ku4y7BCVEJzueKvQC_KvOR026w3ONWsxfsA_YrEc,3249
869
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=iJZ_tAzoYGUmg9ltil4e8vzKlKi980yTmswEMWqV1Jw,546
870
+ "vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fDomA7uBQKX8kbO_4MFcoBwHhIR_7sOkngQPv6cQq4Y,548
871
+ "vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ucrZBIN_ivmmfMAvkT40xQpH87LdQK38lZbeLWMyV4M,3806
872
+ "vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zDnVqBqgT-nLkz_Cou-KTPsNIVh-YbTBno9L2MgdRTM,3803
873
+ "vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zDnVqBqgT-nLkz_Cou-KTPsNIVh-YbTBno9L2MgdRTM,3803
874
+ "vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=zd5cMYrxQ6PD0jKpd3YF6ThT9RGdqgEQnCW6F4W-r4E,3249
875
+ "vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=CjO6dh_qt1iTu5kYRs98tTLL-W6FOzLO4AESMUFHz5s,3254
876
+ "vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=7v4tp0RaT4vxF4urSBrkK5FR_5ikeFQ1htF3DwDl1lk,3249
877
+ "vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=M5F5wzSmFokEm0X8__ogLvdE1QVC6EW8atqq-kp3rVA,3253
878
+ "vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0J2MFgaLkv-mfVE5x363lgVKYU6miLG_xRO3tJUga_M,3249
879
+ "vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=983yfFeeo-BClL_H1g-owXwbA6t0l-kREiy7kLURUMw,550
880
+ "vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RzrnY_xKo39wZ4nO8zUorLp1ivTFabB8ZQOFRx5JcMc,3251
881
+ "vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=f7upf6kaHS5_3EqQYDxtSsbgb4D1iTvjCiC4auzbx3Q,3254
882
+ "vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=C2eM8RudmP-qXEf_Apg-qcB5n2Ugxf8-7uG8hQDSt1g,3801
883
+ "vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=llI6PWlSDgQf-ouTDXkFYOoSz9u3bzklwBtZYY_fWVM,3807
884
+ "vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=llI6PWlSDgQf-ouTDXkFYOoSz9u3bzklwBtZYY_fWVM,3807
885
+ "vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=q9HUcoL0cdZCOWZ8MKbcpR8NSy5iNEBq6NPTaHLgRB0,3242
886
+ "vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=uJu6Gv4e80vxVrDyBo8_y47tOV03RmWVsMIWQ-bbW6Q,3251
887
+ "vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4ubbhwSFX_XbefRLEkLoWxJkcetFWPzsszPu0X3_Wrw,3242
888
+ "vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=euiKvhb3DXkvPPQJLqNE_xN2evsTOoZnVIiquyN2Cm4,3246
889
+ "vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FhyniGTx5QeCuVrBSVTQys6q05Pr5lPEcPykpAX7Iyo,3247
890
+ "vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=pLQvMaVvlet_JenEz25mxxplAaHNisl6SFTSZ7lYP2w,548
891
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=irQUBLd3KHNd8JNX8eFe2fBB3ZZ3zMl3aAF22uxJ65Q,3266
892
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=gklD55iBvg488-PecvtcEypwCDZ2lCi8c5o9bqgEEeI,3266
893
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=uAa-ZQmASwlqZbr1l1CM6FyJI9irNdLBzc1U5Hdyw1E,3802
894
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RnN7lfu15CE-4ywMjAbEz8wWV743AP-1Fq5U_j8EQeI,3812
895
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RnN7lfu15CE-4ywMjAbEz8wWV743AP-1Fq5U_j8EQeI,3812
896
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=cE3BscS_zEtF_m_jr51IPfpaZZgIEojmhTHsrb9jABM,3260
897
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=SScyo-oYCBxJR9C7ZIKu_pJJNiXdpT13kYe26rddvPQ,3261
898
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0v17v78pETXv6S2ZoibekxOVhiTmCm807DYG4DONUck,3259
899
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AOuovUsPAHqZlbr4G3_CnCNE__fgxCz6RuOhOxCwWv4,3258
900
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ulvOEAFO8c-UOa34FEZrjOkCR6ovhJlfFFDhmaKIBiU,3245
901
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=BiZowqExbvXftuE37SYcheOdtYX7Z5BEXyykJ6GbYSk,3254
902
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=W-xd0c2ziC5YbC96TXlc0xkj2cmbfcdXclW453PsLpI,3258
903
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=7ok0uooTihvRSckZMNd6jInRvht_xkC5posHO66ejqc,552
904
+ "vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=h_Z6wBKdSGBEo5BfQKaxuFlxztrnbbZR0pkcYKv92sk,551
905
+ "vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=k63VgniyN3Rl_-h1hYmT_q9QZtSFqQmXBqhEXJQkxqE,3800
906
+ "vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=icswqRYUsUdoQMrv4YIqO46GG9BzepmBJmnTre9-VjU,3800
907
+ "vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=icswqRYUsUdoQMrv4YIqO46GG9BzepmBJmnTre9-VjU,3800
908
+ "vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=sL0E4zZzb01g6GHaTCXltg20uSbthXHSJFQ0SaxZ7PU,3245
909
+ "vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=MZcJz7BjwVOHHHxvYqGrWw77WnxslYhwW80bZw-jSKQ,3249
910
+ "vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=GsLoYkaZ2p4Qu0Coj-X90s7JWyfZBOloIHPlyNKSIes,3246
911
+ "vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4--7YWnJYUK4XmQ2zZ4M1ZYdKvUkET0VkNgIBn6xaOA,3247
912
+ "vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=NjEA2QjOVXyOaVSMPch5qa1Dq3igbW7MmE986-7taW0,547
913
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=21Buh2aiGTHjpW45Rm-TwZD8MSaAy8NMUrK5l_hGT5k,3803
914
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=P8p-dZZt_D61G6k3PgUetF01xzTRmCDJAnqCIsSDW8I,3805
915
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=P8p-dZZt_D61G6k3PgUetF01xzTRmCDJAnqCIsSDW8I,3805
916
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=8zuJhFdd6aXREpiqPFhIKEFWA5lgLVGrG0-a9UXcBqk,3262
917
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=_42bDZX4VODErI6OL-NrWja36iNHC4DzgF1l5Mk67-c,3248
918
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Zn1TvhAoPOv0zQBYHOZhwdDw3oqyxm0zIa7IJkTCHpo,3247
919
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=H9wONEU0XXSxOJfkx5UkS8Ss3A2QCp9G0XNoJEqE9nQ,548
920
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=2T2TYZhXgC97slH92HQ8GvZS3KuUt1ZiC3RtudPVEPA,3802
921
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=b6_bhUuQrI9HYvvwmAvUYh4v1GZ8w0sjApOmwuj_t8Y,3806
922
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=b6_bhUuQrI9HYvvwmAvUYh4v1GZ8w0sjApOmwuj_t8Y,3806
923
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=yqjO7zML7EseBJw6Bn5MTyHeAitkPsl1dndXeL6Rn6A,3257
924
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-nQIhKAOVCQrxLV6HDlcD0V8HMWvqrv-vyiORVU7qls,3244
925
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=KKmCvNh5T_qfD8v7JijMqXxQ5L6-gRX7oc6c5re6EF0,3248
926
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=M3nwpZd2-0w263ywZt9gaw53z7MN673T5tl4tc43Ntk,3249
927
+ "vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=H9wONEU0XXSxOJfkx5UkS8Ss3A2QCp9G0XNoJEqE9nQ,548
928
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=KmEgJ7zP2Sr_7GsAfL-12_g2S2a2wVpnxgCiF5dFiLI,3802
929
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=J4SXwpsioBRdTXOaj2OjrdNrEuW1NF43cLds65UWzCY,3808
930
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=J4SXwpsioBRdTXOaj2OjrdNrEuW1NF43cLds65UWzCY,3808
931
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=UjBOmVqYynBH3dJVuMJXjKnuZ6LssohzzEBpLBG4_G4,3256
932
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=8BJsjc2UUYdotrIqwyzisjrq0wcyW4jnTo_M8J3qYwA,3263
933
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=vLoV3JMtvHOKpR5D1BeCQPMuYlWUAlrXu54gByNkwKY,3266
934
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=BmXTZvWk7kphfBmGmuSIuolAK-3qCGdmcPhD4FcKd3g,3265
935
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=N0kCPHvybNK-HvMO2EqNDLkj7m7WrHTl-3AD32LBD4k,3248
936
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=mjh-AgJN_IoWAc1uwhUiB1lE3ufAPDf-KPP6vUTrDKw,3251
937
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=h0qz-pNlC9ZGNbyeFsESFdowFPfTTK3rh8SK4NH2Css,3259
938
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=mcF12eQTtGxocrVIA3I98NHd1NLd0-8EyfXtqDgv0PM,549
939
+ "vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AThoa7FUcGdNXYB_v9iMpBh2X8C0iLfc7y-C0xy2cRY,548
940
+ "vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=MJgIvZHf01ju8IWEVO6vyMedy5OTZxDpzv6A7_8W-Tg,3813
941
+ "vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AT2yrMoTvmoizi4sxwLtiULZ57P1CBhKGg9-6Gxnuc4,3819
942
+ "vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AT2yrMoTvmoizi4sxwLtiULZ57P1CBhKGg9-6Gxnuc4,3819
943
+ "vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=T60CKtM9YhIEZs8F9Lljrdqqc4ReloR7Xl9IYsfex-E,3261
944
+ "vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kk8WqNCGmjh8-tOMHBP8sv_5fW81Xkdzdf8-2WDm0RQ,3263
945
+ "vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=cPtr1UJq_B-dTqgMrVm8ptiYXA6qOy_F8rs2f7ljuEI,3811
946
+ "vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=cobt_ZhR3dt2CySr12bGPVwn1oS98YvGLdIh9H8BDQ0,3801
947
+ "vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=cobt_ZhR3dt2CySr12bGPVwn1oS98YvGLdIh9H8BDQ0,3801
948
+ "vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=6Z7kIa14RjVq3ek_C15q5mUu1IrY2r0OP8S-_pm-MYU,3252
949
+ "vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=r63SZkUJJV87B00hAX074_uaC7wwQXdurlJsB1jUA0I,3254
950
+ "vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=hL3doX7zzxld3UcS8p9ACSadDaE6t3xXlYwM7X3GOeI,3252
951
+ "vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xBhxdCFf3waTUsLxJxA54R90zODbC_DKI3XXBVKjKRw,3252
952
+ "vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=2ks7TQUULAD-Zn5i69YHo_2hpmsmxlocdYmJccSh2No,552
953
+ "vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zm2eqlVlPWlP-5o944QL40OCzMpUHGkPJwduy8HOV8A,3259
954
+ "vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Yfg4GDiXIYLyzL-334YirvDbcChz-Ep_atCghEZSntU,3257
955
+ "vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=eiI8X2fFNknJmiT0uHbzSaEKQwwZk5bxn676gNvcyg0,3802
956
+ "vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fQQDJMlLdYsY5Cosg5HkRzvrJ4asjQmc0WGgoD4bC20,3810
957
+ "vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fQQDJMlLdYsY5Cosg5HkRzvrJ4asjQmc0WGgoD4bC20,3810
958
+ "vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=O_SV2vo_oaABfT6Mxqcmo12pnhKtfX4TnXfe02OcHJk,3254
959
+ "vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=g12Xkurat7oUS7LdS9pHLKFlur4_FaMGiGBvdq-iBCs,3242
960
+ "vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=EWLxbWncwGJyL-dV6EO-s8kk25wfYrESa0STjCnzD64,3244
961
+ "vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=tFdrY5nADmXUlShdN8w8Jzkxuj_RPLXCRceX9FhQ35E,3251
962
+ "vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=M-ewEHbgHLBLYLi1Hgz5Pp4kypnUiCRo0ut2scNnvDw,550
963
+ "vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zTzLbdff09HwMuWlWpoAIgQZ6NEjsFXSF0Y5z4Be7Ig,3802
964
+ "vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=dcPHbYEbz8T9SM5-a5sP_K_npDkhH7u0KM9aiLn9esE,3806
965
+ "vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=dcPHbYEbz8T9SM5-a5sP_K_npDkhH7u0KM9aiLn9esE,3806
966
+ "vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=TO2qRGmp37v53Zqu8Joeq_BSbtwM_mpVoozGyoNg0-o,3254
967
+ "vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=QqijmgLqIoBUxRPnuUQGsoQASRFRMsCVQKTjEjGecVo,3247
968
+ "vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0xquf00fgfrDODpaxyre0VDcjqfzqExj939rzeJ8pMo,3244
969
+ "vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ipg8iK8w2ySRe1Z08YJUWAHX43rvkrXpR6svxRhSnFE,548
970
+ "vllm/model_executor/layers/quantization/utils/configs/N=5120,K=25600,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RfKJ57-Tvq7WogfSRBPys53fLXfIr74m1YklXtzFgA8,3252
971
+ "vllm/model_executor/layers/quantization/utils/configs/N=5120,K=8192,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=isRjD-twCTzTRlXloDHwMvjUZzTOhZL8-qnL4oqN-I0,3258
972
+ "vllm/model_executor/layers/quantization/utils/configs/N=51200,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=pIFPPhTKBT7leK-TSMCmy1LWZiDc6_5r4zoP0i7bX98,3266
973
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-wuzdNXf3K0jfFQGB8nFSyoSZ4BfAvIkY10k6FdjnLY,3800
974
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-o9QqqQQ-9kRVCuDOUGBuKXHRTd0asGTzrDcHGGYJLQ,3799
975
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-o9QqqQQ-9kRVCuDOUGBuKXHRTd0asGTzrDcHGGYJLQ,3799
976
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=DbemSQdo2h5vGjSNB6Fovnn-aAGfjti04Bp-5KxLALk,3246
977
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=6glWpljtfiuspJv_Esg_LWCDDQ57d2HETsOIv0zr2Ec,3249
978
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qG6v3n3qF6LE2DdGT-mDIXecZ1a7vg7p3QqXYCMX85k,3254
979
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=l-9r2k1gcKB8UXlBXVuzkoa1JDLgJVTBQ_OaQK80z-k,3252
980
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4--7YWnJYUK4XmQ2zZ4M1ZYdKvUkET0VkNgIBn6xaOA,3247
981
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=ZfPPlx0qcuR4WjaFAE-W1QZgSPAMf3NyGcpvQIvyFMs,3245
982
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=9w-sicV97vSQxkRcEKnFKFjkzBOx-VOHlrh6b1hhQ1g,3254
983
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=QgSlDAhlB2W4bzTd2O98UL-C_IKfJm_cVmQz8FqsLF0,361
984
+ "vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=i3wy_CBO7BQQVhKReRC2F0PaRIQDdN9F5lJ7kD0xe1I,548
985
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=QpkqpJnyjuHH8Zo4U4QZgehUF2F2uQDZFb8fdhixXWI,3794
986
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=wv5GjGAA-NyJ41SYdYG3tPAgwf6JK7Zf6SaWALQ5c3Y,3806
987
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=wv5GjGAA-NyJ41SYdYG3tPAgwf6JK7Zf6SaWALQ5c3Y,3806
988
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=RRMNeM_qiHvlUTOAeqwgs7ukSoAZSlK8XN4z8hgWl0k,3258
989
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=brB0-FFr-Sv2bdrz4DQJ_NaFhETctf1g4Yzwj_Fcczc,3251
990
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bPQWtvaJrzOOIgI-R-MIxs_f4yC_FobkDydu3OkOFtg,3252
991
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RYLh-Uim9U2_djLkFwwpV0rNQHik0tZHzecuj1_hPLw,3248
992
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ZRgiuHZ2SFC6u-WV5DGwau4k1RiPLI67eENO0e-5Ylg,3253
993
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4EzbnLWHVwrjyKYPMcDxbxM2o-krjlT0YXvM8oPH5Cg,549
994
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OFgOtRkUHwyOT7Hk_BQft_WzuZOwbhMSLP65Fbr4goA,3799
995
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AOu05da2LZbCzD9SKsrgnzH-ih3CdXsRIdJc_4J1lps,3807
996
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AOu05da2LZbCzD9SKsrgnzH-ih3CdXsRIdJc_4J1lps,3807
997
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=qzmFm2pqxphir1LBrycDZp5JA4It8OdQeQ5iTrTwLNE,3253
998
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=2UyOMRMdbvHt6WlZdOKALm3Or0eMCx7vvwgLiCYyoOs,3259
999
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-hP_P8NM0K04mGzTmpGBNibQ5xxh5gPz5WtoMXhoz1E,3253
1000
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=vEU4_YOMnLdYFf1BkBEdFbGRMG8KLhsO_t0gv7vaO4Y,3244
1001
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FB5Le4obvPoCgFSnC_3-Uh59n-Mt4Rol8saXVcK3RPw,3252
1002
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=k1rzpgm9m19AHf_HPQcNCuSBtAwFgMePUYB1jZeFyYY,549
1003
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=9IbzTwLRgTCfFLSvjEWKiajCjG81R-wTljIV2zUYUA8,3809
1004
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=B4uEwuftvaj9gHGdoDBnVhxbNRmzUtzu4LH0u-O7voA,3804
1005
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=B4uEwuftvaj9gHGdoDBnVhxbNRmzUtzu4LH0u-O7voA,3804
1006
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=ZTPWtJA3JBL2jhy7C60RdsntKCN8oQ-DDIL17ok7OB4,3257
1007
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=mokCWoXdKi8p4mLYqgljjwDRJWK5I2oF6_MJuObi5sU,3254
1008
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kLviGvVngpgOuelfKtvv9Is7MWQ89rGxlomMRP6t0Ic,3250
1009
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bIVRtaaHThozH54VIte0Nk0sOGV67K4s2YZUE6QWx2s,3252
1010
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_YXzQ6N3QpF3Ou1Fy-51YyL-J3i5gOBVCgSM42vOT9I,549
1011
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=csaz7AaVDTvCuzaptN-e8K1PNuIwZm9OwnPSJydHI90,3803
1012
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=scfO3_ncCtyrqcYSnIoAZTMfvBzjB4o_0_bdiiVSNh4,3803
1013
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=scfO3_ncCtyrqcYSnIoAZTMfvBzjB4o_0_bdiiVSNh4,3803
1014
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=CE1wRLyFONo4_icKO8fcTTX-5giKNJ9_1F-2mr-lGQU,3257
1015
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=JdUaLiMmf8oEbwuhPHMIncvWzXS2SxOEgfM80ZjM7l0,3259
1016
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=vlys0Zi_CaaU41OHGbWSBtbVglFi98bgqEySBMc9Sdg,3258
1017
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-sqiMkGGMzhrs1WdhEfwiNZd2r-NmhEsfvJxczLZJ-g,3258
1018
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=GY9VBPi21K6vJlF1NOEzCyqMS7LX3xq5dRxrK0jvIHk,3244
1019
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=8LWF55ZPjrOY_sEdRGqf1eLcTNySgUiiWNWsN4EGxLY,3247
1020
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xEN9qWPikXf4njuYyKQJVW0SM5cDReje-euoWbr64WE,3258
1021
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_Cc0EqUzl6d93OxWJRWYbYpEaTIp0glJhdfV-GSAi5M,552
1022
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ZSHvdnC2vOXI2HPW1iNI9HdihoLcNYlRLMF85pqjWZE,551
1023
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=SkyMLsoxGoHdO4kgTerihone7eEi0nmHlrvZUI1I_V4,3804
1024
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=6Jo2hw2gQpyiNoCRZpGItu4MBkYytzdW-VggWUC4fPE,3804
1025
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=6Jo2hw2gQpyiNoCRZpGItu4MBkYytzdW-VggWUC4fPE,3804
1026
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=xbDfUYLphVtZWJojZWODlxGMCoiIgxn4LsnD9ge3r9A,3257
1027
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=hqh8TQw3t5hPM9u7rmHPuaMjwgxmQ-Zt35fSTgOS0HQ,3261
1028
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Ggy4hejkcWjiw5Bi-wGzSP5JLVuvOjip_rbjXFBJZbs,3257
1029
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RzkrUzR_nzxnD4L2jF0_8aDX-nidn6AjhVXlJK50VyY,3259
1030
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qKG9hmaxN_7tCB_06L1dh0csxs3TGeya9B-X6W-tNhg,3245
1031
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=jb7vGi1RJefImkT3BZU_9iOkiCulcd5oDjxpVSt7big,3246
1032
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=at0_Rcc0-lSzI9MFj-TjnjyDt0HckCZYAZ19q-7p5zI,3257
1033
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_Cc0EqUzl6d93OxWJRWYbYpEaTIp0glJhdfV-GSAi5M,552
1034
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=TWpzs48j0QwApAsBWt3iIlu6cqR46Meslyp96MOANcc,551
1035
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=i5b52A1Oe8kCdPrPLBGud7OMHm8779JD0rBocYO_lo4,3797
1036
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=U20Q4JwG63kU-6cc241VHGdpettCWbBXRJ9EZ-fbkqA,3803
1037
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=U20Q4JwG63kU-6cc241VHGdpettCWbBXRJ9EZ-fbkqA,3803
1038
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4uWiQMh3cZY_EtLA0a3PU8Z1VCunF2PpolTPYeP9Rjo,3256
1039
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OgXOVvRKqsgzlJwjHNxNCsJ_o3POBFigwCqafbh_aKc,3258
1040
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=toHzCprq0KetQI0-9IrLYCIm1bQ0nSeP1gXArU0GogI,3245
1041
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_0V6CEfYgBsaUnF5DwNWWseo8N1Ph_R0la_XN8HzcuM,3259
1042
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=pGZZj_gZms1T9Zgjs4tbIm90LhbEy1UUkkgrto9jPts,551
1043
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fqnjZCn0gbY7fO9JwZOHMYJJHe8gceWhWCZOFPRUlYM,3802
1044
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OTZt3ell0OZ7Cg5L17K2NPU4UwayAkTihV5HjUmUiAw,3810
1045
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OTZt3ell0OZ7Cg5L17K2NPU4UwayAkTihV5HjUmUiAw,3810
1046
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=LdtOyXsA9r18GiFkmDOkiRinsDSZBZ8NYapL59EZ4iM,3264
1047
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=07GarBHmiiYkyqn-qxEtrAcgCETuUbqm6HqlbH9yJi8,3252
1048
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=xMNxtLL_8tyg4TWSt_llz_IJ2qlxc2NEwhUzhV1VsG8,3252
1049
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kEuvCsW3YNByF-DALYqPZpW3TL8ZbtQ5gUNq7-8YvZ4,3252
1050
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4uNqB71a6ctZ-c4tF3r66vOsHFrqcR28g_UWy0N8iBo,550
1051
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=QkrfZ69jxW_mweigtHL5R0Sv_WcSBp7wjFX75G9kbHw,3805
1052
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xMGmoN2ZTjKQBZS-k75mFTPpAEbPR3kyMwqZVtgbEiM,3802
1053
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xMGmoN2ZTjKQBZS-k75mFTPpAEbPR3kyMwqZVtgbEiM,3802
1054
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=PD4AJYCkHfy2ivv9baMouFXzBTy0eKMumbAfxfm91HI,3256
1055
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=iu8M35YR-RDpKWbjXSRzk02sW9nr_dtbhalfLSNtxNs,3251
1056
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FFBjSWlpKXMxfAUUYUqXbOK_Hd7qBeBsfbcaa9uB4qY,3249
1057
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=41m0bvskFUzVtlr_yppBr4PZ0cVkqHvy9Hrc5pUCUyY,552
1058
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=2VxMGfWtxTzXcF0bP3d5s7rc1cKb5TNBAn-WiCKAngw,3804
1059
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=VtQGO3fEiyhbKG4sl07cuVc6id2EtKeV05ozLmN_ENQ,3807
1060
+ "vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=VtQGO3fEiyhbKG4sl07cuVc6id2EtKeV05ozLmN_ENQ,3807
1061
+ "vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=W3cYFteFIZLu5c1K41cOh4_-WZzFU6-jGnZocDzmKaA,3796
1062
+ "vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HIoWSUgAOcNaK2kj2YwDjDa23PzQVTT2C2ePW985Ovw,3805
1063
+ "vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HIoWSUgAOcNaK2kj2YwDjDa23PzQVTT2C2ePW985Ovw,3805
1064
+ vllm/model_executor/layers/quantization/utils/configs/README.md,sha256=kfjjurECwd-xH4EDjuueS0Xezi86c_pYu2yELgiw8Ew,102
1065
+ vllm/model_executor/layers/rotary_embedding/__init__.py,sha256=A1EG4EpZ-wn30zwkTLBRtIzEj8fuOwZufnE1j4tdxf8,9699
1066
+ vllm/model_executor/layers/rotary_embedding/base.py,sha256=CWN3LXITzFPb2bYgpsM5TtZG5TsBk6VAYuzlvN4qlAI,9510
1067
+ vllm/model_executor/layers/rotary_embedding/common.py,sha256=EAzytBloxNAij8Lk-Ex_UAZ0CiFQQbfafqmgIzI2_nw,8441
1068
+ vllm/model_executor/layers/rotary_embedding/deepseek_scaling_rope.py,sha256=2MV788ANZDQlICbUCoDIGHbWDoon7gn0S2PFfXfDp6s,6234
1069
+ vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py,sha256=vCIgcU7FgX8eymrhLHyZ2MXl9i5-kevyyE-J3ex9Mtc,8461
1070
+ vllm/model_executor/layers/rotary_embedding/dynamic_ntk_alpha_rope.py,sha256=gkD_OmIqduxIUvBgqEqFu22dVDm4zzOmtJ5SgRQJOAc,1289
1071
+ vllm/model_executor/layers/rotary_embedding/dynamic_ntk_scaling_rope.py,sha256=6lZQAj1v-nvRbZkLIR9_4a9nzAczr09YByOF7IXDr_U,2681
1072
+ vllm/model_executor/layers/rotary_embedding/ernie45_vl_rope.py,sha256=xibKvReUksJnWiESNi0qVg9L8-qZul1Ti1gghVT34Oc,3059
1073
+ vllm/model_executor/layers/rotary_embedding/linear_scaling_rope.py,sha256=5a1OVeRvwUeU35x7xjUbhpc_UNtWd2MRWlZ1QftnxkI,4643
1074
+ vllm/model_executor/layers/rotary_embedding/llama3_rope.py,sha256=EMeHz5tB4hKDXr6ce4GFfFpt8x03HKYlmedwXUgDcHw,1785
1075
+ vllm/model_executor/layers/rotary_embedding/llama4_vision_rope.py,sha256=ls-dUts73Wyp99QPkk4_ED1fewJVH05BighSzRpCmm4,3313
1076
+ vllm/model_executor/layers/rotary_embedding/mrope.py,sha256=zgqRJKYWKnQXIPKfwJyNo7hHclopjevBEdpZrtcpqB4,14256
1077
+ vllm/model_executor/layers/rotary_embedding/ntk_scaling_rope.py,sha256=KzRfhq8fROqVm5Eu6ETmQZyvc8LZjIKzde0ZGcr8Pkc,1462
1078
+ vllm/model_executor/layers/rotary_embedding/phi3_long_rope_scaled_rope.py,sha256=AT89hmBGCmGUtX1hoy4agKZfYdHd98eJnE1fGlzkQVA,5699
1079
+ vllm/model_executor/layers/rotary_embedding/xdrope.py,sha256=MDHhx7D3Lir4BWx_bhmOYIruQfBJCzsD-OV7g2sUfGA,5108
1080
+ vllm/model_executor/layers/rotary_embedding/yarn_scaling_rope.py,sha256=rZENzx8gm_Ysbp_OzOn0qQB9v-D1faYWz5ZILHJBbrs,2863
1081
+ vllm/model_executor/model_loader/__init__.py,sha256=LHfIEpPjCh0nFjOPe4GS8kswwCr9bsvss8bumDhMHys,4901
1082
+ vllm/model_executor/model_loader/base_loader.py,sha256=o_x9JAQVFEEDuEVO1i-ZaHdfNlPsPQHn0rjlydv7evE,2457
1083
+ vllm/model_executor/model_loader/bitsandbytes_loader.py,sha256=w2FWxxM3-HpWzKKFvaWBL7K09U1Cu6lpUY1m7-TQW84,34771
1084
+ vllm/model_executor/model_loader/default_loader.py,sha256=q9CgNhkBAJThlJYpyHA_0rHKuMdrXlvF0CD0AGl6uR4,11705
1085
+ vllm/model_executor/model_loader/dummy_loader.py,sha256=QStJ9SXJTYqzTWI6ytieoh0KNsQWlfL_sFz7bcHqtEY,1115
1086
+ vllm/model_executor/model_loader/gguf_loader.py,sha256=s3_2sWCmZ1Svbi8tX_iAM3dVQ4GZcIfp1Z6GiaXaki8,15751
1087
+ vllm/model_executor/model_loader/online_quantization.py,sha256=I92q7uvu1vyWcYUnFkQwRzghsb52R0IC8Qi-GShx9lQ,11543
1088
+ vllm/model_executor/model_loader/runai_streamer_loader.py,sha256=MDs3DpQ1tlP-dD27te-_TGtHAN9loB1euJ311vJJvx0,4383
1089
+ vllm/model_executor/model_loader/sharded_state_loader.py,sha256=KxhCy60owpwAzg8OxoWX-NcAcJsbo0gRwQUy4LolrF8,8248
1090
+ vllm/model_executor/model_loader/tensorizer.py,sha256=4e5UDNpm2aSFbbVE0T2W4X5LNdahkW3NbLGyRpXiz0Q,29915
1091
+ vllm/model_executor/model_loader/tensorizer_loader.py,sha256=brQv1ywScnNSpYMAt9l0zbLz1hUbEbStsEGhVcwpuJw,5826
1092
+ vllm/model_executor/model_loader/utils.py,sha256=oHHozqHTnUqECluu57SlYtoAbu8mjLyU7XIUrhhyaSk,11518
1093
+ vllm/model_executor/model_loader/weight_utils.py,sha256=V-fenvZ2RpGsX8rDS3Ozij5Vx0HFwpsj-aWwUD1339c,44673
1094
+ vllm/model_executor/models/__init__.py,sha256=JC8KFZavvBlB4woyRgOBd_vcuoiA31nmBOR5dGcJSjo,997
1095
+ vllm/model_executor/models/adapters.py,sha256=3jbs9cNHSiKvz8fzVuu7O7ggBbtgObncBcz5a7gzcZY,21329
1096
+ vllm/model_executor/models/afmoe.py,sha256=pHKY1xMRDOxk-rGiR8Fu6Hx4jBrn5aIvm-bfM33MGsY,26162
1097
+ vllm/model_executor/models/aimv2.py,sha256=M23uR7otjxLQxh0zIhlEC9sYs-yNSUR3Zq1ITwnukOY,8337
1098
+ vllm/model_executor/models/apertus.py,sha256=j6U_TSIMgttLx6zU9GeNlQ6wL3C6f7CV4f3e1ZjGBT8,20751
1099
+ vllm/model_executor/models/arcee.py,sha256=-UFp6gIs8sqbk26I2gVKv0gq78Qb5h3CoKDQac6XXc4,16084
1100
+ vllm/model_executor/models/arctic.py,sha256=6R12kBzrcYzCNcoZrzGgv4rInpsg_CaThzE2aHQ2J9o,23767
1101
+ vllm/model_executor/models/aria.py,sha256=g4ioTjdLczTrV6nH6coSTovcjf2aRkwbC9i_zFR_ijY,23784
1102
+ vllm/model_executor/models/audioflamingo3.py,sha256=7HjeHtulK8XuVdORujEJNKNA4SWXVHg24euxjkwTpr4,22481
1103
+ vllm/model_executor/models/aya_vision.py,sha256=Esr0Rhs-2WgIsQ9VfinNOpDmvyRcKrIN-DftZfbDEek,16534
1104
+ vllm/model_executor/models/bagel.py,sha256=ZVmKrh9FMJsFrL4KkzVUoHVJq1jLfDW8nODKkL_5Wl0,20917
1105
+ vllm/model_executor/models/baichuan.py,sha256=6IXVn92LhEmfMlJRxw1NojW_OWlVX9UDYRyAeyUHDfU,17811
1106
+ vllm/model_executor/models/bailing_moe.py,sha256=dpLSZq-13RQEiXJ8aOnYPhvKDlRaCIhcScs-XWepkNw,23070
1107
+ vllm/model_executor/models/bamba.py,sha256=6OvWNj4F5o0sthrrqJwJsdtqBVp_JyRujOjUFcauk5U,17641
1108
+ vllm/model_executor/models/bee.py,sha256=BXEICXixtwrG50Roqwk1cujdmQ4pljJGfxQgUt7ZqtA,5450
1109
+ vllm/model_executor/models/bert.py,sha256=TTUYy_DVa_ib9tyDXhuSoK3VcDtqtq-CL5kL7RNzsuc,30912
1110
+ vllm/model_executor/models/bert_with_rope.py,sha256=yH88fpTUdGxxlQnZPF1x2KYtW6BOh8DFM72b6LFxYhk,25299
1111
+ vllm/model_executor/models/blip.py,sha256=NWuepkpmapgNlg8kYYC47IGK2A77xboyAzD1Hso5Ofo,11947
1112
+ vllm/model_executor/models/blip2.py,sha256=l89N6GeXbQcmRFRgqC8UgBoSynN24bs--P5BjfRa4XI,24839
1113
+ vllm/model_executor/models/bloom.py,sha256=9Y1UAwmAaiZt4fI4kfOfF68liZxOy4RiFLwl0eyiXxI,13967
1114
+ vllm/model_executor/models/chameleon.py,sha256=6CpG6u53h9P-TGaK6gBKx3nGrJJTP2DA3gom9Yz13i8,40437
1115
+ vllm/model_executor/models/chatglm.py,sha256=Q-EvWJ_rHJjWW6-ammlfgYDNt5JX5KAmWZMbVq7RO6o,17596
1116
+ vllm/model_executor/models/clip.py,sha256=_6ICidmIiRHCmhXiCbS19Nbo_l-YQcGCa09F-8UDo2I,34865
1117
+ vllm/model_executor/models/cohere2_vision.py,sha256=wgGh15eJbJYQNt73nKVxoWUWit4K49RkpaYh-lFyj-8,17035
1118
+ vllm/model_executor/models/commandr.py,sha256=z0T7oWaXgHkJmkvHebOBkq7fIqiod_NuBxuB9ex4GLY,17396
1119
+ vllm/model_executor/models/config.py,sha256=I7pon7Qnx9uV2HjLvFAWxt8Pwj3cj6iHzKIj1feSf2M,23785
1120
+ vllm/model_executor/models/dbrx.py,sha256=Gxoy3rWLsZ_1mgWu_AX2T4Mg94kl8v2T2ar2k1L45wc,17429
1121
+ vllm/model_executor/models/deepencoder.py,sha256=SSK8JK0tKFSV3gtyGJct8NEl4JGnanT9-hwxbTjPW6s,23960
1122
+ vllm/model_executor/models/deepseek_eagle.py,sha256=godN3QkVdWqAcpDrX7lpHe_8tVFmvvThd_BAzcexk8k,9347
1123
+ vllm/model_executor/models/deepseek_mtp.py,sha256=Ecgyblu8x10ltNjV4OnnlcCRrOxBaPCPHT75dUZvvAE,18044
1124
+ vllm/model_executor/models/deepseek_ocr.py,sha256=6MfXQfX99BBE-XCFONlmAM7xTJtCTv64bqRmXxUqAp8,20696
1125
+ vllm/model_executor/models/deepseek_v2.py,sha256=RW46ejkr7V4F-b61cwjcInOOqERbIpglY0c2d9GMuNA,65919
1126
+ vllm/model_executor/models/deepseek_vl2.py,sha256=e5VbFjrnizO3rIut3tqhoXWQ-5DzgfnZOcwI2k2-MNs,22891
1127
+ vllm/model_executor/models/dots1.py,sha256=tbB8Yvnnu9-KIUUxsK4P8TVNA7xjHRpp8yRLOHrQD2k,20835
1128
+ vllm/model_executor/models/dots_ocr.py,sha256=jbpEUL9jketJgSd-RKeZ9FYqQEOJ-UtSHgqRn6TQNFA,28340
1129
+ vllm/model_executor/models/ernie45.py,sha256=gxkle1tmFbYsDkQx8AjoYZ-2_e93ALUtHMMdVnPA_fY,2244
1130
+ vllm/model_executor/models/ernie45_moe.py,sha256=9UIuVyXWhzHj0IfdTSosfiECg1ieP9svXVxvlk9mAr0,28110
1131
+ vllm/model_executor/models/ernie45_vl.py,sha256=gbTahDVdlxLWAZY2H2jSLRzcfKEbEiedlb7EJ1eSqaI,60825
1132
+ vllm/model_executor/models/ernie45_vl_moe.py,sha256=hyttk411FahAyAZHVpvEOGvyBnxCCPdCSFl9ZpOXPgw,30414
1133
+ vllm/model_executor/models/ernie_mtp.py,sha256=ZNDD4FaLkHaRmVXKJUaLP2IsxVJxqVXPfEUknD3oDuo,10521
1134
+ vllm/model_executor/models/exaone.py,sha256=OxzjHhrvrjZjVSFkAzCy_aRYuo_AUTtnrGzronVJL2I,18809
1135
+ vllm/model_executor/models/exaone4.py,sha256=0-0s93CXJ7WI5veday04LF3rLVh--H0WAjHMod5lpXc,18730
1136
+ vllm/model_executor/models/exaone_moe.py,sha256=uTV_jEYY_KCxKzFW3yMnt7qi-3ctELgPQ2eVQ_1z0nE,21888
1137
+ vllm/model_executor/models/exaone_moe_mtp.py,sha256=84xCAROtS2_BNWcySKRFm-v7bUS1sjUsIjhoE6clH_k,9294
1138
+ vllm/model_executor/models/fairseq2_llama.py,sha256=dIadCgG1u8yASjN4qmOTvkli4xxu-Ygl3t0iL2Czsik,6375
1139
+ vllm/model_executor/models/falcon.py,sha256=A21xTnBOvRCvxCmVfUPVrSCqvOmMA-opohJtxrbkGjM,20467
1140
+ vllm/model_executor/models/falcon_h1.py,sha256=nBH-JEKxWxzODx5cVRnfo_TkwhdkETYzcSXLrD-iX_s,24127
1141
+ vllm/model_executor/models/flex_olmo.py,sha256=eWFSijc0m35t7xMZKdsb0cXZv1OdI3vbAw8nAujahMI,5624
1142
+ vllm/model_executor/models/fuyu.py,sha256=yA2FTp7WZdyFSVO8fp5U9vXWSVl4_AA84DOGQGFSFJ0,12918
1143
+ vllm/model_executor/models/gemma.py,sha256=VBliwRauNqjT9Qbu14VZNWIbwzTiu19UuMbj8n89Z90,15534
1144
+ vllm/model_executor/models/gemma2.py,sha256=PfOtV3CxWfFGuMkW8B9CKq83h2Qrbpedx8s4cR4isPw,16362
1145
+ vllm/model_executor/models/gemma3.py,sha256=GS7o6txWeBj1gddD_HJAh3pIo9oh25o-LcJz41T-bpQ,19565
1146
+ vllm/model_executor/models/gemma3_mm.py,sha256=p7D9bFLX35FfPxHexFQR2QjWkISI_F6Ai3s8LYY_lTE,21907
1147
+ vllm/model_executor/models/gemma3n.py,sha256=bnG2MOpyZ-jDFXzlI3thk8d8l4grcYhrbzjV111W5WA,44169
1148
+ vllm/model_executor/models/gemma3n_audio_utils.py,sha256=8QRbJkqTWWcTtQZ8q8w-jBC6WlslT1ytYX49Zqn-oxQ,2414
1149
+ vllm/model_executor/models/gemma3n_mm.py,sha256=8LPcciajHTfDRukxUtOxhSOabCePsc9RtUSl2Z5RpBs,29850
1150
+ vllm/model_executor/models/glm.py,sha256=Xnak9Z2N9i2PFVY9m9-ocRcocTEQCPow5mGFena0URI,1108
1151
+ vllm/model_executor/models/glm4.py,sha256=ADNwgV7F9LiTBARzRsz7S8e2dTEfgXKgd_7K8nGTBsc,10572
1152
+ vllm/model_executor/models/glm4_1v.py,sha256=OJwNopDEdFhhGPrOSvL7CYMBOM0KMbQHctOtsMum4WI,66349
1153
+ vllm/model_executor/models/glm4_moe.py,sha256=KhoeClYAnMmLPA_F7BBu56PE8hlGnfLzoh5A65QB0vg,27624
1154
+ vllm/model_executor/models/glm4_moe_mtp.py,sha256=HI5_5LYBwT4tL5JWjL7Vq7cJP7UWO-KwBozS3byMT28,14518
1155
+ vllm/model_executor/models/glm4v.py,sha256=HSOu09rEdgGLtjLtoIw8I1mBp0Vjz2lOBj6MadMs2tk,25783
1156
+ vllm/model_executor/models/glmasr.py,sha256=Q8mtSryu-nVU9PPtSX0bg8iFtZ8YHoVE-8SS99V9oqA,42009
1157
+ vllm/model_executor/models/glmasr_utils.py,sha256=16SAP8xFLA5sIvcAvZ0ZKwVK8dzPWTe0kD4QShc9tE0,6583
1158
+ vllm/model_executor/models/gpt2.py,sha256=y00HSL3xY5ZvNXosVovt9bLT9fOkA63f6MqizyphF1k,13918
1159
+ vllm/model_executor/models/gpt_bigcode.py,sha256=nN3bU32akyp24tLWpc5Puzfka96VlfUdcLObR6YC7EA,12135
1160
+ vllm/model_executor/models/gpt_j.py,sha256=5PUa1VYw2hhOcxzVq9Rt_RALaA6PSJrTTpupGdQMn0g,12758
1161
+ vllm/model_executor/models/gpt_neox.py,sha256=QQQmIeC6n8ZEdGcE1XBcTKbiOaU5_kVbgkCRrW21zC0,12703
1162
+ vllm/model_executor/models/gpt_oss.py,sha256=CVbU7zWl29daVYUBPfc_xFJetE8HIcPSHnwb2mbe9Eg,28865
1163
+ vllm/model_executor/models/granite.py,sha256=FtLf7dUAbREvCYDySYBp3ky2haPjE3vVOgFDV_oMPGk,17369
1164
+ vllm/model_executor/models/granite_speech.py,sha256=5BlSk07HMgdmAWtthJVVwwmf3yaRXboAE7RvQbgb7OQ,34882
1165
+ vllm/model_executor/models/granitemoe.py,sha256=vPVqhFM6XX61gPYvtMMlkLl-U-qP8ASzmXw5lzbd03c,21118
1166
+ vllm/model_executor/models/granitemoehybrid.py,sha256=1YHD-ZQi_BdPQn58Q-JE6zpkdhYT5Hcqt8_F18yy_Yw,25749
1167
+ vllm/model_executor/models/granitemoeshared.py,sha256=mOXadUhv4xcOoQhff4qB_cwgT5yIolVss8Do0Ds1wY0,12029
1168
+ vllm/model_executor/models/gritlm.py,sha256=TI4KV2jQeocNtwY-VF1gGq_66EvX1kPo7NNG7a738Vk,8267
1169
+ vllm/model_executor/models/grok1.py,sha256=kLndRburQ7WFJx7SBrS4LfH23BTYtCm7IKfmrwSkBuE,29231
1170
+ vllm/model_executor/models/h2ovl.py,sha256=esbz1E_zaZK6p0YBB5QqcbZaU3eq-3kXZEqLSYsydJs,17830
1171
+ vllm/model_executor/models/hunyuan_v1.py,sha256=LnI_wdnfYN8jall8U1HFc0G7BII59u4Oc1K62g862EM,39480
1172
+ vllm/model_executor/models/hunyuan_vision.py,sha256=NuNHPYuIxMmxjyuqrHhrk7TUySJAMWGhOz7M-H73I4k,35259
1173
+ vllm/model_executor/models/hyperclovax_vision.py,sha256=Zq5NuRMMsWJQJk6Nfmw4ZADVwjTIfJPX3T1fY7ULekM,40640
1174
+ vllm/model_executor/models/idefics2_vision_model.py,sha256=4E5PLI2bo-PvaiaQei7ekNoqXj7e-BuUAiTOhf09Yo4,15576
1175
+ vllm/model_executor/models/idefics3.py,sha256=dPPccYZgcwslmwL55uhs48tu7rrbaKd1Iaxlx2kYxvU,25103
1176
+ vllm/model_executor/models/interfaces.py,sha256=bWKn-hzO9gZQKSmUOHNCHCZqBZ8yQMqc7YDYXMocK0E,36093
1177
+ vllm/model_executor/models/interfaces_base.py,sha256=8h0YkfqNv3JyBIjXN4oYtme7lMaOoZ0ROZw9CC49yfQ,6946
1178
+ vllm/model_executor/models/intern_vit.py,sha256=dU1IdbvDFQ5WX-hkjSXpDrXs45bGY-AkX45ZYZtCNqk,15136
1179
+ vllm/model_executor/models/internlm2.py,sha256=pfdmoSNNhs2wOCtNu4esFDY4FxRfJsEqWNNNTxNpbV8,16087
1180
+ vllm/model_executor/models/internlm2_ve.py,sha256=hDhlTCpPsJ50_mnB7XqLnMT6waw_E99gSM7n2tr93mw,5350
1181
+ vllm/model_executor/models/interns1.py,sha256=4a_yUfyFAJ3oTfOT5_UKOFCfJ4dcZsORV3Op1Edjb-M,30601
1182
+ vllm/model_executor/models/interns1_vit.py,sha256=VnNwLe5YVHR5y8uC_hgUlm9WiVuMei2da8vnx7C3M-I,14946
1183
+ vllm/model_executor/models/internvl.py,sha256=OrL04LyNEIYcmDfDKQAfIL_Upq0XKMcGBUw9ReyWnbk,49211
1184
+ vllm/model_executor/models/iquest_loopcoder.py,sha256=ykB1sYqrf4dHHGAzDH-8PmGP5f8HZtCIz0sNiMobOv4,22482
1185
+ vllm/model_executor/models/isaac.py,sha256=9r6TKQ8UhKxAaOaAIE93PniGqvB6h7JpQVCGZ1E-cA0,54467
1186
+ vllm/model_executor/models/jais.py,sha256=iDGCyrKYbJMfa1TYl0oyJz5S3ZRJqmR7YXJ92wEJnUc,14198
1187
+ vllm/model_executor/models/jais2.py,sha256=T5rJ5glhgf062eoaOM_-ciCCSCTr7oX3rTMgLYTszzw,18610
1188
+ vllm/model_executor/models/jamba.py,sha256=fSKBz7GTASw16HjN4rK5TwRanBi85rGOWtxmuGKNVhA,21245
1189
+ vllm/model_executor/models/jina_vl.py,sha256=AA5t_OB6VPBubHiLSLLkEcSzS7ZY5SNY_K3yyQ1gQCA,5077
1190
+ vllm/model_executor/models/kanana_v.py,sha256=mCrV-cewEThNXtLbHoYiD0cgMeXZi-heioiiVtbmqdI,27270
1191
+ vllm/model_executor/models/keye.py,sha256=BY0gl-xgi05KPYPNa1EHYqzRP5byf6iyAiXlqDXwBfE,59152
1192
+ vllm/model_executor/models/keye_vl1_5.py,sha256=YCYjlfOWX4grJj2cYQyR2WAFYVdI7h_aSPpqxXvhJsc,24916
1193
+ vllm/model_executor/models/kimi_linear.py,sha256=GfBGQ4j9k7TTtlsUGDJ6JQRgvPLeFvARhdO8g_maW0g,23832
1194
+ vllm/model_executor/models/kimi_vl.py,sha256=r20rXzxy_uQHBfoybSxC54yrbeL0NBsIxLYHxlDOTQQ,22183
1195
+ vllm/model_executor/models/lfm2.py,sha256=TnFfBaVDug9LHQoloTT-Ft802geLlQUHe0ROvM2Yils,18222
1196
+ vllm/model_executor/models/lfm2_moe.py,sha256=3wsc3ITEDEzBqrK4AK9qR_aVU9Foe4l76RM1OVw7pmc,26788
1197
+ vllm/model_executor/models/lfm2_vl.py,sha256=WZvfoN01d1LoiOQ91hScCyxAuB2p00PFcNIIozXhPX8,26312
1198
+ vllm/model_executor/models/lightonocr.py,sha256=UlcbFNNHJhJmsy8OcNFp9ktjr2iLYkOSy35fqXcuL-0,7135
1199
+ vllm/model_executor/models/llama.py,sha256=JBiVq9FY6o59uDgKj8XwOCS9RyQqbsk1FTs9u4fVMTo,26740
1200
+ vllm/model_executor/models/llama4.py,sha256=evYUh9pb4tAl83TEW01dkiaZXkgNnUBGHfYgkmVKMNU,35190
1201
+ vllm/model_executor/models/llama4_eagle.py,sha256=C2sO3dMfHiRgTPEorq_zPu-A6-se68-1_RwtjhSu8WU,8946
1202
+ vllm/model_executor/models/llama_eagle.py,sha256=y8zOZL1d5-E-OAqNpX98DydzaXa8_2P42Yu3QvrSZLw,7937
1203
+ vllm/model_executor/models/llama_eagle3.py,sha256=2bGYKrlU4mHFDu8KXIbeKhCsLVeCbXOgAA1qcYAvvM8,13899
1204
+ vllm/model_executor/models/llava.py,sha256=u2F06WWBIi7FlHIA-iPjReJuXJBmkjCT6QD7Aah-X3M,30197
1205
+ vllm/model_executor/models/llava_next.py,sha256=keLzvA9LUGedQAoRn12pwZXNNSAEY5qdS3b3bv3uwKA,22069
1206
+ vllm/model_executor/models/llava_next_video.py,sha256=ERcJcJH_RM0N2jz0vQgyo8NJoJYoUxLgiveOPTJnGxM,16173
1207
+ vllm/model_executor/models/llava_onevision.py,sha256=IkZaFf5jmVKVHuiu3L3c1r2PP-OzifLAij9edAY-Lr4,32845
1208
+ vllm/model_executor/models/longcat_flash.py,sha256=jLyrMTIMkeBR1KNzx-PCxaWyxe6oyQgGxvm_xmqXzow,28661
1209
+ vllm/model_executor/models/longcat_flash_mtp.py,sha256=8A0ssGYqWlGTE-hX_EQSQPLjT96ctREEaGdRDT5-jwA,15504
1210
+ vllm/model_executor/models/mamba.py,sha256=su7lsV3dqkgTgsc4TTBca8QVuhg2hl4e5OXvqFMNW7w,9787
1211
+ vllm/model_executor/models/mamba2.py,sha256=_3ljnMFLPp_-8VM1h34_0uUFD96bDQZaQVjaM5oUZSE,10000
1212
+ vllm/model_executor/models/medusa.py,sha256=ljZQYNwpS3jkemq1r2ghTc2Z1LW8ncpdfh6qzY20TKg,6738
1213
+ vllm/model_executor/models/midashenglm.py,sha256=hkbjPk_pf_gm-RYTnzVhSFDnFloFx-2rHQ6cexWvk4I,27783
1214
+ vllm/model_executor/models/mimo.py,sha256=4b4Ezgz1uHqVOyhjxm8_FOd8IthV0WXoGSqTs_zq2Qs,7332
1215
+ vllm/model_executor/models/mimo_mtp.py,sha256=LZGDXqszX94QsLS32RRGuC8d-cFlM2O02mjwgC9oRc4,11061
1216
+ vllm/model_executor/models/mimo_v2_flash.py,sha256=KuDMZ49S0xPuCM6V0havCxbch0z3YXSdjOrkymttp_g,25712
1217
+ vllm/model_executor/models/minicpm.py,sha256=voVHRKQhRTZBlFXjmqur7yA78LJ7LW7AzsCQGT9x3_U,23874
1218
+ vllm/model_executor/models/minicpm3.py,sha256=KbPlWRmzD16Eltl_u6MjWU_2CiX-VKRwGr5miPxIGDI,8569
1219
+ vllm/model_executor/models/minicpm_eagle.py,sha256=-Y-N1X76_Crvq1OMd_r-2FqPfZ-d-5-OYbOhgZYHI1o,14435
1220
+ vllm/model_executor/models/minicpmo.py,sha256=mD4uCUlkpmdeW7kPJoU-BITGtex3uuvvH2RZN22Iy9g,26859
1221
+ vllm/model_executor/models/minicpmv.py,sha256=lamr97NxB_jx305DaNnFtX8soIqTLqDaT28u9hsLNdo,59094
1222
+ vllm/model_executor/models/minimax_m2.py,sha256=PyXQ6cZt6ntT6d2coBUJ0gc5xZX-6mDcKEiVOpQkibM,20752
1223
+ vllm/model_executor/models/minimax_text_01.py,sha256=pVridBrOnU5H3XiDY1DiYzCFkDzQ2OQDjFXbCXXbPGQ,38045
1224
+ vllm/model_executor/models/minimax_vl_01.py,sha256=0nICq8i1ZeCbZBh7h0-Z4VhNM5_kj96qnmwmXsNEfbM,14521
1225
+ vllm/model_executor/models/mistral3.py,sha256=JoJ67JaLsDYAxrTFUTqeOEceRbQ4z9QSUlV5FkH2sjw,22225
1226
+ vllm/model_executor/models/mistral_large_3.py,sha256=iS7LwF8g1RaDqEC6XPNY65zDVoN8atVksWnAvF7WXDM,3671
1227
+ vllm/model_executor/models/mistral_large_3_eagle.py,sha256=6ybrBPtbFXEKHEWTpgFPgFdnaqgMRtc3PYf3-IpDyZA,5043
1228
+ vllm/model_executor/models/mixtral.py,sha256=8WLP4Qp9ANJaQ3BYj3QmRL4D3uwygKOEv6Fkq-bvpzM,22475
1229
+ vllm/model_executor/models/mllama4.py,sha256=v_1ayz-xcwWyxQWw2LCHhoHMmCmwBuODxcWJymqUhlA,42711
1230
+ vllm/model_executor/models/mlp_speculator.py,sha256=HDvlP-QB88Z6facl3fDKmIck7dtSWjpifteV4i1E23c,8457
1231
+ vllm/model_executor/models/modernbert.py,sha256=D3tkLz5E4dl9eSLt7jaNNZymAEI32DLFbmR5Kj9slck,16425
1232
+ vllm/model_executor/models/module_mapping.py,sha256=YdEB0K1EaW-BbLfkr-IvlO-E9pv7G5qrYUn_vQwnLis,1688
1233
+ vllm/model_executor/models/molmo.py,sha256=Jx-75ZkI31B5vRZIHHsQJtKezYeky8moQ1D1Ubl9lgw,53159
1234
+ vllm/model_executor/models/moonvit.py,sha256=EfTkZvb0LgMf-uPZNqUuXBzkpidl4T2hfjLNVICZZog,22000
1235
+ vllm/model_executor/models/mpt.py,sha256=HLqYAFNUcxNdSRShcP-mgY41dLkb6xDMazq_pvp8JU8,12119
1236
+ vllm/model_executor/models/nano_nemotron_vl.py,sha256=wZPZdRFWcl959hnFTFi1xz9tXkJcVgZZfTkzFbHKO20,64378
1237
+ vllm/model_executor/models/nemotron.py,sha256=pN_fGmgPh-7x_Ia3gwRPw10OQUT-5ek7UpzhSbyIVXM,17929
1238
+ vllm/model_executor/models/nemotron_h.py,sha256=75ril-Ng85m_yUkUTuS0kIaxOIz4ElCt4F8jhK-YGcA,32697
1239
+ vllm/model_executor/models/nemotron_nas.py,sha256=G2SVa7IXGSO2OCiErASmSSEN9zWEJRvffG0kRRU2FXc,16945
1240
+ vllm/model_executor/models/nemotron_parse.py,sha256=GwWuBnYquOC-qZ3IFBES_sXJK0wRzrXZ9QcOAoNyY6o,31899
1241
+ vllm/model_executor/models/nemotron_vl.py,sha256=guhq__kswnXkAAvbAuycrF9kg50Z4h_RF4QGusc1RM0,22472
1242
+ vllm/model_executor/models/nvlm_d.py,sha256=MqXkN1AQ-SJv9UCAbpdTvOe4-R1yVcG3wEOv94z45nY,7636
1243
+ vllm/model_executor/models/olmo.py,sha256=cwUjSi4fxMrFoJGOM_Mp5v7M7vlFfIPKc0Iqdtdlqt8,14327
1244
+ vllm/model_executor/models/olmo2.py,sha256=VlaVNOjkLXZlTYh59h9Sq6_IqT0IQb7Seu0o1A48hR4,16588
1245
+ vllm/model_executor/models/olmoe.py,sha256=nvcD24hSbFjUVSxtD4Yysm9MRVf5mxuEqbdhc9OQEOo,18461
1246
+ vllm/model_executor/models/opencua.py,sha256=bXM2xS5DcLfNAXjShDonlmWmgEdTmdUVuL8SukV0_84,8492
1247
+ vllm/model_executor/models/openpangu.py,sha256=72yBsyffCDneyS_Udjo4UVS2By7oNfk8ndGwDc3JVr8,52314
1248
+ vllm/model_executor/models/openpangu_mtp.py,sha256=6Qg5q5Op5dq0cbHr76Qdt-f3LTRGJCO3eHdTnhkhbk4,10340
1249
+ vllm/model_executor/models/opt.py,sha256=xd_6gvFtiwdJe9am899LwXsalxBVx2TbYNpxiVB-lJ4,15681
1250
+ vllm/model_executor/models/orion.py,sha256=Pd8_6bXczO7GGQqR41lUd-RzRX_jXz46N7a2quwnQIo,13212
1251
+ vllm/model_executor/models/ouro.py,sha256=Czgcz13VFNzdBqyFUABNyNdzmfQeM2YBQlDmX0lNP0U,18776
1252
+ vllm/model_executor/models/ovis.py,sha256=X9I4Au3uR8pSmNiFQUWD-eC6rROdwSX8qWQMxbTvTkM,20308
1253
+ vllm/model_executor/models/ovis2_5.py,sha256=I46Q4h3O4ZAh6znw-AHsjW5RRSN8Lo3TMFor-1duTFw,24618
1254
+ vllm/model_executor/models/paddleocr_vl.py,sha256=0NoMH2YjsGRedgfduyqgUYT1WZFtgt2WZ_vuOQ4E6pg,44487
1255
+ vllm/model_executor/models/paligemma.py,sha256=KoUTL7i38NeWUck9WeqwtW5jD9bSgA8EPiV8w8-TJFI,13998
1256
+ vllm/model_executor/models/persimmon.py,sha256=B4Pc35wex4wv1A_LNq6Wdh7pN8Z-UW9mRcHxBsr6LWA,13590
1257
+ vllm/model_executor/models/phi.py,sha256=rvYb6cRWBcVsm8ypnIdh0X2Aj9GonFK54fOnQFDegqo,12957
1258
+ vllm/model_executor/models/phi3.py,sha256=N380ApMP7_3VL-rlWeVD27SUjC-kLXbldzYNWgG8ApM,456
1259
+ vllm/model_executor/models/phi3v.py,sha256=UUcY-jKHZXVaYvJYOYXUNNdez6qH5XpjcAxgab7ZGWU,25988
1260
+ vllm/model_executor/models/phi4mm.py,sha256=zPRJwtFJJ4VuiXfIhxhrF9CsmPNydFTQQBdVfqMyAIA,45228
1261
+ vllm/model_executor/models/phi4mm_audio.py,sha256=EML6r9O_PY-LQZQwCbC45nvf0QY2j0pevPYKPuZNsE0,50483
1262
+ vllm/model_executor/models/phi4mm_utils.py,sha256=un2oSpNyKdnDN9wLMnBn2CzxWO1xNeRwAPyV4pI6Gj0,67179
1263
+ vllm/model_executor/models/phimoe.py,sha256=OfBj2QeGNI4GZdckwCaWITux998HLp_dCfaU3pg93TI,23500
1264
+ vllm/model_executor/models/pixtral.py,sha256=eyq8z99s3oVkk5Iv7PUERBV2eW-8T2BiAttrSt1gpfo,50480
1265
+ vllm/model_executor/models/plamo2.py,sha256=NOtJrF9bvfplDT5ajpJnke4IbpH_jiAjDZpsKc--N6s,37945
1266
+ vllm/model_executor/models/plamo3.py,sha256=py0MFyebL2eEb6Uk7WKPUII4Jb2mYlD9eZazp3tUSKw,15867
1267
+ vllm/model_executor/models/qwen.py,sha256=gnypsb37-wJgO2ee2lD_j1dB-mZW_3GydVWO_z6Kx9Y,13244
1268
+ vllm/model_executor/models/qwen2.py,sha256=ZMlkEG6T63X5ciIVKaT1bbtYXIg3mvyj6xQxdx0CT_Q,22272
1269
+ vllm/model_executor/models/qwen2_5_omni_thinker.py,sha256=XbumT7bv45yvGyei3Ndo0w6Av1PDlA0VUJvNME4JabQ,46126
1270
+ vllm/model_executor/models/qwen2_5_vl.py,sha256=ykunYWEgzMj0no71-BOL-gA_2iSZni-TBwbutiJ39Vs,56992
1271
+ vllm/model_executor/models/qwen2_audio.py,sha256=NgPoCsHLsgil2GVAmoErxOZrbuX01lCfbxB3Y14MVh8,17118
1272
+ vllm/model_executor/models/qwen2_moe.py,sha256=9zK0vaY12RpgPvL0H1W_wfyaAls3qs4VnX2mY5yrTpc,23234
1273
+ vllm/model_executor/models/qwen2_rm.py,sha256=y_-RIWAs8bht29hge2COLBGqq-FRzk9iTZQ00skuTbw,4113
1274
+ vllm/model_executor/models/qwen2_vl.py,sha256=t0hcbD7TddYmn5Jb6gJXjkJPCnauWUR9a9O_dOwmICo,55146
1275
+ vllm/model_executor/models/qwen3.py,sha256=XDbTsSapmP9ZcqpBFHgoqg_fiboGusswTNOou9eNnEo,12349
1276
+ vllm/model_executor/models/qwen3_moe.py,sha256=_ZHMzamUVP1eoSROgABKuln6eLotoL_uT4aBIr23gLw,29691
1277
+ vllm/model_executor/models/qwen3_next.py,sha256=au2Ga_o59GWTLLlbFrM_ejo6esNOLC6qJAoXQ78EeBo,51576
1278
+ vllm/model_executor/models/qwen3_next_mtp.py,sha256=MQhhH4jCS8EjIrzAbK4yRzv9vYDwV67Ia8i0BTZxwK4,10548
1279
+ vllm/model_executor/models/qwen3_omni_moe_thinker.py,sha256=6N3AssBPLdUq1BFQKihMWxhKWU9QMRfwbhkRdDT9LJI,71671
1280
+ vllm/model_executor/models/qwen3_vl.py,sha256=wsh-BQQLcZ1hTDVkcD6fyjgg3GH74pqtzl0QOd1gLg4,81882
1281
+ vllm/model_executor/models/qwen3_vl_moe.py,sha256=mr8BU7UIIimDaHou59sk8795zzIUUBvk5UAJjBBNIZw,19587
1282
+ vllm/model_executor/models/qwen_vl.py,sha256=yyGy-Yft2hApm7Xk4KUViT1YQTyjgvdZEA0rf-Ir7uQ,25806
1283
+ vllm/model_executor/models/radio.py,sha256=HL30rKlvZFmKXT16xicFSEMHWqewFp0pmZxzgHNcTZg,19088
1284
+ vllm/model_executor/models/registry.py,sha256=qWrcf2tz9FwX1UhFlP9pDAhMJDxp9fi9mXZ_6br0m9g,48405
1285
+ vllm/model_executor/models/roberta.py,sha256=JwEKqoBCpOtu1l5zMF0fRMLDbDFLRY0UqwerdAv02AA,9007
1286
+ vllm/model_executor/models/rvl.py,sha256=-XiyV1RZrjlWPfJhnL0K8ulP02dHOLbt0DiLuWdvhLk,3567
1287
+ vllm/model_executor/models/seed_oss.py,sha256=M0dtVEpY6MUbIzfnftoSrd5d-gxspqAtnwxjqd_pm7w,17871
1288
+ vllm/model_executor/models/siglip.py,sha256=vRJ3wEbgGUBdCcl7pDF8OZfgGxqYpW31TOFvAjFCEIA,43426
1289
+ vllm/model_executor/models/siglip2.py,sha256=pTHJazu6ZPKVmO1Q01zwICsmMJoQ-lqw1cf8KFPzLSo,17854
1290
+ vllm/model_executor/models/siglip2navit.py,sha256=hNkuwCSY_ysa8_tpo4coBT7zwDoEp2VRBicN33GLTXw,24328
1291
+ vllm/model_executor/models/skyworkr1v.py,sha256=9TqQqpXD0Vqtgw31ImaM41b9gTD1sNiNGAjYXMcYb0Q,31789
1292
+ vllm/model_executor/models/smolvlm.py,sha256=ZsY0x3CaHHUuTBggSWCwGv-HfUAiwks8jZRNoMd7hXs,1450
1293
+ vllm/model_executor/models/solar.py,sha256=TG8UDuu8zhfowfowGgVx2MVJR0MUYixbINrTCghMyRI,17763
1294
+ vllm/model_executor/models/stablelm.py,sha256=KxUTy25A8l58yHqFul35weGh8IuRGvCyQxttjtSM8rA,13565
1295
+ vllm/model_executor/models/starcoder2.py,sha256=KIkBzXUYSPYWBFG2-IkdjxM9P0q5lKUiytzI25AX2Y8,13371
1296
+ vllm/model_executor/models/step3_text.py,sha256=fGboyFYndqg13I06YXOdiYNQGBaTC66wc4ehcZqcxd0,19864
1297
+ vllm/model_executor/models/step3_vl.py,sha256=_1rTxJ3BJrW6O7kOtruBpp5P0apjauHY0ilybefjhrA,40363
1298
+ vllm/model_executor/models/swin.py,sha256=gKgBbW4e1gkSkUw_2OlqvLyijWGPkPu6YBYvfkKZ-ro,16428
1299
+ vllm/model_executor/models/tarsier.py,sha256=dv-rWT5x4LdqiCCZmwumZp7aDDXuVHp1w_EY3S30BEU,23115
1300
+ vllm/model_executor/models/telechat2.py,sha256=wOEquSezPeLg2qqUNZ7ncsIzpfxHxRCrFoproADyARE,6245
1301
+ vllm/model_executor/models/teleflm.py,sha256=vlTObvAPJAJhkhy-8Snyx_7R1jGqAbYU8OYbWAPgvh4,3030
1302
+ vllm/model_executor/models/terratorch.py,sha256=nqr9QPZg-2zBpc66UaartaXzeKMSeTScVuyX-lwq-zE,11164
1303
+ vllm/model_executor/models/ultravox.py,sha256=5GOFEqBb2c7JyFOL9FonpkY9zimoTdjIxqaVOO7II3g,29246
1304
+ vllm/model_executor/models/utils.py,sha256=Jtw-OwjPC8aXYtpF9ICfMurukCzLqLs6tv9-GafKGXg,27418
1305
+ vllm/model_executor/models/vision.py,sha256=2RJuf-Z0IxTqvmRGqLeU99N2aak6Y6I018Q07m7CgQo,19134
1306
+ vllm/model_executor/models/voxtral.py,sha256=OPjTPbNYp5cdp5L4FBcz9Wod2VMFdDWcA9_-KYqkroY,31675
1307
+ vllm/model_executor/models/voxtral_streaming.py,sha256=c4kVFOLyxNoVUuA6s9u-JrT-7QzpMXztGe2YvbrYRJ4,11022
1308
+ vllm/model_executor/models/whisper.py,sha256=bNd28GIPQtAOsh4mFC0vq8c6ETMYZhjzf-0-abOXZaM,35318
1309
+ vllm/model_executor/models/whisper_utils.py,sha256=wuHdDwVdEeYdhLdUfC7h8Hc99dffG-U75DapghFN3H4,9852
1310
+ vllm/model_executor/models/zamba2.py,sha256=BzNuNIBdRplY7qbJ-sjJo9ZHj6M8o-qXhO_BxJxfBiw,35475
1311
+ vllm/model_executor/models/transformers/__init__.py,sha256=KR0hAoCBU4oqFfOpZ1kT9u80zQ_s-Z6HWpTfkvra-iM,4264
1312
+ vllm/model_executor/models/transformers/base.py,sha256=GMmrNyNnP4oG2O-ni-EoAgp6y-etmlMNXIYo-jITtlc,21099
1313
+ vllm/model_executor/models/transformers/causal.py,sha256=WkomK1hlsPamiJU7wi-Y-kXtPKo9j8e5mEb7rUn2_hM,2609
1314
+ vllm/model_executor/models/transformers/legacy.py,sha256=NY96kEaStY66o4Sa3tOFCqLhhwgiIf3eO2dnViXowIQ,3229
1315
+ vllm/model_executor/models/transformers/moe.py,sha256=Kk-3RxQpxGN2eZe_XckpAQ1kifK0hkkGZXSTxZ_Ynlk,14326
1316
+ vllm/model_executor/models/transformers/multimodal.py,sha256=j1ngZl-EITEnfpktupUrmcdTAfsrRqhbsm-98EpS2qU,17621
1317
+ vllm/model_executor/models/transformers/pooling.py,sha256=SS_1ciigE75k4WB5IthheWqYLZPeIGZWiT3tvKCmaqE,4077
1318
+ vllm/model_executor/models/transformers/utils.py,sha256=HVyyfp_2Y9XPwg15SacdGFlpbWSK8abHE1ZQRFb4-I8,8825
1319
+ vllm/model_executor/warmup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1320
+ vllm/model_executor/warmup/deep_gemm_warmup.py,sha256=8SO0_6r8eMigP07HC10Pqomq5cd0-8b9JNnrVZrkUIg,12922
1321
+ vllm/model_executor/warmup/kernel_warmup.py,sha256=1UcUbxZD4tZspHk8WZIydYUHM90YO-Igq63kIf3pVjI,3524
1322
+ vllm/multimodal/__init__.py,sha256=tnAxNnu1kVSEBizAbOTSXQ2zpRHvc_ZnyxORjLjmGBc,985
1323
+ vllm/multimodal/audio.py,sha256=TOhNGRvrbavf1fNAdsXf9Wh8aRifVh2lrTaO4_67YYs,9499
1324
+ vllm/multimodal/base.py,sha256=TVBLApanN02y6_zEJZAWNdAwl0mowy2-5KgxFgZfS5I,1928
1325
+ vllm/multimodal/cache.py,sha256=MdtBH2XCGo9OOGcik_3_uZt2-du2iDY8Xq-9CSgnBR4,25625
1326
+ vllm/multimodal/evs.py,sha256=fRGDSsF8VNjS6c665IH4SgKZd__RKIll-sEeDZP3Kyg,10886
1327
+ vllm/multimodal/hasher.py,sha256=gZO37nPF92JDwoa-NSM5f6gC6RYh2kE_lkGVtTtegxw,4188
1328
+ vllm/multimodal/image.py,sha256=rBw4HZUThfZ_xPl3GMk19ugLYTb9h4c4dp3FN_YLlRk,5569
1329
+ vllm/multimodal/inputs.py,sha256=zxbb1vspAUMZ7xrCxY0aLjga2aP7utsgfzIzy9CZJH8,31356
1330
+ vllm/multimodal/parse.py,sha256=RcB2HhDkbkbbxdjPsxpkTM72rj1vT3-rJbQnNVQuiUE,22167
1331
+ vllm/multimodal/processing.py,sha256=ILnRSNQgox2HXZLhI4AT6fCWPlj7glaIrqufuGsIAjI,81444
1332
+ vllm/multimodal/profiling.py,sha256=avZemFCtjlGtbGAdt2fVng_k0EBDDJ4_RrQ5wal2iAE,11460
1333
+ vllm/multimodal/registry.py,sha256=W-8IDWmIlfK-3PS4xbQUgYcQMLoT6Ts0MewU8vUxIVQ,12987
1334
+ vllm/multimodal/utils.py,sha256=fKfrJS36nYC2mhsCixVrOQgijY2Na7xrnz4T7Ju-Dao,17049
1335
+ vllm/multimodal/video.py,sha256=l3FL58tJw9xN7PPK_ruEuqDFAZlZbaKgIw16Ar8sugs,17948
1336
+ vllm/platforms/__init__.py,sha256=9MJt87rVxIFAeoDiKAQWoMsJOhD8noEyUZ1SUakJWvo,9896
1337
+ vllm/platforms/cpu.py,sha256=A6IadFGGgKvVh9_5fbTOVt5fkFzY9C594bdFmjkURBc,16027
1338
+ vllm/platforms/cuda.py,sha256=L2mO43t43uflSx_nNxmPqhA3bFvoi62r0DGkQXGQo8I,22518
1339
+ vllm/platforms/interface.py,sha256=3vLgYBSTW4yX14k2KBoKQnHnNJum-LxKxHYhsHxEn3o,22909
1340
+ vllm/platforms/rocm.py,sha256=t_zsmlJj2Pmr7dujuID6L-noRKntWRHUiULjWkyc9AA,22558
1341
+ vllm/platforms/tpu.py,sha256=jP2fyAJCwm7b0phOFcRlT7BxXHubFOiQMFLxA3oE31Q,497
1342
+ vllm/platforms/xpu.py,sha256=rH-PfaZ6M10PP7aSZgrp-U5dtuiVs8ONFleyWtLRLpA,9470
1343
+ vllm/plugins/__init__.py,sha256=Nsw0J9H4aw1c1Re9Lq57fapbZooXT5itsF6kG3GJPwo,2833
1344
+ vllm/plugins/io_processors/__init__.py,sha256=UhJEF--e0B816MCdrtyBxon4RQgsuM6vxLTBu6V6Y4A,2517
1345
+ vllm/plugins/io_processors/interface.py,sha256=6ZIp0yXv07pH3gynuueyYb0QcHk9YbTKyoLqzU3If_k,2583
1346
+ vllm/plugins/lora_resolvers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1347
+ vllm/plugins/lora_resolvers/filesystem_resolver.py,sha256=Frj6--zxNA52jqW6UhIEjH5P9DoTaup3N2WeMHyF4V0,1957
1348
+ vllm/profiler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1349
+ vllm/profiler/layerwise_profile.py,sha256=p_EhWfWFVE-Nkhiz6VlwR5S5Y7OUEx12mvJp3TE7lsQ,13424
1350
+ vllm/profiler/utils.py,sha256=0rGR3LYSg6uZitAxN0bKgruTtVwtvytsNfbFZz4QLjk,4659
1351
+ vllm/profiler/wrapper.py,sha256=5U9fh423IEnl6L5WNvdZMo1BTBQNZijfEF25JgwbNhM,8137
1352
+ vllm/ray/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1353
+ vllm/ray/lazy_utils.py,sha256=0QXF-uTIUdzl992ugkYgkvHbWUG-85yjuIDNSLVu2gQ,651
1354
+ vllm/ray/ray_env.py,sha256=hi3BEix6Bwyaaunm-2KvvhCuqV4AD3ooK6SQQDowizA,2562
1355
+ vllm/reasoning/__init__.py,sha256=mOIAEflcrF9u7l4izGqJPLIKBsY2MIZtLbWhnDhik4U,2434
1356
+ vllm/reasoning/abs_reasoning_parsers.py,sha256=LiJ9XekQbIDVhNeKoAU3ghJUVJvBMB_31emrn5OQnFI,10575
1357
+ vllm/reasoning/basic_parsers.py,sha256=Wu76rQUSlHPKFj0-GSR8NJspxZUHUlwTCl-WvQIl1YA,6828
1358
+ vllm/reasoning/deepseek_r1_reasoning_parser.py,sha256=aCkmFQVv4d-4EqYMbNtdHnozRs_5tLrOJWfXXHT6U-E,2351
1359
+ vllm/reasoning/deepseek_v3_reasoning_parser.py,sha256=TiowlPrTFNSF5Gg-DdIBAWPNFf3zZfOr3L9F2hljhGw,2483
1360
+ vllm/reasoning/ernie45_reasoning_parser.py,sha256=FWSQqSHiUxh9VeR0jP7fMbWVjeiwnKs8iqy9Eudy-oI,6828
1361
+ vllm/reasoning/glm4_moe_reasoning_parser.py,sha256=-hI-fteXwX86gw4l25w5fBMrdOPQU79E1H1haAvkymM,360
1362
+ vllm/reasoning/gptoss_reasoning_parser.py,sha256=_L616-u2stNttfvReMTrKTgkpWZTjMUySYn1EpSIoqU,6817
1363
+ vllm/reasoning/granite_reasoning_parser.py,sha256=d6BikPcKaIBd5WkZaIm2dG1H8HUrCcjPR4gEePz15js,15196
1364
+ vllm/reasoning/holo2_reasoning_parser.py,sha256=iXccz-pCqfecA2vUS9_h5yAyovnUlavpL2FYlovuzF8,3384
1365
+ vllm/reasoning/hunyuan_a13b_reasoning_parser.py,sha256=sTm9xUNnoJ73zevO_Z0hkx_O4SriOKNe6e7THs_NCYU,9571
1366
+ vllm/reasoning/identity_reasoning_parser.py,sha256=DCuphNKtu5il8168dcVqutoqszFOW5x9pQEXIO7_3_4,2112
1367
+ vllm/reasoning/minimax_m2_reasoning_parser.py,sha256=Xga1pMPUmAFTryfisnwcKOLqKCuUd_6KEISKVQnVD5Q,3806
1368
+ vllm/reasoning/mistral_reasoning_parser.py,sha256=aI8g_6qAz5xnUG4VpYAQdNf1CUglg97gJGdtNftg2e4,6199
1369
+ vllm/reasoning/olmo3_reasoning_parser.py,sha256=-RtXQ-UF091RzUMjMGEfCSzBLQm-2BQl_0AKPU5rPl4,10991
1370
+ vllm/reasoning/qwen3_reasoning_parser.py,sha256=6yJYZVXxa-QL3I2ZHqmFdhZOpmoJh4pWex-6YWegSrU,2487
1371
+ vllm/reasoning/seedoss_reasoning_parser.py,sha256=Oz4zSgr6seYtssSyDKsFi7J-b9kTy-IcuC01HNJkv_c,832
1372
+ vllm/reasoning/step3_reasoning_parser.py,sha256=RuMnQF_As4SXSyOdGzRE9Cgi5-um6MLYew0c8exWV-0,4220
1373
+ vllm/third_party/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1374
+ vllm/third_party/pynvml.py,sha256=HRQEbE5ZB-AgMIySG4j24hjlEgSGLrNvHJUq7UawCfA,234653
1375
+ vllm/tokenizers/__init__.py,sha256=F3xPUuvHJZfUCeLImLWYyDBZa-e_1aMlj37SfUZHr_A,418
1376
+ vllm/tokenizers/deepseek_v32.py,sha256=3C-Muun1vEC9-IZ5OPLnbIaR0PCnNEVOw9f-wPuzlvs,5725
1377
+ vllm/tokenizers/deepseek_v32_encoding.py,sha256=rnDB7uPCChOLCoQhaRlwYX3W4AACquI2m2-UrBjmPmA,15541
1378
+ vllm/tokenizers/detokenizer_utils.py,sha256=pn4BAMQzAWeDC-rgBUVyJjhKMFvuVbkbP8Szqr3ihkQ,7601
1379
+ vllm/tokenizers/grok2.py,sha256=jtJVIaxgwbNIOOxIulvQSAiWxNnbjR3uguugrHlNyE8,14306
1380
+ vllm/tokenizers/hf.py,sha256=U7z-BrHXNwbYHvtCLpu9rkxzYYPie9VGNIh0aMrUmac,4321
1381
+ vllm/tokenizers/mistral.py,sha256=TT_7-cZPX2VSf7zTwNIa7YFBexEN-ytBREC1UkxSHXQ,21300
1382
+ vllm/tokenizers/protocol.py,sha256=sSYFeI-HqEHQkkFqxgXjSR02vl9jjpw3CoHp6XzBex4,3200
1383
+ vllm/tokenizers/registry.py,sha256=7h5AWf-rvynr1DFmnF9oWYzC3-1FWJ_rmnkq0V-dvKg,8084
1384
+ vllm/tool_parsers/__init__.py,sha256=RebORr1XVnUFwh8JzlkthaKK5jNnqwPDjShHYBGzUjk,3582
1385
+ vllm/tool_parsers/abstract_tool_parser.py,sha256=fPJcff8CHofqykUM_lOWQbGHmPT6cVjT56is_K6gj1w,9688
1386
+ vllm/tool_parsers/deepseekv31_tool_parser.py,sha256=rJB8NJKPPOcySVtsbS-9oVQYjN7bPPmZzMPfy9--Ouo,16428
1387
+ vllm/tool_parsers/deepseekv32_tool_parser.py,sha256=tbg6_aN15ogN7zlJpxrKlwqd4ytFoJnJGHzvLbb4cCQ,24967
1388
+ vllm/tool_parsers/deepseekv3_tool_parser.py,sha256=YGEuF79RKHg1RJvOtmRvyzw2n7s6eoOMXa7h1tsOrSU,16535
1389
+ vllm/tool_parsers/ernie45_tool_parser.py,sha256=-G1vjjtaNvDlLgzRrnlsqoevHXHchBICVwShRA29PZQ,8338
1390
+ vllm/tool_parsers/functiongemma_tool_parser.py,sha256=C8Loo0A1PqXBQqJP7Q7yfTgIEEfYQetwglhy_XC-kvY,12677
1391
+ vllm/tool_parsers/gigachat3_tool_parser.py,sha256=2HfUniM7x99HD4ZyuFmOhgg74A3vW0X45N4R9dqt3o8,6189
1392
+ vllm/tool_parsers/glm47_moe_tool_parser.py,sha256=8cE5x9mBDyxMyg2kfbKecKS_8xcgsKKEbnfaC5e2YjI,736
1393
+ vllm/tool_parsers/glm4_moe_tool_parser.py,sha256=bcrHC9zvDGKdhKU1byn0h00r3n-BTbXGKq3comgEaSk,8254
1394
+ vllm/tool_parsers/granite_20b_fc_tool_parser.py,sha256=Xlakk5wWGl8ouI4u7uqkbqmjDuQbqDpQYt3p7Vhphrw,10986
1395
+ vllm/tool_parsers/granite_tool_parser.py,sha256=unkk9K7dgtG4w_B_BiIxyvkk1vLxKV3XyWRgCGp07eI,10242
1396
+ vllm/tool_parsers/hermes_tool_parser.py,sha256=ogXQ5BjufuzL1jJAAJ4aT_EwFk3Vz4xeg58bJFu-tWI,21206
1397
+ vllm/tool_parsers/hunyuan_a13b_tool_parser.py,sha256=FW44O9ZpEG76HS3h7IaDWHR7OLZ5Q1gA-zdVh_x98ZQ,16676
1398
+ vllm/tool_parsers/internlm2_tool_parser.py,sha256=xf_VknHLp0jjwMa02zx9e5XfijOMFka3SDm8Oo8E8Xs,9069
1399
+ vllm/tool_parsers/jamba_tool_parser.py,sha256=d4HpyS6YTrF6pEYGRAEzv6dapQp79Qvfdm4t69Y-rWw,13708
1400
+ vllm/tool_parsers/kimi_k2_tool_parser.py,sha256=ibDBWSwHcTOapi-5Iy2IzF2_6NvcBSWeIo-Tsg9HQuk,26661
1401
+ vllm/tool_parsers/llama4_pythonic_tool_parser.py,sha256=x_sSczt4GLc7xAWAChlQOvkx4PJayHi8LvhTLUbDluM,12815
1402
+ vllm/tool_parsers/llama_tool_parser.py,sha256=72mCiHazsLf5GnxQBd4czKCrFis7o6-E4x9gyB6a4f8,13630
1403
+ vllm/tool_parsers/longcat_tool_parser.py,sha256=5nkwBi6yGlAALwvT3A1zx1GbnFeGsZAM3wqElOnMaqc,1287
1404
+ vllm/tool_parsers/minimax_m2_tool_parser.py,sha256=Eblwcgb11Hj514BRm1v-ch0Leg-2Xf0kect-fFwyEIg,31717
1405
+ vllm/tool_parsers/minimax_tool_parser.py,sha256=VpAWCdekghCq5-spQuPVUP6ykM-2uY9K0s-blyJPMJE,28481
1406
+ vllm/tool_parsers/mistral_tool_parser.py,sha256=_WRxjEjc0KvzKM0lRf56zPAf8e-khl1wwFyLuFt-Daw,26127
1407
+ vllm/tool_parsers/olmo3_tool_parser.py,sha256=bX_5qG0HMgaBMlMAcU0ymrVlnpUFH8YF-8UGkVPybxw,13918
1408
+ vllm/tool_parsers/openai_tool_parser.py,sha256=zamJ6XBEP8zRLD_W8HzI1-MgFP9eZuYRsMWMUGL6Z90,4207
1409
+ vllm/tool_parsers/phi4mini_tool_parser.py,sha256=YpjNdhrP8REcGlgdNb22-Ox7skMeYm7xZP2gQDhcvKs,4012
1410
+ vllm/tool_parsers/pythonic_tool_parser.py,sha256=uOUzU89Jm-HU9z-_gzAVIkH55eeGih6bTUHhNBdWia8,12197
1411
+ vllm/tool_parsers/qwen3coder_tool_parser.py,sha256=vELPpNJeRlj9sAsyrOAVQdmOBTSsy0HNVypJLeLG_Q8,32732
1412
+ vllm/tool_parsers/qwen3xml_tool_parser.py,sha256=qfJ0HxwsyVNokWG20ANLNR2CtWE582HKTljiviviIVM,53785
1413
+ vllm/tool_parsers/seed_oss_tool_parser.py,sha256=oUm_S6Kq-oLyKNoCPemnYSSq2O4rn4PHYi04-q47Hk0,31332
1414
+ vllm/tool_parsers/step3_tool_parser.py,sha256=X0JEBbJ5BoeisSs4FrSEOCLm9KQ49QoY7FOkkfbujAk,12087
1415
+ vllm/tool_parsers/utils.py,sha256=5VZCLxbxuOP8FtiFjYneEb7PKtQyLJBVp247IaxsHyQ,7444
1416
+ vllm/tool_parsers/xlam_tool_parser.py,sha256=HHigcWAvMY1dbWEFDYUVU-IxMHsJVLfN14M54MZhq-I,24618
1417
+ vllm/transformers_utils/__init__.py,sha256=BTdT_ym1ftRVhgxBUkdJQqmO2LiKDX2MZZEEG8U_05E,932
1418
+ vllm/transformers_utils/config.py,sha256=EG9ifSEmI1ICJYwPxV3VKI4irCO53hzV3bw9OtfkApg,42590
1419
+ vllm/transformers_utils/config_parser_base.py,sha256=qSyL1AYBvvnQTII-lS9_N602OJ_Huf5BkUZYBhQEFtU,523
1420
+ vllm/transformers_utils/dynamic_module.py,sha256=Gh0_B_IHLEedgKAHPNUZcQo2F_dAxicKo6luvfTo7zw,2038
1421
+ vllm/transformers_utils/gguf_utils.py,sha256=2EW5JN3sGwMXmym-2QpHtzyvdcEoAPR12j-_S5J9Q1Q,9566
1422
+ vllm/transformers_utils/model_arch_config_convertor.py,sha256=ROOmoXnyyKPrzMjmp5BJROFC8wHxgw5mA4KXhm35CNw,15538
1423
+ vllm/transformers_utils/processor.py,sha256=GjYvqyJhcdvoLOj28g7hQ-YIh6wroEDD6GmqQLYG-Rg,15065
1424
+ vllm/transformers_utils/repo_utils.py,sha256=iFkVvdV7Hjyo4isZozMjoMwxCQxbsWpFAELcZAd9XDU,8467
1425
+ vllm/transformers_utils/runai_utils.py,sha256=udKJP-FS0s0GTkSqe4zBlpKBCtwdnFo_YTVpmz-P0ao,3212
1426
+ vllm/transformers_utils/s3_utils.py,sha256=S8pMrLcoUOXiexsioyzBjuYz4wst_YZC-yqTpC0QCsI,2783
1427
+ vllm/transformers_utils/tokenizer.py,sha256=UENbACgDGRrt7YiWQfC1jH6UYSIRBQSty6Z9gKYvgwg,589
1428
+ vllm/transformers_utils/utils.py,sha256=H5CxGzLlIpCA-Zd8lkKlghMcFgeHopgYBA_9p7Rrle4,3078
1429
+ vllm/transformers_utils/chat_templates/__init__.py,sha256=U1sUyX9swSjxaULlg0B6rSroU5H8upeyInuHsF74SEE,208
1430
+ vllm/transformers_utils/chat_templates/registry.py,sha256=f5ULuuY1mJUrpwFwJXY_QqDskleozjJKMomEhr-jUBc,2563
1431
+ vllm/transformers_utils/chat_templates/template_basic.jinja,sha256=DMH0156UMA7eoJelXKUMEDzB-SigjbyCOBxIu9OyFJE,78
1432
+ vllm/transformers_utils/chat_templates/template_blip2.jinja,sha256=ltMbjFdK7T4HUcN_OQaX4hj2r0PGlS1EJ9zhSlnTz1c,332
1433
+ vllm/transformers_utils/chat_templates/template_chatml.jinja,sha256=CKxCWf_KemM_DntV70Hf03WNkDvxznolyW-03SJJw54,370
1434
+ vllm/transformers_utils/chat_templates/template_deepseek_ocr.jinja,sha256=sN0qqjXqEmWsTBafWtrvXbYnSaeCOTgfDjzmwvk4Njk,499
1435
+ vllm/transformers_utils/chat_templates/template_deepseek_vl2.jinja,sha256=WX32uOZ7h8_xqrWvmsI5R-6Ns8ZcXVn74CKB7FJOifA,785
1436
+ vllm/transformers_utils/chat_templates/template_fuyu.jinja,sha256=hzdsPgeUMaZnd5L23QPiz2oC6_wMBy5WgZkXMVs3Dgo,85
1437
+ vllm/transformers_utils/chat_templates/template_minicpmv45.jinja,sha256=tNvJgf7S0je1GqFxPUQ-q5nSGwXoINdqW3-VOFNekh8,4231
1438
+ vllm/transformers_utils/configs/__init__.py,sha256=mrTYFVX0CujC5TvNWW8OYkNwpBQoTopzwpJbtaoal40,4222
1439
+ vllm/transformers_utils/configs/afmoe.py,sha256=aQB0DRO3xFbPr3HhYN8Qu_n-D65SpjJcdcdBVRzaXts,3212
1440
+ vllm/transformers_utils/configs/arctic.py,sha256=jy-9t3V9xqxrPtwgTDq3HmB0W1tzo1ehxgbUbQQ_szc,9790
1441
+ vllm/transformers_utils/configs/bagel.py,sha256=H_ZvmTVMbslvRpirbsELoBaPc80dse45fIxtUfd9bL8,1903
1442
+ vllm/transformers_utils/configs/chatglm.py,sha256=0Lw_vCbBpbsWOSiLQG6q9LpgeWmgbTAIJJwlHYbMWPk,2731
1443
+ vllm/transformers_utils/configs/deepseek_vl2.py,sha256=0X1rctqdTJmbNu1uFybVeYSpDxAr299Ly0qZjl0SQLU,3881
1444
+ vllm/transformers_utils/configs/dotsocr.py,sha256=_mxuA6xDpO6N2-FD4R5XVqLDP79D8i0OAZcPvqUCSdU,2445
1445
+ vllm/transformers_utils/configs/eagle.py,sha256=R8LT924n_tTE8LkfYcENCv_UVvLmsIWKl6th6okyOWg,3012
1446
+ vllm/transformers_utils/configs/falcon.py,sha256=XNrg2x08UDZngZqtv5T0CiEFZq7qhoJPWdEYnI64e_Q,2937
1447
+ vllm/transformers_utils/configs/flex_olmo.py,sha256=NInzKT7pO5w6CKxxaaEAXW_YnN6f1Sv3hDWQYhPL7ko,3157
1448
+ vllm/transformers_utils/configs/hunyuan_vl.py,sha256=ErUQbR08co_u4Mt4l1uyCI386fTVK2IjwDE7EapVmRw,14493
1449
+ vllm/transformers_utils/configs/isaac.py,sha256=VRn-XeZvwAYDDEqDuTAwrTcqdNybHvHaobH1w-ZoDIA,3289
1450
+ vllm/transformers_utils/configs/jais.py,sha256=0mHMFC7GztEyIRf8IJGF6ELhzyVlCqPnJpOEFBUpIRY,10441
1451
+ vllm/transformers_utils/configs/kimi_linear.py,sha256=NQpLdbqUEQYGOsaUrvqMbPFgUv8C3uDBCv5X8dPZ3lE,5377
1452
+ vllm/transformers_utils/configs/kimi_vl.py,sha256=wGV24Na51emzxtMP6EbQ2pereXMCjkIQPo1A2pgcSZs,1362
1453
+ vllm/transformers_utils/configs/lfm2_moe.py,sha256=WUTK1E6qOA8ROk3kCzaP1fxJLjZchXyvd3nD3nZk4G8,7514
1454
+ vllm/transformers_utils/configs/medusa.py,sha256=ECZ7guyPJJob-viGpZh1LZSdi0VPQg1w84pym4C6Q3o,1930
1455
+ vllm/transformers_utils/configs/midashenglm.py,sha256=FG_hFNjxJaAmXV5LIePEXWcYZqs6IRlSle-9awAeU_c,3631
1456
+ vllm/transformers_utils/configs/mistral.py,sha256=hamquwSzDBIV2ijEzGPhJRVrrNijjl6SdgqXzHnAbt0,9418
1457
+ vllm/transformers_utils/configs/mlp_speculator.py,sha256=aTNL7dpJxF6piYE6EysUiB11sBAOFw_xlmlDOFEoEa8,2403
1458
+ vllm/transformers_utils/configs/moonvit.py,sha256=wENIYbaocro7cWlpcc2yrIaWSyzkLpABVTEJ-JQ7Aak,1232
1459
+ vllm/transformers_utils/configs/nemotron.py,sha256=EAYX0byXwgziKfac4nL2cFtaatPyDQb5WMgSByjsO4M,9765
1460
+ vllm/transformers_utils/configs/nemotron_h.py,sha256=kz1QlSu-pGurkckNK1qrDoBUy16JkC5VhbvB3JrkFSM,13176
1461
+ vllm/transformers_utils/configs/olmo3.py,sha256=pnjjin2JhHw7lA0JzpsVaRiF4l3-jDwj5_DrroEEVTU,3026
1462
+ vllm/transformers_utils/configs/ovis.py,sha256=zjfzz8-btPauEhKwQm9dRqmsZ8jakSaVCqqZ2rJZv2g,7535
1463
+ vllm/transformers_utils/configs/qwen3_next.py,sha256=zUXBpEMzdGVlXIH_ELTyUWdUI_4lepALyZ7fhXmQS0k,14999
1464
+ vllm/transformers_utils/configs/radio.py,sha256=F_lN4X1HeOAaqdNAV9bq-j0eIVdGc9OPt-XzXEqGu5o,4097
1465
+ vllm/transformers_utils/configs/step3_vl.py,sha256=4qeCToaFjy95XRlvAN1UHyYQpz89VVd33iVOEdOB8x4,5238
1466
+ vllm/transformers_utils/configs/tarsier2.py,sha256=ydiT9TPSYbSL58QHX8y2KwtboQ0gthhAjT8eML8gxj8,685
1467
+ vllm/transformers_utils/configs/ultravox.py,sha256=4DwreIyyKxSwyie6av42UJof5wejQHeDLWtcA5jBPO0,4944
1468
+ vllm/transformers_utils/configs/speculators/__init__.py,sha256=48Vcuw16i9R99vM3iDVkRkX107yJtFeTtdWgLQE-XFg,107
1469
+ vllm/transformers_utils/configs/speculators/algos.py,sha256=ZUKraC3NROj6rIWXDUqWJBELGFbNI3P0-4Or4W39enQ,1538
1470
+ vllm/transformers_utils/configs/speculators/base.py,sha256=6ltGW5jguo0u1Sznw2I1pXfIAe0ojteBKsm9DhaMOsQ,4382
1471
+ vllm/transformers_utils/processors/__init__.py,sha256=cpoANOQp_WiE40YIFmumVwlMtHa0dFQ2tAOtGSTm47s,964
1472
+ vllm/transformers_utils/processors/bagel.py,sha256=-86PwGcS62YOoTSF93IDF0mUWgYUTHTnE-G7Ihm3p7Q,2855
1473
+ vllm/transformers_utils/processors/deepseek_ocr.py,sha256=qhDq_pr2PZjisj5Mj0SBY6mjX0ivSSGmp3z_V0i8K3U,15088
1474
+ vllm/transformers_utils/processors/deepseek_vl2.py,sha256=YWmA16RtLAOE_eMHTJwHJSFoRFlBU3wD7cR3ZXP9JyQ,15121
1475
+ vllm/transformers_utils/processors/hunyuan_vl.py,sha256=Rvrhf60qg2f7fmzcM2rCRzZ4mfaQeSyWLMEoIZLGp2Q,9496
1476
+ vllm/transformers_utils/processors/hunyuan_vl_image.py,sha256=KeauATCER1RdedquOh8bvXPKk9GT6eQAG8avSRqSdz8,22292
1477
+ vllm/transformers_utils/processors/ovis.py,sha256=wzvMI1WEBK408Yb4PxgepUwJ96-LQV2n-lxyUI9mcjM,19426
1478
+ vllm/transformers_utils/processors/ovis2_5.py,sha256=AGj8iHo5IrDmPlRmljIYnh9T2DED9Ior1HFSJWwXsGo,19505
1479
+ vllm/triton_utils/__init__.py,sha256=FY20qv1flNw_TDjM9j544voqnflClkYGSOEF5lPwv0M,567
1480
+ vllm/triton_utils/importing.py,sha256=CcaJ7kpP7bKP3yfuR_1w_vNRBxiZk8qNdcatjsvoAYI,3589
1481
+ vllm/usage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1482
+ vllm/usage/usage_lib.py,sha256=b4cl_FCt4PJ3-H9FlJDKNdSGPq3GZRyvG63Bs60ln8U,9065
1483
+ vllm/utils/__init__.py,sha256=rdKYd7C14ffM86xeXb2QUtJsVz3DcFk6jZTn_aOCLfY,1224
1484
+ vllm/utils/argparse_utils.py,sha256=IORb1CcXML5OmrtI2m7bwNQX4pHPpqQk5CoPsVKydts,19049
1485
+ vllm/utils/async_utils.py,sha256=nwAA8cr1EgJb7rAAwifFWXHAQbTZvhRqH9KRdKPHNdk,11193
1486
+ vllm/utils/cache.py,sha256=p6Cvrul9e1fOuw4h9-n74qmY_lHMQyS0BqhHXQqN-_Y,6206
1487
+ vllm/utils/collection_utils.py,sha256=OevIR00n3MlaZIvf4q39a0fXkqek0bR7WXi57WHxBdk,3070
1488
+ vllm/utils/counter.py,sha256=6Xa0WjHey2LwyPJkGfYa37mgOsQfcHJF9kRypIcaHDQ,1165
1489
+ vllm/utils/deep_gemm.py,sha256=FC-wSKYkPlFHux0bZ0u7jZ1p5W42X-lCC_CTK47iLf8,14436
1490
+ vllm/utils/flashinfer.py,sha256=XeKfS_on5GkXAAqt7lZgENj4g576bn5GdvBct4TvAGQ,19207
1491
+ vllm/utils/func_utils.py,sha256=pLXKoub-DlGrxZRwliCGmuMy2eiEHrglZPEQSbvPjKg,7706
1492
+ vllm/utils/gc_utils.py,sha256=zMuLZmEcjECblk30kHjKGwLdOHANND5vopi17x_IRjI,4970
1493
+ vllm/utils/hashing.py,sha256=ibS9K9JGpb_c8A12bqOKgYI3auz9a2t9XEfZaxVZJD4,3618
1494
+ vllm/utils/import_utils.py,sha256=Bp2tglhTOL4qnGk2NXSaz70HqS0wpsMt8XLvZTxBrm0,13553
1495
+ vllm/utils/jsontree.py,sha256=lktXNEOq0w1qqAGTPgpJ5eDogjetHDC15Hq___2OLmg,3755
1496
+ vllm/utils/math_utils.py,sha256=MskLJpEF6qy1In1mRyRLzmuyDRBlJgtZHfyu2Okq1c4,774
1497
+ vllm/utils/mem_constants.py,sha256=DerNf9-iEKE2kx8c6ufmLY23mn7vV3K1vskiAw3SWJU,390
1498
+ vllm/utils/mem_utils.py,sha256=PCw-W483_EV7jp-IfbpDQDC0Y_vnF8CPYrAWTo5ykwA,10341
1499
+ vllm/utils/nccl.py,sha256=V0yVYxhEKRi2hSWBqK_7OaFwvVR_RAJBNQ-a3wgCDXA,1915
1500
+ vllm/utils/network_utils.py,sha256=J3SsZGRhg_47sujXrpKD88HdirxxRrkSow9dQTZxmsI,10076
1501
+ vllm/utils/nvtx_pytorch_hooks.py,sha256=6XEURPMyQs4YZNajLQUbvwugs3tfF5Zd5uXbugwMdf8,10538
1502
+ vllm/utils/platform_utils.py,sha256=V5bnsv9S_IGUJtlyqhIG0Nn-BldsEwrqDAvRTgSp_QY,1873
1503
+ vllm/utils/profiling.py,sha256=UWku3rWFiMP4UclIokbOxF1fh5xVuwiOc4vjsq2Fdo4,1469
1504
+ vllm/utils/registry.py,sha256=gWRZ2XRwU-YapctL5A05O1bG2Vgm-QBcPrxjUPRugFU,1555
1505
+ vllm/utils/serial_utils.py,sha256=6rNd70X-CanGQJBx41Yp9-eLp6XiDBoAZR7ST5Df_9k,5876
1506
+ vllm/utils/system_utils.py,sha256=3OqHJryqp4uQDZWtKPxOs8yz7gPlHUOA1Cgqbkx0YeQ,8930
1507
+ vllm/utils/tensor_schema.py,sha256=Q2GzQ-CzlvQjA9qvZBcP8f3layD454s7c5nRt_FeZWU,9140
1508
+ vllm/utils/torch_utils.py,sha256=BwtwX6CUMLf4EkETYTqI9D18m4ACN4e3S5wpxP-QiD8,26493
1509
+ vllm/v1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1510
+ vllm/v1/cudagraph_dispatcher.py,sha256=w7rTMA763PoJgYaNK5fiwUIRQepqqb2M6zNgOFtpzQo,7766
1511
+ vllm/v1/kv_cache_interface.py,sha256=V1m1wMT_KxQTo8cTWAZ9iGtS3d5QOQZtWTLIRaoEiyE,17480
1512
+ vllm/v1/outputs.py,sha256=2ajKwJmun1H9CSJsAia97oPoRTfHAHXXEpDZWGVykmQ,8367
1513
+ vllm/v1/request.py,sha256=Lk7yr9_tskXn4jSSzkH5hH8tUU-fFKY5RU0MpcD7bpM,10208
1514
+ vllm/v1/serial_utils.py,sha256=ZlsUvbLaHJkPY56rUUxwMgt_tVk5D39vV7QVuBp0q18,19800
1515
+ vllm/v1/utils.py,sha256=krrrvsFMavh0CXGD7lilBjewK39Yiy1co9w-zSwKkzA,15797
1516
+ vllm/v1/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1517
+ vllm/v1/attention/backend.py,sha256=meuuBRTCSOWhIXRK-enCsgOLcOABjrtDa7deKMKp42I,25675
1518
+ vllm/v1/attention/selector.py,sha256=5hQSBWZN2-vDewlrfv5oc1nl4MplkVqA5SLp9OmREQk,4445
1519
+ vllm/v1/attention/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1520
+ vllm/v1/attention/backends/cpu_attn.py,sha256=Qdnu-q2xcxvQKPnWuSh3bG6kLv6tix7i2O9BTCUTlTs,18215
1521
+ vllm/v1/attention/backends/fa_utils.py,sha256=a20uS1mpppjzeuakS8fGhOkKkbhTGF2438gu86Ah_lM,3997
1522
+ vllm/v1/attention/backends/flash_attn.py,sha256=JPGqvhCO19Z4A3MYtLyA5iXtbaljV4c0Qv2Inc-WalQ,42883
1523
+ vllm/v1/attention/backends/flash_attn_diffkv.py,sha256=8EU5rcDQZDtc8znzCvrL8mc5AFWFbQbPUDsPIap9DgE,11068
1524
+ vllm/v1/attention/backends/flashinfer.py,sha256=5QIQpmxfnzhIFuxlIFQwIgs8m-L91H4WNOjSgCv93CQ,67571
1525
+ vllm/v1/attention/backends/flex_attention.py,sha256=ABcFH85pcU0wjncszNEPMKSpB5QMzxR-UJF8lf13nMY,39774
1526
+ vllm/v1/attention/backends/gdn_attn.py,sha256=zI9FFT2uHBWWnDOWV8QJvSANzkMjN0vZT145ZxPvJt4,15132
1527
+ vllm/v1/attention/backends/linear_attn.py,sha256=cNwkl4Z_jQhL_kEwPW2jG_4qNcrzRkEtvnr1xSRilh8,2416
1528
+ vllm/v1/attention/backends/mamba1_attn.py,sha256=nMDnzX5L1l-KYCf9Hir09dMO67ls52EYEz4zEOKVjXs,782
1529
+ vllm/v1/attention/backends/mamba2_attn.py,sha256=fVCJ1R-_oMj57XWWzJZnRX-DrHdqAOxutDrcFeifnx8,9674
1530
+ vllm/v1/attention/backends/mamba_attn.py,sha256=Yb6P6EHaopzD45W-ledZFYqknq1co5xjZaQO_8kCpX0,11931
1531
+ vllm/v1/attention/backends/registry.py,sha256=mIOgPhZVROPkXLUZJRkH4Wzq0OnM_nZjUnUZZ_z_65Q,9624
1532
+ vllm/v1/attention/backends/rocm_aiter_fa.py,sha256=uefcXUHqinapZWGlxBM4hDfBpodinIbFenqE4J0pA3c,38618
1533
+ vllm/v1/attention/backends/rocm_aiter_unified_attn.py,sha256=EJyb8_8OtI9t5QRIYYiKEV9hIiSlVCbdtzy7eGLeGF4,7055
1534
+ vllm/v1/attention/backends/rocm_attn.py,sha256=CoXTAYZoKMWOtZtyFRQhph6FLU4BY86m-qNhVVWPKV8,15143
1535
+ vllm/v1/attention/backends/short_conv_attn.py,sha256=WgXiXNM7ONXLaVf5MJA1EKILP2dm4CCpdbgJ9dwM7iI,756
1536
+ vllm/v1/attention/backends/tree_attn.py,sha256=yUmbBumPQxVnGNmNRTHtI2BQZR8PaALMWSb1ZMx49uI,15738
1537
+ vllm/v1/attention/backends/triton_attn.py,sha256=ugWbsZiCCyO75OSn0_ernFST0vnELCDS_qBubgFYtcQ,21579
1538
+ vllm/v1/attention/backends/utils.py,sha256=iWCaJpP1Zwxr7extjFJiNYI3hbUzrYO7j1UeIPDRKac,37557
1539
+ vllm/v1/attention/backends/mla/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1540
+ vllm/v1/attention/backends/mla/aiter_triton_mla.py,sha256=6eTmxRRS9uTRaqyJ-DQT0RG6Z7CjItiIAfoF_FgLaIQ,1974
1541
+ vllm/v1/attention/backends/mla/common.py,sha256=u5qsTXFTKX_44WkDEIUWb5sd42s4GuoCVkBhqcrJD-U,85051
1542
+ vllm/v1/attention/backends/mla/cutlass_mla.py,sha256=BRubHx3sgQ-kk-__hA9LvWfxJX_mQqEdEA6jP7SAMQI,8804
1543
+ vllm/v1/attention/backends/mla/flashattn_mla.py,sha256=U_c48EIjk9SAcqh8PAzVRQI11aIjkzh8sqZ5freDALo,12151
1544
+ vllm/v1/attention/backends/mla/flashinfer_mla.py,sha256=fAuFs-6h-DWmN9a98Hfya7UuokMwcmUydDeimOl3iBA,5643
1545
+ vllm/v1/attention/backends/mla/flashmla.py,sha256=KvlQwuu1pEajSbn8rqtKr9L0TKMW6XakIhskw87pFVM,11298
1546
+ vllm/v1/attention/backends/mla/flashmla_sparse.py,sha256=WNNTLz6PtrLD1tvwq4GkrraKHS_E6bxhIQBRsNEHJUY,39746
1547
+ vllm/v1/attention/backends/mla/indexer.py,sha256=s31qFcK2x9vNWo8O5LbHaWmz_Jkjy6BWjL8-C2Nyd9M,12622
1548
+ vllm/v1/attention/backends/mla/rocm_aiter_mla.py,sha256=KB-pmSorA8p5RdPWtpDv_9r55LVUv7OhfXXvl19aLFg,9836
1549
+ vllm/v1/attention/backends/mla/rocm_aiter_mla_sparse.py,sha256=MqGGvUSuafvnRXPrghMWd88uRQkTJE0LHJ_uXC6njME,11174
1550
+ vllm/v1/attention/backends/mla/triton_mla.py,sha256=brd8h2wJ4qgAriVBt7F5EqCSsBNm3fiUva4Ndqr7eUw,5131
1551
+ vllm/v1/attention/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1552
+ vllm/v1/attention/ops/chunked_prefill_paged_decode.py,sha256=BlOycbH0C0D9rMG2hukXsmDADkymYAaRnuXQmiRxT_s,15628
1553
+ vllm/v1/attention/ops/common.py,sha256=_v4nUo8OUrwYx6k-d0d8ClbksqU4ZP9vEjwV67MQYUw,13701
1554
+ vllm/v1/attention/ops/flashmla.py,sha256=mFluMSd6pVwm8QpVArJcoUy_Y4RWMNVtAqcQth1T9cM,8389
1555
+ vllm/v1/attention/ops/merge_attn_states.py,sha256=gwJoIzgUPGqEr20vWSF8ByEUPxkBDTSeUd5whJPvAXM,1658
1556
+ vllm/v1/attention/ops/paged_attn.py,sha256=e9UNGgHTThPr7ren8u8WUTB1fAqaEnug7X3Kg4dsB2E,1439
1557
+ vllm/v1/attention/ops/pallas_kv_cache_update.py,sha256=wbl56j_Wv9PEseDhkjZcKurNO-CV785P8fRsjVR10ho,4190
1558
+ vllm/v1/attention/ops/prefix_prefill.py,sha256=_p33Jl6zj3PqWkq7klbBo6pS_RJvnImBnaA9WUzAaxM,27286
1559
+ vllm/v1/attention/ops/rocm_aiter_mla_sparse.py,sha256=xQRZvwzzTdHLNGQhD14w8CQ6nHNpqylmTTmZEUYlG7k,7682
1560
+ vllm/v1/attention/ops/triton_decode_attention.py,sha256=z03ru73yJFNVF33XvpHErHVzCpIHoQzX2rYwalw73sQ,19463
1561
+ vllm/v1/attention/ops/triton_merge_attn_states.py,sha256=4fOT2PY6AocmhvwAYt5Zu1PFIQ9lWAdqCxWd24YMW6c,3982
1562
+ vllm/v1/attention/ops/triton_prefill_attention.py,sha256=MWxmm-cPmIpC5qJxtNHUzieOb5NGFA9gd8CyCENHe2Q,8671
1563
+ vllm/v1/attention/ops/triton_reshape_and_cache_flash.py,sha256=l23FcUrpKLfL1CAjtRKRE7jDotvOm7bGhh4FTBy84cU,12771
1564
+ vllm/v1/attention/ops/triton_unified_attention.py,sha256=D6dHXqdA_BIJ1ia_5bl_QuOKr7fg5CA8VIX6-CmPzUk,38823
1565
+ vllm/v1/attention/ops/vit_attn_wrappers.py,sha256=gRd5pQzD12_mehl8-GaTSJUlAaxAdy-TMly-hY7h6jI,5191
1566
+ vllm/v1/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1567
+ vllm/v1/core/block_pool.py,sha256=GRrPa3l5F7Np_N9PKEuEvsvCe0pc08mKDHoAeByJr00,18949
1568
+ vllm/v1/core/encoder_cache_manager.py,sha256=-K6bsefhPlkUengmyLezLKdsndUw0yI7MwwOA-NA7F0,15993
1569
+ vllm/v1/core/kv_cache_coordinator.py,sha256=BmkzSRXb-QNwk9tESx63hhBWcLira7b7G47ETAHM2kU,20718
1570
+ vllm/v1/core/kv_cache_manager.py,sha256=Y2KQbZGt99FsD9oD6wh7X2_Oheulg4gGQ7LK0tRkU4k,20294
1571
+ vllm/v1/core/kv_cache_metrics.py,sha256=7-3sBP7_XwSm1RxsRkKQtSq4wknWUSGpq58TcNa2f0c,3138
1572
+ vllm/v1/core/kv_cache_utils.py,sha256=IIq8I-HLrr5OgFTsey8UfsGrHR3ENjYsJ3pQbIAEaAY,64270
1573
+ vllm/v1/core/single_type_kv_cache_manager.py,sha256=vlmbWGGIcjVGPghF7KeBEUUM9rexVpTbri4o4x2ih3U,38540
1574
+ vllm/v1/core/sched/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1575
+ vllm/v1/core/sched/async_scheduler.py,sha256=n-tGpO5XkqFbjiBlHHK8C6O-qEqRSBLRxdaB5ec-Hj4,2942
1576
+ vllm/v1/core/sched/interface.py,sha256=g_EK3FrDIfHUNPRQJHiPjfI-k85Wo2MJ7sOMJLT2aEo,7955
1577
+ vllm/v1/core/sched/output.py,sha256=_ynXfniAPeJ3dfOj97D1mUAqjhmfvEs8kDIYRrW4_aA,9828
1578
+ vllm/v1/core/sched/request_queue.py,sha256=S42Tjl-4FS_mEDC4qpkfmD_KyaQFw37YkIBF4F6Crl4,6989
1579
+ vllm/v1/core/sched/scheduler.py,sha256=tOZk_n3J6lwgskZq2TSNSS-e560Z4eAjKf5OiQUn0Yo,89264
1580
+ vllm/v1/core/sched/utils.py,sha256=2smDD11MGEadM13xFJdBiwJCXvJKnKyB_THnO6cnH7o,2175
1581
+ vllm/v1/engine/__init__.py,sha256=M8IM_KvEuYs51BiT6L1o37KD4zAkWo9pGT81Gs_2Apw,6784
1582
+ vllm/v1/engine/async_llm.py,sha256=gYr0Vht65Urn8iXBKcweET0Cw-d0EgSXVIw4JkpLgko,34176
1583
+ vllm/v1/engine/coordinator.py,sha256=6LSv7XNfvyc2pJ9qTYcHRXugupdrqx7E4C-M16VKXyg,17516
1584
+ vllm/v1/engine/core.py,sha256=p6Yk4O0VHwCk4cBmo2pfkaj4GDCCfe0Ga8BzFmpxzac,65104
1585
+ vllm/v1/engine/core_client.py,sha256=YB03UGf6ck4IXcmpkHvVUIJa0oISXXJf0bZYFz47bj4,54405
1586
+ vllm/v1/engine/detokenizer.py,sha256=bqjCl_-KZ5OYiKC9CN-dy4kXm5liJAFNqFyyDFIreC8,13188
1587
+ vllm/v1/engine/exceptions.py,sha256=Uqu6bUKEvMYpeVJYxlqYeveRcd9WnsFUENKt0JLMins,732
1588
+ vllm/v1/engine/input_processor.py,sha256=5VtoYxYTqIDVSMjXiGmZTE1pldyWyxUQfrLNoNhcM74,30122
1589
+ vllm/v1/engine/llm_engine.py,sha256=_dutvt40j8RmO0oVqPXI0AZ4UMKgsbOZH_fjpzhQsaM,15972
1590
+ vllm/v1/engine/logprobs.py,sha256=Fxf8g5pwnjDWtz3vrXx7Iga_T9gmKm3T9CvqbkMTSt4,8679
1591
+ vllm/v1/engine/output_processor.py,sha256=OBxEPgKcTNjyhs5ETaGW-Ovws3k208GDEBNyXCRYMis,28006
1592
+ vllm/v1/engine/parallel_sampling.py,sha256=Ii07rDh3nVSNTIjcHX61f0es0LgYKocBKXPhO2VOrm8,5494
1593
+ vllm/v1/engine/utils.py,sha256=0ZUwYUSPuajhlrNhk2bEBzBc2Wie36gF0qh017fQYyY,41992
1594
+ vllm/v1/executor/__init__.py,sha256=VwU0pRwKjvcCcXII_7N2FIYT2oNj1fquLjvUS-qqE2U,227
1595
+ vllm/v1/executor/abstract.py,sha256=cGs4Ux0wsEv88KonO4bCLRrzJFpM7_8zdwFTCQ9kBao,13233
1596
+ vllm/v1/executor/multiproc_executor.py,sha256=I0ZcC0SbPyO4zAvfiTHb07nUxpU4PQrAJMhP1bvisrM,34770
1597
+ vllm/v1/executor/ray_distributed_executor.py,sha256=tl8FrTK1jqQk2SKF-Rt6RtXacGD6ND-hXIjTrquAbkc,289
1598
+ vllm/v1/executor/ray_executor.py,sha256=efGbsYwh3NuA5VNMWkIZEVtUmveaKSKu0nuuMUgUTaw,24909
1599
+ vllm/v1/executor/ray_utils.py,sha256=a6iOnG-ZuCYsvHEJJWFlVKBYf_O_O139tqE307V_tKE,19266
1600
+ vllm/v1/executor/uniproc_executor.py,sha256=ZOJR_Xq5V581VWJjkvPQFwJMHuMqNDL7k_O7tzqNvQo,7244
1601
+ vllm/v1/kv_offload/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1602
+ vllm/v1/kv_offload/abstract.py,sha256=rEo4jQBZZ3AuYMDWNprePENX8wDFc086h40wFj4gmyg,5262
1603
+ vllm/v1/kv_offload/arc_manager.py,sha256=vUgKdsb11DwRqCcMkzW-lTf2zlMvGN2AaEHGy24G4LU,9545
1604
+ vllm/v1/kv_offload/backend.py,sha256=2ewriYjByJ2UwiWX-YJYhGkriJB0lChRnAbgtN0_8rY,2898
1605
+ vllm/v1/kv_offload/cpu.py,sha256=-rxG1oQEDrFSIR0nJ5Q87hHt16t1aTJ-8jkCL0jATX4,4294
1606
+ vllm/v1/kv_offload/factory.py,sha256=D0zNSL99nXhQnUMp1AuCt4_Dai4g_K8DkaROVHBzzEs,2118
1607
+ vllm/v1/kv_offload/lru_manager.py,sha256=QO85HtD0uV-Et_UkhZdtgXk38-SZqHQtIi0M-qnWULY,4964
1608
+ vllm/v1/kv_offload/mediums.py,sha256=8i5qik1oKldR3Gyf7S5veHM5h1prPZVR4xN05HSOUKQ,880
1609
+ vllm/v1/kv_offload/spec.py,sha256=Dr6ofxpQROmCZ0d-uPKXjLctMQiyCshiFujRb4XGzPA,2353
1610
+ vllm/v1/kv_offload/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1611
+ vllm/v1/kv_offload/backends/cpu.py,sha256=McAbCUX_6yYAipJ8bd418EOKxT_I4eIbzr0fiqeR46Y,2228
1612
+ vllm/v1/kv_offload/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1613
+ vllm/v1/kv_offload/worker/cpu_gpu.py,sha256=JGVIeKYJfcbduYByzTi6EQY09_bAcDlWJQPWTqopQFg,11326
1614
+ vllm/v1/kv_offload/worker/worker.py,sha256=T5JTtv7LY0bxoupRZNWIC-M5Z3m3dNHROuQOeSIps2A,5122
1615
+ vllm/v1/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1616
+ vllm/v1/metrics/loggers.py,sha256=eD4MVbmNb2IOOEsS6fU7K0vknKfOez83SdBNvBxbvtI,49323
1617
+ vllm/v1/metrics/perf.py,sha256=EgNqGgFxguzlcSaaMah6tN6B1qBo8KamJSFqRTubuao,42402
1618
+ vllm/v1/metrics/prometheus.py,sha256=dhI7DQbT7X3gFlcQOXmoa7PY5JPyw3fvFm0azVEP-ok,2777
1619
+ vllm/v1/metrics/ray_wrappers.py,sha256=aKg4C1sdyPhVyS41Cw48c-CSBFRCFaIUhi7FC7yIknk,6268
1620
+ vllm/v1/metrics/reader.py,sha256=drwtEKJn4gOnaCFvlaYEjibmQx7cQHIsDiQii4B9Uk4,8694
1621
+ vllm/v1/metrics/stats.py,sha256=E7jVRMGLQMIedxCbSEjqaZ36aBdi15TPwCpmM4JT6Eg,14935
1622
+ vllm/v1/pool/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1623
+ vllm/v1/pool/metadata.py,sha256=_ztjF86T0kNUDHkBtRyoXJPeM02qt0cCmQqv76B9lUE,4106
1624
+ vllm/v1/sample/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1625
+ vllm/v1/sample/metadata.py,sha256=jLeOuEJuWBJhgcy9TBL2gfjFj2DaJLWk-zPXARUEbsI,1142
1626
+ vllm/v1/sample/rejection_sampler.py,sha256=HsXUfHQy4oqAurvKLVU-GH3VoMlpqHVftxG3AYRvY1I,31019
1627
+ vllm/v1/sample/sampler.py,sha256=H0SOGJZvXIcnoSR7npHY6-j_tjvTiR2uXA5reu8cAVs,12583
1628
+ vllm/v1/sample/logits_processor/__init__.py,sha256=Hs6S01p-p_Xo-LcG5ihCwwGjqypt_8d_TEFnNLNfbIU,12047
1629
+ vllm/v1/sample/logits_processor/builtin.py,sha256=ejN7QaSXMarG07G5rVPwCZ-MbYua3ji6JbnjErnz1x8,10323
1630
+ vllm/v1/sample/logits_processor/interface.py,sha256=p6dGdoKdK94lIUv6RktdOjSHP8adIPNbL4lHxXDfC14,3218
1631
+ vllm/v1/sample/logits_processor/state.py,sha256=Fk_xGySqz7y2MiAi8hL0Q95DNXWelyu5E4XB-pD0d4E,5666
1632
+ vllm/v1/sample/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1633
+ vllm/v1/sample/ops/bad_words.py,sha256=DkYFXZtp1GOS2A8jNHX9M5qC_XNIMLXJpWzsYCYKHN8,1824
1634
+ vllm/v1/sample/ops/logprobs.py,sha256=krdqPu-zZQChtxbssdvIQtm49l4EckUTljJNVSxZfjk,942
1635
+ vllm/v1/sample/ops/penalties.py,sha256=OOrkMB8o3sFEbYjnCq8fvTbT0EEdL7Zn2U1Euf44CjM,1929
1636
+ vllm/v1/sample/ops/topk_topp_sampler.py,sha256=uwPKRHEUpT24chBjxtb0S37r7DL6i_3L8AmgXaWSC-g,14808
1637
+ vllm/v1/sample/tpu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1638
+ vllm/v1/sample/tpu/metadata.py,sha256=-bfn1jLwhVOguzItVzMr44WzBKIvbhozwBZOLTKK8gQ,4624
1639
+ vllm/v1/sample/tpu/sampler.py,sha256=cLhsAU4ZFBJIgpP4915fqr4Cj3IBNVRPgCLrJsJCe6M,7723
1640
+ vllm/v1/spec_decode/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1641
+ vllm/v1/spec_decode/eagle.py,sha256=41Nk8mk0VK31Y3oRtCd-Ea8t2paq5w0xMtyohChfQDY,59069
1642
+ vllm/v1/spec_decode/medusa.py,sha256=DLtgS2e4nxeN4FR3f9jEa7UKNZfuYk0WXDVuMBh55Js,2457
1643
+ vllm/v1/spec_decode/metadata.py,sha256=pmlkh7PIgjwRn2Ad6BUENBve_v6Vuv5nPB9XCrICjag,2353
1644
+ vllm/v1/spec_decode/metrics.py,sha256=KZ4k_OZ5hyJFc9EciPxjEXJCTDWG6BuT9369H0VANxI,7867
1645
+ vllm/v1/spec_decode/ngram_proposer.py,sha256=gt0-XdvMAbW6EXXSInX6lSn9tOFsaav0TBNoGcRyxSI,10802
1646
+ vllm/v1/spec_decode/suffix_decoding.py,sha256=wDpZxnzTTG_sAkfJgGstjwE_KKHLsu7sP7O_ir4r_YY,4240
1647
+ vllm/v1/spec_decode/utils.py,sha256=cHniVrt7mHUQT8oniUcmNpfF4ETH4ZJdIVKK_B_WeGE,4743
1648
+ vllm/v1/structured_output/__init__.py,sha256=P3RtkpsBWIR6m7vLIvTeHuBJxsHYpGKNw_XbSnBGXdk,14663
1649
+ vllm/v1/structured_output/backend_guidance.py,sha256=q7w2HaFbWraY_UG7pnOTq0aQg9ryY6zXgMICvJHRdbg,9845
1650
+ vllm/v1/structured_output/backend_lm_format_enforcer.py,sha256=Srnwxs9RmrtdxO2JL1PkwDOAczjrfZsA5eHh-uuAEH4,6307
1651
+ vllm/v1/structured_output/backend_outlines.py,sha256=e4MIkyIQk6oiKL5cdCJQsK7ZmM0QzKWgp31qLM5W8aA,11748
1652
+ vllm/v1/structured_output/backend_types.py,sha256=71Pfd9VOLNCoM8oyRiG2AFBNbIGrGuRwbo6sC0XqrRQ,3809
1653
+ vllm/v1/structured_output/backend_xgrammar.py,sha256=wLQxqJ7XHzDXewfcRjXgcSXLcqM3ZlxBn4VdQFTHgx8,13732
1654
+ vllm/v1/structured_output/request.py,sha256=z8IQSazynk-XhbgTZC6yi-D9ccjPLiemWXu36-fs6k8,3254
1655
+ vllm/v1/structured_output/utils.py,sha256=Q65uK5vK0qYqk2D2QJocfb7fyJzoS3ktOMJsgeAEZDM,16657
1656
+ vllm/v1/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1657
+ vllm/v1/worker/block_table.py,sha256=-OQlfV1ziXOrxorxyrRA5nngHhZALaOq7LN2jscDJRE,13178
1658
+ vllm/v1/worker/cp_utils.py,sha256=2Ha8RWEizPq9crrYTlxuBDFUOwuSxkm89xdGK8zpGzg,1925
1659
+ vllm/v1/worker/cpu_model_runner.py,sha256=Z4ltdu0avYcshrT5RecZn_fGm0aeQA9zvF2his8jQfA,4195
1660
+ vllm/v1/worker/cpu_worker.py,sha256=WVI7zPAOC3kMDQtwKp9TzunVkTrJPLhlGop_8qyQJAI,7549
1661
+ vllm/v1/worker/dp_utils.py,sha256=HF6MZ5bGffPbVV7rsyfasF18J3yqkj6PSp27NBMo2Eo,8851
1662
+ vllm/v1/worker/ec_connector_model_runner_mixin.py,sha256=pzXYwNrGRuuRZUtYfIiRcAz5u8OG0t_n5YyI94UIR2c,2943
1663
+ vllm/v1/worker/gpu_input_batch.py,sha256=-uj3f2MPJyH8nNKuP-YdS2IMxhXN1T4Y6ZpnvMNvqlo,43313
1664
+ vllm/v1/worker/gpu_model_runner.py,sha256=fqqet4y5n59EPQK63iCHgjn-n8biOMMyvVzHagBBGoU,252941
1665
+ vllm/v1/worker/gpu_ubatch_wrapper.py,sha256=92VcAiiCuBA65SaFzgy4wOVvkIo5-WlV8LRVl22gKbw,18311
1666
+ vllm/v1/worker/gpu_worker.py,sha256=6zO18r04msMnhXcrpZblrs-qrsKB4-39gEuZO0sddJU,40298
1667
+ vllm/v1/worker/kv_connector_model_runner_mixin.py,sha256=4SJ1JPi7fOg_01o4Hyi7h8cwcGY3mlapr08HzzilykY,11726
1668
+ vllm/v1/worker/lora_model_runner_mixin.py,sha256=4Gxu1wE2viR3npJEPZFcmxjnK4PIIoi12mwkseyDRVI,7790
1669
+ vllm/v1/worker/tpu_input_batch.py,sha256=Cc9z4nxam3SR1QSIPEkPYsAJ1e2ins8oLL5FcppSAyU,24177
1670
+ vllm/v1/worker/tpu_worker.py,sha256=t1JSobXhucdP2rQFgrfgJM1Pyl_lOkE-mO8Og_zjfAw,540
1671
+ vllm/v1/worker/ubatch_utils.py,sha256=WiUGrenTCuXsYjmPoxPkLy8OA9rbMGentGyxJOcmKlg,3703
1672
+ vllm/v1/worker/ubatching.py,sha256=BcVxfkpw-5mUSlvK3O-PHMhyD2RI1hsPSYza13vCrCQ,8425
1673
+ vllm/v1/worker/utils.py,sha256=wHWKZqEF5y54_8z8C6J-Gm5bIPY1OXKLy5G3ZRL1bbE,14838
1674
+ vllm/v1/worker/worker_base.py,sha256=3o8afwjyBMNpt3ZhVka2jbNHEBOIZ1jC68XZ5y89M2Q,14126
1675
+ vllm/v1/worker/workspace.py,sha256=ijCEREkVlRhmeLZTCmc7wgaRjQA6mn5WURakvZgKtcg,9133
1676
+ vllm/v1/worker/xpu_model_runner.py,sha256=2U3jepUQpj99KvOkLQf6ok0je8_veXET6ntuUS8gNHk,1251
1677
+ vllm/v1/worker/xpu_worker.py,sha256=xTC_ip7xqcqH2Vm6dGi9iABQm7EI-0CYscK82eF4478,7097
1678
+ vllm/v1/worker/gpu/README.md,sha256=1H_fnHpMus5c95vNXWX5-Ryx3UkQiRwY_b5WDd0D8Ww,181
1679
+ vllm/v1/worker/gpu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1680
+ vllm/v1/worker/gpu/async_utils.py,sha256=Ujtc0V50CXr2Po1-GDpycnqSaqlI79X6Ox5i1vnIKBw,3832
1681
+ vllm/v1/worker/gpu/attn_utils.py,sha256=UCWIOEnU7sxhM3NgYKbFGdtj8vwi3WcaSSIUvy5dXP4,6944
1682
+ vllm/v1/worker/gpu/block_table.py,sha256=9LtUSiCabIxYMGnVNESQs96_LZtiZ3PMkz4436Chgog,8330
1683
+ vllm/v1/worker/gpu/buffer_utils.py,sha256=G2HEV9AkMC-IL_WTSer6gaWnGqGzhAlIhd3zDpZRNKs,7845
1684
+ vllm/v1/worker/gpu/cudagraph_utils.py,sha256=K11Xw7tHmiVGu5ACx2aH6nPieRUFcKpS5waOnysCAQY,9059
1685
+ vllm/v1/worker/gpu/dp_utils.py,sha256=tFuN8YrGpMRaX6wrsJ4j1trxM8dE9Fek2G60a8ovheY,920
1686
+ vllm/v1/worker/gpu/input_batch.py,sha256=vPXk26A89VhqizDJlP2QWH_65V_Rjeps2G-Ue83Trrw,16813
1687
+ vllm/v1/worker/gpu/model_runner.py,sha256=tgjMGm7Gl8MazgHA_e9WWLwXl8GXzwu8sP4chYE9RLQ,40330
1688
+ vllm/v1/worker/gpu/states.py,sha256=u40eW9oM00MniPeHdLg69ueKELYk5JR6gINkMf9y1-M,10523
1689
+ vllm/v1/worker/gpu/structured_outputs.py,sha256=bxH7q8TfizBvK8C3_fFRkeFrTCGj4ofUxD9sR9VtYNM,3375
1690
+ vllm/v1/worker/gpu/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1691
+ vllm/v1/worker/gpu/metrics/logits.py,sha256=6gWNdRCgd6Vfisfkw9WWUINGJE6QjLNyhl1xWfYu3Ik,1205
1692
+ vllm/v1/worker/gpu/mm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1693
+ vllm/v1/worker/gpu/mm/mrope_utils.py,sha256=H5eyUJHva3IMQjXuJHc7PFxE9HxksaOn6v4AHvGem1k,4229
1694
+ vllm/v1/worker/gpu/sample/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1695
+ vllm/v1/worker/gpu/sample/gumbel.py,sha256=00ehDE_nDEIi1paY4_cVw4JqBwLlm7EgB-NkvYuOVqQ,3200
1696
+ vllm/v1/worker/gpu/sample/logit_bias.py,sha256=2_yeY12cCFpai9Y855u-b68_cUMCHTJZ7Cqtq-9Z5gw,8953
1697
+ vllm/v1/worker/gpu/sample/logprob.py,sha256=32kWDLJyz3ct_mHKyp6vhzeuICtXmqs7E2deqJZhGkg,5227
1698
+ vllm/v1/worker/gpu/sample/metadata.py,sha256=HEGxOfImLKxcTxQFS181_jf_Yph9J8-zoAAy-929dGs,2950
1699
+ vllm/v1/worker/gpu/sample/min_p.py,sha256=lVLfsmfQlxk4qKLGf7c8cDvdObAdolGUQ52EbsC64OM,1670
1700
+ vllm/v1/worker/gpu/sample/output.py,sha256=Uzj6Lujb5LEswYwYUsTmJ9HkDwJ-QoV1s1uyH4VZ0CE,349
1701
+ vllm/v1/worker/gpu/sample/penalties.py,sha256=OAx0z1MmFKYANze5Cedu2DcrdCIsOBnmfpFoyshLc1k,5413
1702
+ vllm/v1/worker/gpu/sample/sampler.py,sha256=KlTm4OvpyYzL6AViv0iM0rYn4rGyqLGCsVsSePA9iYk,3428
1703
+ vllm/v1/worker/gpu/spec_decode/__init__.py,sha256=Ca2Xgzk8ZBRa5sae1pFSzBJR9DBk7vWIPgUWsFgILUI,584
1704
+ vllm/v1/worker/gpu/spec_decode/eagle.py,sha256=3MKCIHgRIJOqfWClGHDUTolI2nMyNb3XNcb0S4KJRl0,20365
1705
+ vllm/v1/worker/gpu/spec_decode/eagle_cudagraph.py,sha256=J-m9JoDhouw0AwTafwEC8aI0NnXfqLBXu2hMU2Pl2Y4,4044
1706
+ vllm/v1/worker/gpu/spec_decode/rejection_sample.py,sha256=316CS-i86IEDzWt6y6bEhwQkb4VviFQfqaXDTAUuCPg,2218
1707
+ vllm/vllm_flash_attn/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
1708
+ vllm_cpu_avx512bf16-0.14.0.dist-info/METADATA,sha256=M3mtUp443cWsAcXHWuQvrAm14AY_-nlwwrtILIooOtk,16554
1709
+ vllm_cpu_avx512bf16-0.14.0.dist-info/WHEEL,sha256=AmG_ydfEhn71K4nKKHCuRW9NGRrQB_mEM67PI6NJMuY,113
1710
+ vllm_cpu_avx512bf16-0.14.0.dist-info/entry_points.txt,sha256=ErfiCUEEMrGDD3jBwf8c54AolBCFv7qrc8Ix9iqzzfs,184
1711
+ vllm_cpu_avx512bf16-0.14.0.dist-info/top_level.txt,sha256=fAgb8Pt4zQoKTUA3ZnKEIgcjh0L97_dwEjYDTL5MEEo,5
1712
+ vllm_cpu_avx512bf16-0.14.0.dist-info/RECORD,,