sglang 0.5.3__tar.gz → 0.5.3.post1__tar.gz

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 (1037) hide show
  1. {sglang-0.5.3/sglang.egg-info → sglang-0.5.3.post1}/PKG-INFO +4 -4
  2. {sglang-0.5.3 → sglang-0.5.3.post1}/pyproject.toml +4 -4
  3. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/bench_one_batch.py +0 -2
  4. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/bench_serving.py +224 -127
  5. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/compile_deep_gemm.py +3 -0
  6. sglang-0.5.3.post1/sglang/launch_server.py +16 -0
  7. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/__init__.py +2 -0
  8. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/falcon_h1.py +12 -58
  9. sglang-0.5.3.post1/sglang/srt/configs/mamba_utils.py +117 -0
  10. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/model_config.py +68 -31
  11. sglang-0.5.3.post1/sglang/srt/configs/nemotron_h.py +286 -0
  12. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/qwen3_next.py +11 -43
  13. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/decode.py +7 -18
  14. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/decode_kvcache_offload_manager.py +1 -1
  15. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/nixl/conn.py +55 -23
  16. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/prefill.py +17 -32
  17. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/engine.py +2 -2
  18. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/grpc_request_manager.py +10 -23
  19. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/grpc_server.py +220 -80
  20. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/http_server.py +49 -1
  21. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/protocol.py +159 -31
  22. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_chat.py +13 -71
  23. sglang-0.5.3.post1/sglang/srt/entrypoints/openai/serving_tokenize.py +144 -0
  24. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/environ.py +4 -0
  25. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/function_call_parser.py +8 -6
  26. sglang-0.5.3.post1/sglang/srt/grpc/sglang_scheduler_pb2.py +119 -0
  27. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/grpc/sglang_scheduler_pb2.pyi +64 -6
  28. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/grpc/sglang_scheduler_pb2_grpc.py +88 -0
  29. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/attention_registry.py +31 -22
  30. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/layernorm_gated.py +47 -30
  31. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/flashattention_backend.py +0 -1
  32. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/flashinfer_backend.py +223 -6
  33. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/flashinfer_mla_backend.py +1 -1
  34. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/hybrid_linear_attn_backend.py +165 -59
  35. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/causal_conv1d.py +1 -1
  36. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/causal_conv1d_triton.py +9 -4
  37. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/mamba.py +189 -241
  38. sglang-0.5.3.post1/sglang/srt/layers/attention/mamba/mamba2_metadata.py +211 -0
  39. sglang-0.5.3.post1/sglang/srt/layers/attention/mamba/mixer2_rms_norm_gated.py +120 -0
  40. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/ssd_bmm.py +0 -50
  41. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/ssd_chunk_scan.py +0 -60
  42. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/ssd_chunk_state.py +0 -111
  43. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/ssd_state_passing.py +0 -11
  44. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_backend.py +1 -1
  45. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/logits_processor.py +136 -6
  46. sglang-0.5.3.post1/sglang/srt/layers/modelopt_utils.py +11 -0
  47. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/cutlass_w4a8_moe.py +18 -21
  48. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/ep_moe/kernels.py +31 -452
  49. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/ep_moe/layer.py +8 -286
  50. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/layer.py +6 -11
  51. sglang-0.5.3.post1/sglang/srt/layers/moe/moe_runner/deep_gemm.py +304 -0
  52. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/moe_runner/runner.py +3 -0
  53. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/utils.py +7 -1
  54. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/__init__.py +1 -1
  55. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/fp8.py +84 -18
  56. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/modelopt_quant.py +1 -1
  57. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/quark.py +3 -1
  58. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/w4afp8.py +2 -16
  59. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/lora_manager.py +0 -8
  60. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/overlap_utils.py +18 -16
  61. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/schedule_batch.py +119 -90
  62. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/schedule_policy.py +1 -1
  63. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler.py +213 -126
  64. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_metrics_mixin.py +1 -1
  65. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_output_processor_mixin.py +180 -86
  66. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/tokenizer_manager.py +270 -53
  67. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/tp_worker.py +39 -28
  68. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/allocator.py +7 -2
  69. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/chunk_cache.py +1 -1
  70. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/memory_pool.py +162 -68
  71. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/radix_cache.py +8 -3
  72. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/swa_radix_cache.py +70 -14
  73. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_executor/cuda_graph_runner.py +1 -1
  74. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_executor/forward_batch_info.py +4 -18
  75. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_executor/model_runner.py +55 -51
  76. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_loader/__init__.py +1 -1
  77. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_loader/loader.py +187 -6
  78. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_loader/weight_utils.py +3 -0
  79. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/falcon_h1.py +11 -9
  80. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma3_mm.py +16 -0
  81. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/grok.py +5 -13
  82. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mixtral.py +1 -3
  83. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mllama4.py +11 -1
  84. sglang-0.5.3.post1/sglang/srt/models/nemotron_h.py +514 -0
  85. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/utils.py +5 -1
  86. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/sampling_batch_info.py +11 -9
  87. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/server_args.py +100 -33
  88. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/eagle_worker.py +11 -13
  89. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/ngram_worker.py +12 -11
  90. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/spec_utils.py +0 -1
  91. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/two_batch_overlap.py +1 -0
  92. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/common.py +18 -0
  93. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/hf_transformers_utils.py +2 -0
  94. sglang-0.5.3.post1/sglang/test/longbench_v2/__init__.py +1 -0
  95. sglang-0.5.3.post1/sglang/test/longbench_v2/test_longbench_v2_eval.py +238 -0
  96. sglang-0.5.3.post1/sglang/test/longbench_v2/validate_longbench_v2.py +337 -0
  97. sglang-0.5.3.post1/sglang/test/longbench_v2/validate_longbench_v2_standalone.py +306 -0
  98. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/run_eval.py +40 -0
  99. sglang-0.5.3.post1/sglang/test/simple_eval_longbench_v2.py +332 -0
  100. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_cutlass_w4a8_moe.py +9 -19
  101. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_deterministic.py +18 -2
  102. sglang-0.5.3.post1/sglang/test/test_deterministic_utils.py +81 -0
  103. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_disaggregation_utils.py +63 -0
  104. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_utils.py +32 -11
  105. sglang-0.5.3.post1/sglang/version.py +1 -0
  106. {sglang-0.5.3 → sglang-0.5.3.post1/sglang.egg-info}/PKG-INFO +4 -4
  107. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang.egg-info/SOURCES.txt +16 -5
  108. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang.egg-info/requires.txt +3 -3
  109. sglang-0.5.3/sglang/launch_server.py +0 -30
  110. sglang-0.5.3/sglang/srt/grpc/sglang_scheduler_pb2.py +0 -111
  111. sglang-0.5.3/sglang/srt/layers/attention/mamba/mamba_utils.py +0 -81
  112. sglang-0.5.3/sglang/srt/managers/tp_worker_overlap_thread.py +0 -311
  113. sglang-0.5.3/sglang/test/test_block_fp8_ep.py +0 -358
  114. sglang-0.5.3/sglang/version.py +0 -1
  115. {sglang-0.5.3 → sglang-0.5.3.post1}/LICENSE +0 -0
  116. {sglang-0.5.3 → sglang-0.5.3.post1}/README.md +0 -0
  117. {sglang-0.5.3 → sglang-0.5.3.post1}/setup.cfg +0 -0
  118. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/__init__.py +0 -0
  119. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/bench_offline_throughput.py +0 -0
  120. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/bench_one_batch_server.py +0 -0
  121. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/check_env.py +0 -0
  122. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/eval/llama3_eval.py +0 -0
  123. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/eval/loogle_eval.py +0 -0
  124. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/global_config.py +0 -0
  125. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/api.py +0 -0
  126. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/anthropic.py +0 -0
  127. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/base_backend.py +0 -0
  128. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/litellm.py +0 -0
  129. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/openai.py +0 -0
  130. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/runtime_endpoint.py +0 -0
  131. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/backend/vertexai.py +0 -0
  132. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/chat_template.py +0 -0
  133. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/choices.py +0 -0
  134. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/compiler.py +0 -0
  135. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/interpreter.py +0 -0
  136. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/ir.py +0 -0
  137. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/lang/tracer.py +0 -0
  138. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/profiler.py +0 -0
  139. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/_custom_ops.py +0 -0
  140. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/aio_rwlock.py +0 -0
  141. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/batch_invariant_ops/__init__.py +0 -0
  142. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/batch_invariant_ops/batch_invariant_ops.py +0 -0
  143. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/bench_utils.py +0 -0
  144. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/chatglm.py +0 -0
  145. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/dbrx.py +0 -0
  146. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/deepseekvl2.py +0 -0
  147. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/device_config.py +0 -0
  148. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/dots_ocr.py +0 -0
  149. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/dots_vlm.py +0 -0
  150. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/exaone.py +0 -0
  151. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/internvl.py +0 -0
  152. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/janus_pro.py +0 -0
  153. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/kimi_vl.py +0 -0
  154. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/kimi_vl_moonvit.py +0 -0
  155. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/load_config.py +0 -0
  156. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/longcat_flash.py +0 -0
  157. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/qwen3_vl.py +0 -0
  158. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/step3_vl.py +0 -0
  159. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/update_config.py +0 -0
  160. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/configs/utils.py +0 -0
  161. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/__init__.py +0 -0
  162. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/base_connector.py +0 -0
  163. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/redis.py +0 -0
  164. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/remote_instance.py +0 -0
  165. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/s3.py +0 -0
  166. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/serde/__init__.py +0 -0
  167. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/serde/safe_serde.py +0 -0
  168. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/serde/serde.py +0 -0
  169. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/connector/utils.py +0 -0
  170. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constants.py +0 -0
  171. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/base_grammar_backend.py +0 -0
  172. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/llguidance_backend.py +0 -0
  173. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/outlines_backend.py +0 -0
  174. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/outlines_jump_forward.py +0 -0
  175. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/reasoner_grammar_backend.py +0 -0
  176. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/triton_ops/bitmask_ops.py +0 -0
  177. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/constrained/xgrammar_backend.py +0 -0
  178. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/custom_op.py +0 -0
  179. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/debug_utils/__init__.py +0 -0
  180. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/debug_utils/dump_comparator.py +0 -0
  181. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/debug_utils/dump_loader.py +0 -0
  182. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/debug_utils/dumper.py +0 -0
  183. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/debug_utils/text_comparator.py +0 -0
  184. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/ascend/__init__.py +0 -0
  185. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/ascend/conn.py +0 -0
  186. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/ascend/transfer_engine.py +0 -0
  187. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/base/__init__.py +0 -0
  188. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/base/conn.py +0 -0
  189. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/common/__init__.py +0 -0
  190. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/common/conn.py +0 -0
  191. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/common/utils.py +0 -0
  192. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/decode_schedule_batch_mixin.py +0 -0
  193. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/fake/__init__.py +0 -0
  194. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/fake/conn.py +0 -0
  195. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/kv_events.py +0 -0
  196. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/mini_lb.py +0 -0
  197. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/mooncake/__init__.py +0 -0
  198. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/mooncake/conn.py +0 -0
  199. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/mooncake/transfer_engine.py +0 -0
  200. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/nixl/__init__.py +0 -0
  201. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/disaggregation/utils.py +0 -0
  202. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/__init__.py +0 -0
  203. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/communication_op.py +0 -0
  204. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/all_reduce_utils.py +0 -0
  205. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/cuda_wrapper.py +0 -0
  206. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/custom_all_reduce.py +0 -0
  207. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/custom_all_reduce_utils.py +0 -0
  208. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/hpu_communicator.py +0 -0
  209. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/npu_communicator.py +0 -0
  210. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/pymscclpp.py +0 -0
  211. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/pynccl.py +0 -0
  212. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/pynccl_allocator.py +0 -0
  213. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/pynccl_wrapper.py +0 -0
  214. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/quick_all_reduce.py +0 -0
  215. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/shm_broadcast.py +0 -0
  216. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/symm_mem.py +0 -0
  217. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/device_communicators/xpu_communicator.py +0 -0
  218. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/naive_distributed.py +0 -0
  219. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/parallel_state.py +0 -0
  220. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/distributed/utils.py +0 -0
  221. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/EngineBase.py +0 -0
  222. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/context.py +0 -0
  223. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/harmony_utils.py +0 -0
  224. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/http_server_engine.py +0 -0
  225. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/__init__.py +0 -0
  226. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_base.py +0 -0
  227. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_completions.py +0 -0
  228. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_embedding.py +0 -0
  229. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_rerank.py +0 -0
  230. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_responses.py +0 -0
  231. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/serving_score.py +0 -0
  232. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/tool_server.py +0 -0
  233. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/usage_processor.py +0 -0
  234. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/openai/utils.py +0 -0
  235. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/entrypoints/tool.py +0 -0
  236. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/__init__.py +0 -0
  237. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_algorithms/__init__.py +0 -0
  238. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_algorithms/deepseek.py +0 -0
  239. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_algorithms/deepseek_vec.py +0 -0
  240. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_manager.py +0 -0
  241. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_simulator/__init__.py +0 -0
  242. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/eplb_simulator/reader.py +0 -0
  243. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/expert_distribution.py +0 -0
  244. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/expert_location.py +0 -0
  245. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/expert_location_dispatch.py +0 -0
  246. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/eplb/expert_location_updater.py +0 -0
  247. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/base_format_detector.py +0 -0
  248. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/core_types.py +0 -0
  249. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/deepseekv31_detector.py +0 -0
  250. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/deepseekv3_detector.py +0 -0
  251. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/ebnf_composer.py +0 -0
  252. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/glm4_moe_detector.py +0 -0
  253. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/gpt_oss_detector.py +0 -0
  254. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/json_array_parser.py +0 -0
  255. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/kimik2_detector.py +0 -0
  256. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/llama32_detector.py +0 -0
  257. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/mistral_detector.py +0 -0
  258. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/pythonic_detector.py +0 -0
  259. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/qwen25_detector.py +0 -0
  260. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/qwen3_coder_detector.py +0 -0
  261. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/step3_detector.py +0 -0
  262. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/function_call/utils.py +0 -0
  263. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/grpc/__init__.py +0 -0
  264. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/grpc/compile_proto.py +0 -0
  265. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/host_shared_memory.py +0 -0
  266. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/activation.py +0 -0
  267. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/amx_utils.py +0 -0
  268. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/aiter_backend.py +0 -0
  269. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/ascend_backend.py +0 -0
  270. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/base_attn_backend.py +0 -0
  271. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/cutlass_mla_backend.py +0 -0
  272. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/double_sparsity_backend.py +0 -0
  273. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/dual_chunk_flashattention_backend.py +0 -0
  274. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/chunk.py +0 -0
  275. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/chunk_delta_h.py +0 -0
  276. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/chunk_o.py +0 -0
  277. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/chunk_scaled_dot_kkt.py +0 -0
  278. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/cumsum.py +0 -0
  279. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/fused_recurrent.py +0 -0
  280. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/fused_sigmoid_gating_recurrent.py +0 -0
  281. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/index.py +0 -0
  282. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/l2norm.py +0 -0
  283. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/op.py +0 -0
  284. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/solve_tril.py +0 -0
  285. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/utils.py +0 -0
  286. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/fla/wy_fast.py +0 -0
  287. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/flashmla_backend.py +0 -0
  288. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/hybrid_attn_backend.py +0 -0
  289. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/intel_amx_backend.py +0 -0
  290. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/__init__.py +0 -0
  291. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/layernorm_gated.py +0 -0
  292. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/mamba_ssm.py +0 -0
  293. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/mamba/ops/ssd_combined.py +0 -0
  294. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/merge_state.py +0 -0
  295. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/npu_ops/mla_preprocess.py +0 -0
  296. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/dequant_k_cache.py +0 -0
  297. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/index_buf_accessor.py +0 -0
  298. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/nsa_indexer.py +0 -0
  299. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/quant_k_cache.py +0 -0
  300. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/tilelang_kernel.py +0 -0
  301. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/transform_index.py +0 -0
  302. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa/utils.py +0 -0
  303. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/nsa_backend.py +0 -0
  304. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/tbo_backend.py +0 -0
  305. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/torch_flex_backend.py +0 -0
  306. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/torch_native_backend.py +0 -0
  307. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/decode_attention.py +0 -0
  308. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/double_sparsity_attention.py +0 -0
  309. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/extend_attention.py +0 -0
  310. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/merge_state.py +0 -0
  311. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/prefill_attention.py +0 -0
  312. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/triton_ops/rocm_mla_decode_rope.py +0 -0
  313. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/trtllm_mha_backend.py +0 -0
  314. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/trtllm_mla_backend.py +0 -0
  315. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/utils.py +0 -0
  316. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/vision.py +0 -0
  317. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/vision_utils.py +0 -0
  318. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/wave_backend.py +0 -0
  319. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/wave_ops/decode_attention.py +0 -0
  320. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/wave_ops/extend_attention.py +0 -0
  321. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/attention/wave_ops/prefill_attention.py +0 -0
  322. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/communicator.py +0 -0
  323. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/dp_attention.py +0 -0
  324. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/elementwise.py +0 -0
  325. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/flashinfer_comm_fusion.py +0 -0
  326. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/layernorm.py +0 -0
  327. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/linear.py +0 -0
  328. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/model_parallel.py +0 -0
  329. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/__init__.py +0 -0
  330. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/cutlass_moe.py +0 -0
  331. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/cutlass_moe_params.py +0 -0
  332. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/ep_moe/__init__.py +0 -0
  333. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/flashinfer_cutedsl_moe.py +0 -0
  334. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_native.py +0 -0
  335. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/__init__.py +0 -0
  336. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
  337. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  338. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
  339. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  340. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
  341. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +0 -0
  342. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  343. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
  344. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  345. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
  346. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  347. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=144,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  348. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  349. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1024,device_name=NVIDIA_H200.json +0 -0
  350. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json +0 -0
  351. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  352. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  353. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
  354. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  355. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
  356. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  357. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  358. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  359. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  360. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
  361. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +0 -0
  362. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  363. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
  364. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  365. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  366. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +0 -0
  367. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  368. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +0 -0
  369. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  370. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
  371. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=20,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  372. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=24,N=1024,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  373. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  374. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json +0 -0
  375. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  376. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
  377. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  378. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_H20,block_shape=[128, 128].json +0 -0
  379. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  380. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  381. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  382. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  383. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  384. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  385. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  386. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  387. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
  388. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=64,device_name=NVIDIA_L20,dtype=int8_w8a8.json +0 -0
  389. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=256,N=64,device_name=NVIDIA_L40S,dtype=int8_w8a8.json +0 -0
  390. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  391. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  392. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
  393. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  394. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  395. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  396. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=1280,device_name=NVIDIA_H200.json +0 -0
  397. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  398. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  399. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=2560,device_name=NVIDIA_H200.json +0 -0
  400. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  401. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  402. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  403. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=320,device_name=NVIDIA_H200.json +0 -0
  404. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  405. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  406. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
  407. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json +0 -0
  408. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  409. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  410. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  411. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=64,N=640,device_name=NVIDIA_H200.json +0 -0
  412. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=AMD_Instinct_MI300X.json +0 -0
  413. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=AMD_Instinct_MI325X.json +0 -0
  414. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=AMD_Radeon_Graphics.json +0 -0
  415. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  416. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  417. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=14336,device_name=NVIDIA_H200.json +0 -0
  418. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=AMD_Instinct_MI300X.json +0 -0
  419. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=AMD_Instinct_MI325X.json +0 -0
  420. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=AMD_Radeon_Graphics.json +0 -0
  421. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json +0 -0
  422. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  423. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  424. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  425. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=1792,device_name=NVIDIA_H200.json +0 -0
  426. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  427. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  428. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  429. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  430. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=2048,device_name=NVIDIA_H200.json +0 -0
  431. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=AMD_Instinct_MI300X.json +0 -0
  432. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=AMD_Instinct_MI325X.json +0 -0
  433. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=AMD_Radeon_Graphics.json +0 -0
  434. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json +0 -0
  435. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  436. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json +0 -0
  437. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  438. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  439. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  440. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_H200.json +0 -0
  441. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=3584,device_name=NVIDIA_L40S.json +0 -0
  442. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +0 -0
  443. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +0 -0
  444. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json +0 -0
  445. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  446. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  447. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  448. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  449. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=4096,device_name=NVIDIA_H200.json +0 -0
  450. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=AMD_Instinct_MI300X.json +0 -0
  451. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=AMD_Instinct_MI325X.json +0 -0
  452. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=AMD_Radeon_Graphics.json +0 -0
  453. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  454. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  455. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  456. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  457. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=7168,device_name=NVIDIA_H200.json +0 -0
  458. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +0 -0
  459. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +0 -0
  460. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8.json +0 -0
  461. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +0 -0
  462. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_1_0/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  463. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
  464. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  465. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_H20.json +0 -0
  466. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=192,device_name=NVIDIA_H200.json +0 -0
  467. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  468. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  469. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H20.json +0 -0
  470. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  471. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=384,device_name=NVIDIA_H200.json +0 -0
  472. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  473. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
  474. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  475. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  476. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H20.json +0 -0
  477. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  478. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=768,device_name=NVIDIA_H200.json +0 -0
  479. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=128,N=96,device_name=NVIDIA_H20.json +0 -0
  480. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=129,N=352,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
  481. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=160,N=320,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
  482. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=161,N=192,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
  483. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  484. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  485. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  486. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  487. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=257,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  488. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
  489. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  490. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  491. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=264,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  492. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +0 -0
  493. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  494. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  495. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=272,N=64,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
  496. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=288,N=64,device_name=NVIDIA_A800-SXM4-80GB.json +0 -0
  497. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_2_0/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  498. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_0/E=16,N=1024,device_name=NVIDIA_B200.json +0 -0
  499. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=352,device_name=NVIDIA_RTX_6000_Ada_Generation,dtype=fp8_w8a8.json +0 -0
  500. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  501. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  502. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  503. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=128,N=768,device_name=NVIDIA_H20.json +0 -0
  504. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  505. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=320,device_name=NVIDIA_H20-3e.json +0 -0
  506. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +0 -0
  507. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=160,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  508. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  509. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  510. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  511. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  512. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  513. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=257,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  514. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  515. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  516. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=384,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  517. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=385,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  518. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=385,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  519. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_3_1/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  520. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=128,N=352,device_name=NVIDIA_RTX_5880_Ada_Generation,dtype=fp8_w8a8.json +0 -0
  521. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=128,N=384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  522. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=352,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +0 -0
  523. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=352,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Max-Q_Workstation_Edition,dtype=fp8_w8a8.json +0 -0
  524. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=129,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +0 -0
  525. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=161,N=384,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Max-Q_Workstation_Edition,dtype=fp8_w8a8.json +0 -0
  526. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  527. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=256,device_name=NVIDIA_H800,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  528. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=256,N=512,device_name=NVIDIA_H20.json +0 -0
  529. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  530. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=257,N=64,device_name=NVIDIA_A100-SXM4-80GB.json +0 -0
  531. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  532. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  533. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H20-3e.json +0 -0
  534. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H200.json +0 -0
  535. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=128,device_name=NVIDIA_H800,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  536. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=256,device_name=NVIDIA_B200.json +0 -0
  537. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=256,device_name=NVIDIA_H20-3e.json +0 -0
  538. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=256,device_name=NVIDIA_H200.json +0 -0
  539. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=64,device_name=NVIDIA_H100_80GB_HBM3.json +0 -0
  540. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/configs/triton_3_4_0/E=512,N=64,device_name=NVIDIA_H200.json +0 -0
  541. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/fused_moe.py +0 -0
  542. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_config.py +0 -0
  543. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/fused_moe_triton_kernels.py +0 -0
  544. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/moe_align_block_size.py +0 -0
  545. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/fused_moe_triton/triton_kernels_moe.py +0 -0
  546. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/moe_runner/__init__.py +0 -0
  547. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/moe_runner/base.py +0 -0
  548. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/moe_runner/triton.py +0 -0
  549. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/rocm_moe_utils.py +0 -0
  550. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/router.py +0 -0
  551. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/token_dispatcher/__init__.py +0 -0
  552. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/token_dispatcher/base.py +0 -0
  553. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/token_dispatcher/deepep.py +0 -0
  554. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/token_dispatcher/standard.py +0 -0
  555. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/moe/topk.py +0 -0
  556. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/multimodal.py +0 -0
  557. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/parameter.py +0 -0
  558. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/pooler.py +0 -0
  559. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/awq.py +0 -0
  560. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/awq_triton.py +0 -0
  561. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/base_config.py +0 -0
  562. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/blockwise_int8.py +0 -0
  563. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/__init__.py +0 -0
  564. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/compressed_tensors.py +0 -0
  565. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/compressed_tensors_moe.py +0 -0
  566. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/schemes/__init__.py +0 -0
  567. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py +0 -0
  568. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py +0 -0
  569. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +0 -0
  570. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py +0 -0
  571. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/compressed_tensors/utils.py +0 -0
  572. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  573. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  574. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  575. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  576. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  577. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  578. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  579. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  580. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  581. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  582. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  583. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  584. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  585. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  586. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  587. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  588. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  589. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  590. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  591. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  592. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  593. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  594. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  595. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  596. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  597. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  598. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  599. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  600. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  601. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  602. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  603. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  604. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  605. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  606. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  607. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  608. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  609. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  610. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  611. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  612. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  613. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  614. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  615. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  616. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  617. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  618. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  619. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  620. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  621. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  622. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  623. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  624. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  625. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  626. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  627. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  628. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  629. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  630. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  631. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  632. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  633. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  634. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  635. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  636. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  637. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  638. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  639. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  640. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  641. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  642. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  643. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  644. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  645. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  646. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  647. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  648. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  649. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  650. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  651. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  652. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  653. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  654. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  655. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  656. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  657. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  658. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  659. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  660. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  661. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  662. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  663. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  664. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  665. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  666. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  667. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  668. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  669. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  670. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  671. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  672. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  673. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  674. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  675. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  676. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  677. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  678. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  679. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  680. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  681. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  682. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  683. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  684. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  685. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  686. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  687. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  688. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  689. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  690. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  691. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  692. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  693. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  694. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  695. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  696. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  697. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  698. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  699. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  700. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  701. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  702. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  703. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  704. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  705. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  706. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  707. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  708. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  709. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  710. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  711. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  712. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  713. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  714. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  715. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  716. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  717. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  718. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  719. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  720. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=AMD_Radeon_Graphics,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  721. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  722. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128, 128].json +0 -0
  723. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128, 128].json +0 -0
  724. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/deep_gemm_wrapper/__init__.py +0 -0
  725. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/deep_gemm_wrapper/compile_utils.py +0 -0
  726. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/deep_gemm_wrapper/configurer.py +0 -0
  727. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/deep_gemm_wrapper/entrypoint.py +0 -0
  728. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/fp8_kernel.py +0 -0
  729. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/fp8_utils.py +0 -0
  730. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/fpgemm_fp8.py +0 -0
  731. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/gptq.py +0 -0
  732. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/int8_kernel.py +0 -0
  733. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/int8_utils.py +0 -0
  734. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/kv_cache.py +0 -0
  735. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/marlin_utils.py +0 -0
  736. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/marlin_utils_fp8.py +0 -0
  737. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/moe_wna16.py +0 -0
  738. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/mxfp4.py +0 -0
  739. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/mxfp4_tensor.py +0 -0
  740. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/petit.py +0 -0
  741. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/petit_utils.py +0 -0
  742. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/qoq.py +0 -0
  743. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/__init__.py +0 -0
  744. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/quark_moe.py +0 -0
  745. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/schemes/__init__.py +0 -0
  746. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/schemes/quark_scheme.py +0 -0
  747. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py +0 -0
  748. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/quark/utils.py +0 -0
  749. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/rocm_mxfp4_utils.py +0 -0
  750. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/unquant.py +0 -0
  751. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/utils.py +0 -0
  752. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/w8a8_fp8.py +0 -0
  753. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/quantization/w8a8_int8.py +0 -0
  754. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/radix_attention.py +0 -0
  755. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/rocm_linear_utils.py +0 -0
  756. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/rotary_embedding.py +0 -0
  757. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/sampler.py +0 -0
  758. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/torchao_utils.py +0 -0
  759. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/utils.py +0 -0
  760. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/layers/vocab_parallel_embedding.py +0 -0
  761. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/backend/base_backend.py +0 -0
  762. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/backend/chunked_backend.py +0 -0
  763. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/backend/triton_backend.py +0 -0
  764. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/layers.py +0 -0
  765. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/lora.py +0 -0
  766. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/lora_config.py +0 -0
  767. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/lora_registry.py +0 -0
  768. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/mem_pool.py +0 -0
  769. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/__init__.py +0 -0
  770. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/chunked_sgmv_expand.py +0 -0
  771. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/chunked_sgmv_shrink.py +0 -0
  772. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/gate_up_lora_b.py +0 -0
  773. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/qkv_lora_b.py +0 -0
  774. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/sgemm_lora_a.py +0 -0
  775. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/triton_ops/sgemm_lora_b.py +0 -0
  776. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/lora/utils.py +0 -0
  777. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/async_dynamic_batch_tokenizer.py +0 -0
  778. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/cache_controller.py +0 -0
  779. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/configure_logging.py +0 -0
  780. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/data_parallel_controller.py +0 -0
  781. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/detokenizer_manager.py +0 -0
  782. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/disagg_service.py +0 -0
  783. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/io_struct.py +0 -0
  784. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/mm_utils.py +0 -0
  785. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/multi_tokenizer_mixin.py +0 -0
  786. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/multimodal_processor.py +0 -0
  787. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_input_blocker.py +0 -0
  788. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_profiler_mixin.py +0 -0
  789. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_recv_skipper.py +0 -0
  790. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/scheduler_update_weights_mixin.py +0 -0
  791. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/session_controller.py +0 -0
  792. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/template_manager.py +0 -0
  793. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/tokenizer_communicator_mixin.py +0 -0
  794. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/managers/utils.py +0 -0
  795. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/allocator_ascend.py +0 -0
  796. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/base_prefix_cache.py +0 -0
  797. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/cpp_radix_tree/radix_tree.py +0 -0
  798. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/evict_policy.py +0 -0
  799. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/flush_cache.py +0 -0
  800. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/hicache_storage.py +0 -0
  801. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/hiradix_cache.py +0 -0
  802. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/memory_pool_host.py +0 -0
  803. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/multimodal_cache.py +0 -0
  804. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/radix_cache_cpp.py +0 -0
  805. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/__init__.py +0 -0
  806. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/aibrix_kvcache/aibrix_kvcache_storage.py +0 -0
  807. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/aibrix_kvcache/unit_test.py +0 -0
  808. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/backend_factory.py +0 -0
  809. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/eic/eic_storage.py +0 -0
  810. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/eic/test_unit.py +0 -0
  811. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/hf3fs_client.py +0 -0
  812. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/hf3fs_usrbio_client.py +0 -0
  813. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/hf3fs_utils.cpp +0 -0
  814. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/mini_3fs_metadata_server.py +0 -0
  815. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py +0 -0
  816. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/hf3fs/test_hf3fs_utils.py +0 -0
  817. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/lmcache/lmc_radix_cache.py +0 -0
  818. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/lmcache/unit_test.py +0 -0
  819. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/mooncake_store/mooncake_store.py +0 -0
  820. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/mooncake_store/test_mooncake_store.py +0 -0
  821. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/nixl/hicache_nixl.py +0 -0
  822. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/nixl/nixl_utils.py +0 -0
  823. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/mem_cache/storage/nixl/test_hicache_nixl_storage.py +0 -0
  824. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/metrics/collector.py +0 -0
  825. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/metrics/func_timer.py +0 -0
  826. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/metrics/startup_func_log_and_timer.py +0 -0
  827. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/metrics/utils.py +0 -0
  828. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_executor/cpu_graph_runner.py +0 -0
  829. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_executor/npu_graph_runner.py +0 -0
  830. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_loader/remote_instance_weight_loader_utils.py +0 -0
  831. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/model_loader/utils.py +0 -0
  832. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/apertus.py +0 -0
  833. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/arcee.py +0 -0
  834. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/baichuan.py +0 -0
  835. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/bailing_moe.py +0 -0
  836. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/bailing_moe_nextn.py +0 -0
  837. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/bert.py +0 -0
  838. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/chatglm.py +0 -0
  839. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/clip.py +0 -0
  840. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/commandr.py +0 -0
  841. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/dbrx.py +0 -0
  842. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/deepseek.py +0 -0
  843. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/deepseek_janus_pro.py +0 -0
  844. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/deepseek_nextn.py +0 -0
  845. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/deepseek_v2.py +0 -0
  846. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/deepseek_vl2.py +0 -0
  847. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/dots_ocr.py +0 -0
  848. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/dots_vlm.py +0 -0
  849. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/dots_vlm_vit.py +0 -0
  850. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/ernie4.py +0 -0
  851. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/ernie4_eagle.py +0 -0
  852. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/exaone.py +0 -0
  853. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma.py +0 -0
  854. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma2.py +0 -0
  855. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma2_reward.py +0 -0
  856. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma3_causal.py +0 -0
  857. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma3n_audio.py +0 -0
  858. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma3n_causal.py +0 -0
  859. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gemma3n_mm.py +0 -0
  860. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/glm4.py +0 -0
  861. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/glm4_moe.py +0 -0
  862. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/glm4_moe_nextn.py +0 -0
  863. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/glm4v.py +0 -0
  864. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/glm4v_moe.py +0 -0
  865. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gpt2.py +0 -0
  866. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gpt_bigcode.py +0 -0
  867. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/gpt_oss.py +0 -0
  868. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/granite.py +0 -0
  869. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/granitemoe.py +0 -0
  870. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/hunyuan.py +0 -0
  871. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/idefics2.py +0 -0
  872. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/internlm2.py +0 -0
  873. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/internlm2_reward.py +0 -0
  874. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/interns1.py +0 -0
  875. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/internvl.py +0 -0
  876. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/kimi_vl.py +0 -0
  877. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/kimi_vl_moonvit.py +0 -0
  878. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama.py +0 -0
  879. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama4.py +0 -0
  880. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama_classification.py +0 -0
  881. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama_eagle.py +0 -0
  882. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama_eagle3.py +0 -0
  883. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama_embedding.py +0 -0
  884. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llama_reward.py +0 -0
  885. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llava.py +0 -0
  886. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/llavavid.py +0 -0
  887. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/longcat_flash.py +0 -0
  888. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/longcat_flash_nextn.py +0 -0
  889. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mimo.py +0 -0
  890. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mimo_mtp.py +0 -0
  891. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/minicpm.py +0 -0
  892. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/minicpm3.py +0 -0
  893. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/minicpmo.py +0 -0
  894. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/minicpmv.py +0 -0
  895. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mistral.py +0 -0
  896. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mixtral_quant.py +0 -0
  897. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/mllama.py +0 -0
  898. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/nemotron_nas.py +0 -0
  899. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/olmo.py +0 -0
  900. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/olmo2.py +0 -0
  901. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/olmoe.py +0 -0
  902. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/opt.py +0 -0
  903. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/persimmon.py +0 -0
  904. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phi.py +0 -0
  905. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phi3_small.py +0 -0
  906. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phi4mm.py +0 -0
  907. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phi4mm_audio.py +0 -0
  908. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phi4mm_utils.py +0 -0
  909. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/phimoe.py +0 -0
  910. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/pixtral.py +0 -0
  911. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen.py +0 -0
  912. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2.py +0 -0
  913. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_5_vl.py +0 -0
  914. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_audio.py +0 -0
  915. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_classification.py +0 -0
  916. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_eagle.py +0 -0
  917. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_moe.py +0 -0
  918. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_rm.py +0 -0
  919. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen2_vl.py +0 -0
  920. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3.py +0 -0
  921. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_classification.py +0 -0
  922. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_moe.py +0 -0
  923. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_next.py +0 -0
  924. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_next_mtp.py +0 -0
  925. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_vl.py +0 -0
  926. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/qwen3_vl_moe.py +0 -0
  927. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/registry.py +0 -0
  928. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/roberta.py +0 -0
  929. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/sarashina2_vision.py +0 -0
  930. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/siglip.py +0 -0
  931. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/solar.py +0 -0
  932. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/stablelm.py +0 -0
  933. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/starcoder2.py +0 -0
  934. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/step3_vl.py +0 -0
  935. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/torch_native_llama.py +0 -0
  936. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/transformers.py +0 -0
  937. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/vila.py +0 -0
  938. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/xverse.py +0 -0
  939. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/xverse_moe.py +0 -0
  940. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/models/yivl.py +0 -0
  941. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/mm_utils.py +0 -0
  942. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/base_processor.py +0 -0
  943. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/clip.py +0 -0
  944. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/deepseek_vl_v2.py +0 -0
  945. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/dots_vlm.py +0 -0
  946. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/gemma3.py +0 -0
  947. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/gemma3n.py +0 -0
  948. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/glm4v.py +0 -0
  949. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/internvl.py +0 -0
  950. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/janus_pro.py +0 -0
  951. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/kimi_vl.py +0 -0
  952. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/llava.py +0 -0
  953. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/minicpm.py +0 -0
  954. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/mlama.py +0 -0
  955. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/mllama4.py +0 -0
  956. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/phi4mm.py +0 -0
  957. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/pixtral.py +0 -0
  958. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/qwen_audio.py +0 -0
  959. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/qwen_vl.py +0 -0
  960. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/sarashina2_vision.py +0 -0
  961. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/step3_vl.py +0 -0
  962. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/multimodal/processors/vila.py +0 -0
  963. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/offloader.py +0 -0
  964. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/operations.py +0 -0
  965. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/operations_strategy.py +0 -0
  966. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/parser/code_completion_parser.py +0 -0
  967. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/parser/conversation.py +0 -0
  968. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/parser/harmony_parser.py +0 -0
  969. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/parser/jinja_template_utils.py +0 -0
  970. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/parser/reasoning_parser.py +0 -0
  971. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/custom_logit_processor.py +0 -0
  972. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/penaltylib/__init__.py +0 -0
  973. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/penaltylib/frequency_penalty.py +0 -0
  974. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/penaltylib/min_new_tokens.py +0 -0
  975. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/penaltylib/orchestrator.py +0 -0
  976. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/penaltylib/presence_penalty.py +0 -0
  977. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/sampling/sampling_params.py +0 -0
  978. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/server_args_config_parser.py +0 -0
  979. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/single_batch_overlap.py +0 -0
  980. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/build_eagle_tree.py +0 -0
  981. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/ngram.cpp +0 -0
  982. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/ngram.h +0 -0
  983. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/ngram_cache.py +0 -0
  984. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/ngram_cache_binding.cpp +0 -0
  985. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/param.h +0 -0
  986. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/cpp_ngram/queue.h +0 -0
  987. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/eagle_draft_cuda_graph_runner.py +0 -0
  988. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/eagle_draft_extend_cuda_graph_runner.py +0 -0
  989. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/eagle_info.py +0 -0
  990. /sglang-0.5.3/sglang/srt/speculative/ngram_utils.py → /sglang-0.5.3.post1/sglang/srt/speculative/ngram_info.py +0 -0
  991. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/spec_info.py +0 -0
  992. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/speculative/standalone_worker.py +0 -0
  993. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/tokenizer/tiktoken_tokenizer.py +0 -0
  994. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/torch_memory_saver_adapter.py +0 -0
  995. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/tracing/trace.py +0 -0
  996. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/__init__.py +0 -0
  997. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/patch_torch.py +0 -0
  998. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/poll_based_barrier.py +0 -0
  999. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/rpd_utils.py +0 -0
  1000. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/utils/slow_rank_detector.py +0 -0
  1001. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/warmup.py +0 -0
  1002. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/weight_sync/tensor_bucket.py +0 -0
  1003. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/srt/weight_sync/utils.py +0 -0
  1004. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/__init__.py +0 -0
  1005. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/attention/__init__.py +0 -0
  1006. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/attention/test_flashattn_backend.py +0 -0
  1007. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/attention/test_flashattn_mla_backend.py +0 -0
  1008. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/attention/test_prefix_chunk_info.py +0 -0
  1009. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/attention/test_trtllm_mla_backend.py +0 -0
  1010. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/doc_patch.py +0 -0
  1011. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/few_shot_gsm8k.py +0 -0
  1012. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/few_shot_gsm8k_engine.py +0 -0
  1013. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/get_logits_ut.py +0 -0
  1014. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/runners.py +0 -0
  1015. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/send_one.py +0 -0
  1016. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_common.py +0 -0
  1017. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_gpqa.py +0 -0
  1018. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_humaneval.py +0 -0
  1019. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_math.py +0 -0
  1020. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_mgsm.py +0 -0
  1021. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_mmlu.py +0 -0
  1022. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/simple_eval_mmmu_vlm.py +0 -0
  1023. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_activation.py +0 -0
  1024. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_block_fp8.py +0 -0
  1025. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_block_fp8_deep_gemm_blackwell.py +0 -0
  1026. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_custom_ops.py +0 -0
  1027. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_cutlass_moe.py +0 -0
  1028. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_deepep_utils.py +0 -0
  1029. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_dynamic_grad_mode.py +0 -0
  1030. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_fp4_moe.py +0 -0
  1031. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_layernorm.py +0 -0
  1032. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_marlin_moe.py +0 -0
  1033. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_marlin_utils.py +0 -0
  1034. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/test/test_programs.py +0 -0
  1035. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang/utils.py +0 -0
  1036. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang.egg-info/dependency_links.txt +0 -0
  1037. {sglang-0.5.3 → sglang-0.5.3.post1}/sglang.egg-info/top_level.txt +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: sglang
3
- Version: 0.5.3
3
+ Version: 0.5.3.post1
4
4
  Summary: SGLang is a fast serving framework for large language models and vision language models.
5
5
  License: Apache License
6
6
  Version 2.0, January 2004
@@ -221,7 +221,7 @@ Requires-Dist: cuda-python
221
221
  Requires-Dist: datasets
222
222
  Requires-Dist: einops
223
223
  Requires-Dist: fastapi
224
- Requires-Dist: flashinfer_python==0.4.0rc3
224
+ Requires-Dist: flashinfer_python==0.4.0
225
225
  Requires-Dist: hf_transfer
226
226
  Requires-Dist: huggingface_hub
227
227
  Requires-Dist: interegular
@@ -250,7 +250,7 @@ Requires-Dist: requests
250
250
  Requires-Dist: scipy
251
251
  Requires-Dist: sentencepiece
252
252
  Requires-Dist: setproctitle
253
- Requires-Dist: sgl-kernel==0.3.14.post1
253
+ Requires-Dist: sgl-kernel==0.3.15
254
254
  Requires-Dist: soundfile==0.13.1
255
255
  Requires-Dist: tiktoken
256
256
  Requires-Dist: timm==1.0.16
@@ -263,7 +263,7 @@ Requires-Dist: tqdm
263
263
  Requires-Dist: transformers==4.57.0
264
264
  Requires-Dist: uvicorn
265
265
  Requires-Dist: uvloop
266
- Requires-Dist: xgrammar==0.1.24
266
+ Requires-Dist: xgrammar==0.1.25
267
267
  Requires-Dist: grpcio==1.75.1
268
268
  Requires-Dist: grpcio-tools==1.75.1
269
269
  Provides-Extra: decord
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
4
4
 
5
5
  [project]
6
6
  name = "sglang"
7
- version = "0.5.3"
7
+ version = "0.5.3.post1"
8
8
  description = "SGLang is a fast serving framework for large language models and vision language models."
9
9
  readme = "README.md"
10
10
  requires-python = ">=3.10"
@@ -24,7 +24,7 @@ dependencies = [
24
24
  "datasets",
25
25
  "einops",
26
26
  "fastapi",
27
- "flashinfer_python==0.4.0rc3",
27
+ "flashinfer_python==0.4.0",
28
28
  "hf_transfer",
29
29
  "huggingface_hub",
30
30
  "interegular",
@@ -53,7 +53,7 @@ dependencies = [
53
53
  "scipy",
54
54
  "sentencepiece",
55
55
  "setproctitle",
56
- "sgl-kernel==0.3.14.post1",
56
+ "sgl-kernel==0.3.15",
57
57
  "soundfile==0.13.1",
58
58
  "tiktoken",
59
59
  "timm==1.0.16",
@@ -66,7 +66,7 @@ dependencies = [
66
66
  "transformers==4.57.0",
67
67
  "uvicorn",
68
68
  "uvloop",
69
- "xgrammar==0.1.24",
69
+ "xgrammar==0.1.25",
70
70
  "grpcio==1.75.1", # keep it align with compile_proto.py
71
71
  "grpcio-tools==1.75.1" # keep it align with compile_proto.py
72
72
  ]
@@ -204,7 +204,6 @@ def prepare_inputs_for_correctness_test(bench_args, tokenizer, custom_prompts):
204
204
  origin_input_ids=tmp_input_ids,
205
205
  sampling_params=sampling_params,
206
206
  )
207
- req.prefix_indices = []
208
207
  req.fill_ids = req.origin_input_ids
209
208
  req.extend_input_len = len(req.fill_ids) - len(req.prefix_indices)
210
209
  req.logprob_start_len = len(req.origin_input_ids) - 1
@@ -248,7 +247,6 @@ def prepare_synthetic_inputs_for_latency_test(
248
247
  origin_input_ids=list(input_ids[i]),
249
248
  sampling_params=sampling_params,
250
249
  )
251
- req.prefix_indices = []
252
250
  req.fill_ids = req.origin_input_ids
253
251
  req.extend_input_len = len(req.fill_ids) - len(req.prefix_indices)
254
252
  req.logprob_start_len = len(req.origin_input_ids) - 1