vllm-cpu 0.12.0__cp313-cp313-manylinux_2_17_aarch64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- vllm/_C.abi3.so +0 -0
- vllm/__init__.py +107 -0
- vllm/_aiter_ops.py +1018 -0
- vllm/_bc_linter.py +54 -0
- vllm/_custom_ops.py +2925 -0
- vllm/_ipex_ops.py +457 -0
- vllm/_version.py +34 -0
- vllm/assets/__init__.py +0 -0
- vllm/assets/audio.py +43 -0
- vllm/assets/base.py +40 -0
- vllm/assets/image.py +59 -0
- vllm/assets/video.py +149 -0
- vllm/attention/__init__.py +0 -0
- vllm/attention/backends/__init__.py +0 -0
- vllm/attention/backends/abstract.py +434 -0
- vllm/attention/backends/registry.py +286 -0
- vllm/attention/backends/utils.py +33 -0
- vllm/attention/layer.py +975 -0
- vllm/attention/layers/__init__.py +0 -0
- vllm/attention/layers/chunked_local_attention.py +120 -0
- vllm/attention/layers/cross_attention.py +178 -0
- vllm/attention/layers/encoder_only_attention.py +103 -0
- vllm/attention/ops/__init__.py +0 -0
- vllm/attention/ops/chunked_prefill_paged_decode.py +401 -0
- vllm/attention/ops/common.py +469 -0
- vllm/attention/ops/flashmla.py +251 -0
- vllm/attention/ops/merge_attn_states.py +47 -0
- vllm/attention/ops/paged_attn.py +51 -0
- vllm/attention/ops/pallas_kv_cache_update.py +130 -0
- vllm/attention/ops/prefix_prefill.py +814 -0
- vllm/attention/ops/rocm_aiter_mla_sparse.py +210 -0
- vllm/attention/ops/triton_decode_attention.py +712 -0
- vllm/attention/ops/triton_merge_attn_states.py +116 -0
- vllm/attention/ops/triton_reshape_and_cache_flash.py +184 -0
- vllm/attention/ops/triton_unified_attention.py +941 -0
- vllm/attention/ops/vit_attn_wrappers.py +136 -0
- vllm/attention/selector.py +268 -0
- vllm/attention/utils/__init__.py +0 -0
- vllm/attention/utils/fa_utils.py +117 -0
- vllm/attention/utils/kv_sharing_utils.py +33 -0
- vllm/attention/utils/kv_transfer_utils.py +60 -0
- vllm/beam_search.py +88 -0
- vllm/benchmarks/__init__.py +0 -0
- vllm/benchmarks/datasets.py +3222 -0
- vllm/benchmarks/latency.py +172 -0
- vllm/benchmarks/lib/__init__.py +3 -0
- vllm/benchmarks/lib/endpoint_request_func.py +777 -0
- vllm/benchmarks/lib/ready_checker.py +72 -0
- vllm/benchmarks/lib/utils.py +79 -0
- vllm/benchmarks/serve.py +1531 -0
- vllm/benchmarks/sweep/__init__.py +0 -0
- vllm/benchmarks/sweep/cli.py +41 -0
- vllm/benchmarks/sweep/param_sweep.py +91 -0
- vllm/benchmarks/sweep/plot.py +580 -0
- vllm/benchmarks/sweep/plot_pareto.py +393 -0
- vllm/benchmarks/sweep/serve.py +448 -0
- vllm/benchmarks/sweep/serve_sla.py +492 -0
- vllm/benchmarks/sweep/server.py +114 -0
- vllm/benchmarks/sweep/sla_sweep.py +132 -0
- vllm/benchmarks/sweep/utils.py +4 -0
- vllm/benchmarks/throughput.py +799 -0
- vllm/collect_env.py +857 -0
- vllm/compilation/__init__.py +0 -0
- vllm/compilation/activation_quant_fusion.py +209 -0
- vllm/compilation/backends.py +827 -0
- vllm/compilation/base_static_graph.py +57 -0
- vllm/compilation/caching.py +180 -0
- vllm/compilation/collective_fusion.py +1234 -0
- vllm/compilation/compiler_interface.py +639 -0
- vllm/compilation/counter.py +48 -0
- vllm/compilation/cuda_graph.py +208 -0
- vllm/compilation/decorators.py +614 -0
- vllm/compilation/fix_functionalization.py +253 -0
- vllm/compilation/fusion.py +374 -0
- vllm/compilation/fusion_attn.py +359 -0
- vllm/compilation/fx_utils.py +91 -0
- vllm/compilation/inductor_pass.py +133 -0
- vllm/compilation/matcher_utils.py +315 -0
- vllm/compilation/monitor.py +62 -0
- vllm/compilation/noop_elimination.py +134 -0
- vllm/compilation/partition_rules.py +72 -0
- vllm/compilation/pass_manager.py +136 -0
- vllm/compilation/piecewise_backend.py +121 -0
- vllm/compilation/post_cleanup.py +21 -0
- vllm/compilation/qk_norm_rope_fusion.py +238 -0
- vllm/compilation/sequence_parallelism.py +363 -0
- vllm/compilation/torch25_custom_graph_pass.py +44 -0
- vllm/compilation/vllm_inductor_pass.py +173 -0
- vllm/compilation/wrapper.py +260 -0
- vllm/config/__init__.py +102 -0
- vllm/config/cache.py +220 -0
- vllm/config/compilation.py +1154 -0
- vllm/config/device.py +75 -0
- vllm/config/ec_transfer.py +110 -0
- vllm/config/kv_events.py +56 -0
- vllm/config/kv_transfer.py +114 -0
- vllm/config/load.py +124 -0
- vllm/config/lora.py +96 -0
- vllm/config/model.py +2274 -0
- vllm/config/multimodal.py +247 -0
- vllm/config/observability.py +131 -0
- vllm/config/parallel.py +653 -0
- vllm/config/pooler.py +124 -0
- vllm/config/scheduler.py +297 -0
- vllm/config/speculative.py +643 -0
- vllm/config/speech_to_text.py +38 -0
- vllm/config/structured_outputs.py +94 -0
- vllm/config/utils.py +324 -0
- vllm/config/vllm.py +1353 -0
- vllm/connections.py +189 -0
- vllm/device_allocator/__init__.py +0 -0
- vllm/device_allocator/cumem.py +327 -0
- vllm/distributed/__init__.py +6 -0
- vllm/distributed/communication_op.py +43 -0
- vllm/distributed/device_communicators/__init__.py +0 -0
- vllm/distributed/device_communicators/all2all.py +490 -0
- vllm/distributed/device_communicators/all_reduce_utils.py +344 -0
- vllm/distributed/device_communicators/base_device_communicator.py +297 -0
- vllm/distributed/device_communicators/cpu_communicator.py +209 -0
- vllm/distributed/device_communicators/cuda_communicator.py +340 -0
- vllm/distributed/device_communicators/cuda_wrapper.py +216 -0
- vllm/distributed/device_communicators/custom_all_reduce.py +326 -0
- vllm/distributed/device_communicators/mnnvl_compat.py +27 -0
- vllm/distributed/device_communicators/pynccl.py +386 -0
- vllm/distributed/device_communicators/pynccl_allocator.py +191 -0
- vllm/distributed/device_communicators/pynccl_wrapper.py +564 -0
- vllm/distributed/device_communicators/quick_all_reduce.py +290 -0
- vllm/distributed/device_communicators/ray_communicator.py +259 -0
- vllm/distributed/device_communicators/shm_broadcast.py +733 -0
- vllm/distributed/device_communicators/shm_object_storage.py +697 -0
- vllm/distributed/device_communicators/symm_mem.py +156 -0
- vllm/distributed/device_communicators/tpu_communicator.py +99 -0
- vllm/distributed/device_communicators/xpu_communicator.py +95 -0
- vllm/distributed/ec_transfer/__init__.py +14 -0
- vllm/distributed/ec_transfer/ec_connector/__init__.py +0 -0
- vllm/distributed/ec_transfer/ec_connector/base.py +247 -0
- vllm/distributed/ec_transfer/ec_connector/factory.py +85 -0
- vllm/distributed/ec_transfer/ec_connector/shared_storage_connector.py +201 -0
- vllm/distributed/ec_transfer/ec_transfer_state.py +42 -0
- vllm/distributed/eplb/__init__.py +8 -0
- vllm/distributed/eplb/async_worker.py +115 -0
- vllm/distributed/eplb/eplb_state.py +1154 -0
- vllm/distributed/eplb/rebalance_algo.py +260 -0
- vllm/distributed/eplb/rebalance_execute.py +532 -0
- vllm/distributed/kv_events.py +371 -0
- vllm/distributed/kv_transfer/README.md +29 -0
- vllm/distributed/kv_transfer/__init__.py +20 -0
- vllm/distributed/kv_transfer/disagg_prefill_workflow.jpg +0 -0
- vllm/distributed/kv_transfer/kv_connector/__init__.py +0 -0
- vllm/distributed/kv_transfer/kv_connector/base.py +10 -0
- vllm/distributed/kv_transfer/kv_connector/factory.py +192 -0
- vllm/distributed/kv_transfer/kv_connector/utils.py +268 -0
- vllm/distributed/kv_transfer/kv_connector/v1/__init__.py +19 -0
- vllm/distributed/kv_transfer/kv_connector/v1/base.py +575 -0
- vllm/distributed/kv_transfer/kv_connector/v1/decode_bench_connector.py +419 -0
- vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py +216 -0
- vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/__init__.py +18 -0
- vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/multi_process_adapter.py +378 -0
- vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/utils.py +221 -0
- vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/vllm_v1_adapter.py +1411 -0
- vllm/distributed/kv_transfer/kv_connector/v1/lmcache_mp_connector.py +895 -0
- vllm/distributed/kv_transfer/kv_connector/v1/metrics.py +189 -0
- vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py +454 -0
- vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py +2480 -0
- vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py +538 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/__init__.py +0 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py +531 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py +632 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py +273 -0
- vllm/distributed/kv_transfer/kv_connector/v1/shared_storage_connector.py +450 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/__init__.py +0 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/base.py +179 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/mooncake_store.py +164 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py +242 -0
- vllm/distributed/kv_transfer/kv_pipe/__init__.py +0 -0
- vllm/distributed/kv_transfer/kv_pipe/base.py +66 -0
- vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py +295 -0
- vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py +285 -0
- vllm/distributed/kv_transfer/kv_transfer_state.py +78 -0
- vllm/distributed/parallel_state.py +1790 -0
- vllm/distributed/tpu_distributed_utils.py +188 -0
- vllm/distributed/utils.py +545 -0
- vllm/engine/__init__.py +0 -0
- vllm/engine/arg_utils.py +2106 -0
- vllm/engine/async_llm_engine.py +6 -0
- vllm/engine/llm_engine.py +6 -0
- vllm/engine/protocol.py +188 -0
- vllm/entrypoints/__init__.py +0 -0
- vllm/entrypoints/anthropic/__init__.py +0 -0
- vllm/entrypoints/anthropic/protocol.py +162 -0
- vllm/entrypoints/anthropic/serving_messages.py +460 -0
- vllm/entrypoints/api_server.py +184 -0
- vllm/entrypoints/chat_utils.py +1837 -0
- vllm/entrypoints/cli/__init__.py +13 -0
- vllm/entrypoints/cli/benchmark/__init__.py +0 -0
- vllm/entrypoints/cli/benchmark/base.py +25 -0
- vllm/entrypoints/cli/benchmark/latency.py +21 -0
- vllm/entrypoints/cli/benchmark/main.py +56 -0
- vllm/entrypoints/cli/benchmark/serve.py +21 -0
- vllm/entrypoints/cli/benchmark/sweep.py +21 -0
- vllm/entrypoints/cli/benchmark/throughput.py +21 -0
- vllm/entrypoints/cli/collect_env.py +38 -0
- vllm/entrypoints/cli/main.py +79 -0
- vllm/entrypoints/cli/openai.py +256 -0
- vllm/entrypoints/cli/run_batch.py +68 -0
- vllm/entrypoints/cli/serve.py +249 -0
- vllm/entrypoints/cli/types.py +29 -0
- vllm/entrypoints/constants.py +10 -0
- vllm/entrypoints/context.py +572 -0
- vllm/entrypoints/dynamic_lora.py +57 -0
- vllm/entrypoints/harmony_utils.py +535 -0
- vllm/entrypoints/launcher.py +175 -0
- vllm/entrypoints/llm.py +1762 -0
- vllm/entrypoints/logger.py +84 -0
- vllm/entrypoints/openai/__init__.py +0 -0
- vllm/entrypoints/openai/api_server.py +1891 -0
- vllm/entrypoints/openai/cli_args.py +302 -0
- vllm/entrypoints/openai/orca_metrics.py +120 -0
- vllm/entrypoints/openai/protocol.py +2465 -0
- vllm/entrypoints/openai/run_batch.py +631 -0
- vllm/entrypoints/openai/serving_chat.py +1782 -0
- vllm/entrypoints/openai/serving_completion.py +716 -0
- vllm/entrypoints/openai/serving_engine.py +1478 -0
- vllm/entrypoints/openai/serving_models.py +304 -0
- vllm/entrypoints/openai/serving_responses.py +2032 -0
- vllm/entrypoints/openai/serving_tokenization.py +203 -0
- vllm/entrypoints/openai/serving_tokens.py +281 -0
- vllm/entrypoints/openai/serving_transcription.py +168 -0
- vllm/entrypoints/openai/speech_to_text.py +559 -0
- vllm/entrypoints/openai/tool_parsers/__init__.py +142 -0
- vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py +273 -0
- vllm/entrypoints/openai/tool_parsers/deepseekv31_tool_parser.py +390 -0
- vllm/entrypoints/openai/tool_parsers/deepseekv3_tool_parser.py +390 -0
- vllm/entrypoints/openai/tool_parsers/ernie45_tool_parser.py +210 -0
- vllm/entrypoints/openai/tool_parsers/glm4_moe_tool_parser.py +200 -0
- vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py +273 -0
- vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py +253 -0
- vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py +494 -0
- vllm/entrypoints/openai/tool_parsers/hunyuan_a13b_tool_parser.py +420 -0
- vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py +227 -0
- vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py +322 -0
- vllm/entrypoints/openai/tool_parsers/kimi_k2_tool_parser.py +590 -0
- vllm/entrypoints/openai/tool_parsers/llama4_pythonic_tool_parser.py +341 -0
- vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py +324 -0
- vllm/entrypoints/openai/tool_parsers/longcat_tool_parser.py +37 -0
- vllm/entrypoints/openai/tool_parsers/minimax_m2_tool_parser.py +643 -0
- vllm/entrypoints/openai/tool_parsers/minimax_tool_parser.py +849 -0
- vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py +390 -0
- vllm/entrypoints/openai/tool_parsers/olmo3_tool_parser.py +366 -0
- vllm/entrypoints/openai/tool_parsers/openai_tool_parser.py +97 -0
- vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py +120 -0
- vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py +332 -0
- vllm/entrypoints/openai/tool_parsers/qwen3coder_tool_parser.py +781 -0
- vllm/entrypoints/openai/tool_parsers/qwen3xml_tool_parser.py +1316 -0
- vllm/entrypoints/openai/tool_parsers/seed_oss_tool_parser.py +744 -0
- vllm/entrypoints/openai/tool_parsers/step3_tool_parser.py +303 -0
- vllm/entrypoints/openai/tool_parsers/utils.py +229 -0
- vllm/entrypoints/openai/tool_parsers/xlam_tool_parser.py +556 -0
- vllm/entrypoints/openai/utils.py +49 -0
- vllm/entrypoints/pooling/__init__.py +16 -0
- vllm/entrypoints/pooling/classify/__init__.py +0 -0
- vllm/entrypoints/pooling/classify/api_router.py +50 -0
- vllm/entrypoints/pooling/classify/protocol.py +181 -0
- vllm/entrypoints/pooling/classify/serving.py +237 -0
- vllm/entrypoints/pooling/embed/__init__.py +0 -0
- vllm/entrypoints/pooling/embed/api_router.py +67 -0
- vllm/entrypoints/pooling/embed/protocol.py +208 -0
- vllm/entrypoints/pooling/embed/serving.py +697 -0
- vllm/entrypoints/pooling/pooling/__init__.py +0 -0
- vllm/entrypoints/pooling/pooling/api_router.py +63 -0
- vllm/entrypoints/pooling/pooling/protocol.py +148 -0
- vllm/entrypoints/pooling/pooling/serving.py +348 -0
- vllm/entrypoints/pooling/score/__init__.py +0 -0
- vllm/entrypoints/pooling/score/api_router.py +149 -0
- vllm/entrypoints/pooling/score/protocol.py +145 -0
- vllm/entrypoints/pooling/score/serving.py +505 -0
- vllm/entrypoints/renderer.py +409 -0
- vllm/entrypoints/responses_utils.py +148 -0
- vllm/entrypoints/sagemaker/__init__.py +4 -0
- vllm/entrypoints/sagemaker/routes.py +118 -0
- vllm/entrypoints/score_utils.py +240 -0
- vllm/entrypoints/ssl.py +78 -0
- vllm/entrypoints/tool.py +143 -0
- vllm/entrypoints/tool_server.py +234 -0
- vllm/entrypoints/utils.py +319 -0
- vllm/env_override.py +378 -0
- vllm/envs.py +1710 -0
- vllm/forward_context.py +358 -0
- vllm/inputs/__init__.py +44 -0
- vllm/inputs/data.py +359 -0
- vllm/inputs/parse.py +137 -0
- vllm/inputs/preprocess.py +716 -0
- vllm/logger.py +298 -0
- vllm/logging_utils/__init__.py +13 -0
- vllm/logging_utils/dump_input.py +83 -0
- vllm/logging_utils/formatter.py +127 -0
- vllm/logging_utils/lazy.py +20 -0
- vllm/logging_utils/log_time.py +34 -0
- vllm/logits_process.py +121 -0
- vllm/logprobs.py +206 -0
- vllm/lora/__init__.py +0 -0
- vllm/lora/layers/__init__.py +42 -0
- vllm/lora/layers/base.py +66 -0
- vllm/lora/layers/base_linear.py +165 -0
- vllm/lora/layers/column_parallel_linear.py +577 -0
- vllm/lora/layers/fused_moe.py +747 -0
- vllm/lora/layers/logits_processor.py +203 -0
- vllm/lora/layers/replicated_linear.py +70 -0
- vllm/lora/layers/row_parallel_linear.py +176 -0
- vllm/lora/layers/utils.py +74 -0
- vllm/lora/layers/vocal_parallel_embedding.py +140 -0
- vllm/lora/lora_weights.py +227 -0
- vllm/lora/models.py +903 -0
- vllm/lora/ops/__init__.py +0 -0
- vllm/lora/ops/ipex_ops/__init__.py +6 -0
- vllm/lora/ops/ipex_ops/lora_ops.py +57 -0
- vllm/lora/ops/torch_ops/__init__.py +20 -0
- vllm/lora/ops/torch_ops/lora_ops.py +128 -0
- vllm/lora/ops/triton_ops/README_TUNING.md +60 -0
- vllm/lora/ops/triton_ops/__init__.py +21 -0
- vllm/lora/ops/triton_ops/fused_moe_lora_op.py +661 -0
- vllm/lora/ops/triton_ops/kernel_utils.py +340 -0
- vllm/lora/ops/triton_ops/lora_expand_op.py +310 -0
- vllm/lora/ops/triton_ops/lora_kernel_metadata.py +154 -0
- vllm/lora/ops/triton_ops/lora_shrink_op.py +287 -0
- vllm/lora/ops/triton_ops/utils.py +295 -0
- vllm/lora/ops/xla_ops/__init__.py +6 -0
- vllm/lora/ops/xla_ops/lora_ops.py +141 -0
- vllm/lora/peft_helper.py +128 -0
- vllm/lora/punica_wrapper/__init__.py +10 -0
- vllm/lora/punica_wrapper/punica_base.py +493 -0
- vllm/lora/punica_wrapper/punica_cpu.py +351 -0
- vllm/lora/punica_wrapper/punica_gpu.py +412 -0
- vllm/lora/punica_wrapper/punica_selector.py +21 -0
- vllm/lora/punica_wrapper/punica_tpu.py +358 -0
- vllm/lora/punica_wrapper/punica_xpu.py +276 -0
- vllm/lora/punica_wrapper/utils.py +150 -0
- vllm/lora/request.py +100 -0
- vllm/lora/resolver.py +88 -0
- vllm/lora/utils.py +306 -0
- vllm/lora/worker_manager.py +268 -0
- vllm/model_executor/__init__.py +11 -0
- vllm/model_executor/custom_op.py +194 -0
- vllm/model_executor/layers/__init__.py +0 -0
- vllm/model_executor/layers/activation.py +595 -0
- vllm/model_executor/layers/attention_layer_base.py +32 -0
- vllm/model_executor/layers/batch_invariant.py +1058 -0
- vllm/model_executor/layers/conv.py +256 -0
- vllm/model_executor/layers/fla/__init__.py +8 -0
- vllm/model_executor/layers/fla/ops/__init__.py +17 -0
- vllm/model_executor/layers/fla/ops/chunk.py +240 -0
- vllm/model_executor/layers/fla/ops/chunk_delta_h.py +344 -0
- vllm/model_executor/layers/fla/ops/chunk_o.py +183 -0
- vllm/model_executor/layers/fla/ops/chunk_scaled_dot_kkt.py +154 -0
- vllm/model_executor/layers/fla/ops/cumsum.py +280 -0
- vllm/model_executor/layers/fla/ops/fused_recurrent.py +390 -0
- vllm/model_executor/layers/fla/ops/index.py +41 -0
- vllm/model_executor/layers/fla/ops/kda.py +1351 -0
- vllm/model_executor/layers/fla/ops/l2norm.py +146 -0
- vllm/model_executor/layers/fla/ops/layernorm_guard.py +396 -0
- vllm/model_executor/layers/fla/ops/op.py +60 -0
- vllm/model_executor/layers/fla/ops/solve_tril.py +556 -0
- vllm/model_executor/layers/fla/ops/utils.py +194 -0
- vllm/model_executor/layers/fla/ops/wy_fast.py +158 -0
- vllm/model_executor/layers/fused_moe/__init__.py +110 -0
- vllm/model_executor/layers/fused_moe/all2all_utils.py +171 -0
- vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py +406 -0
- vllm/model_executor/layers/fused_moe/batched_triton_or_deep_gemm_moe.py +180 -0
- vllm/model_executor/layers/fused_moe/config.py +938 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H200,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H100,dtype=fp8_w8a8.json +123 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=1856,device_name=NVIDIA_H100_80GB_HBM3.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=1856,device_name=NVIDIA_L40S.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=352,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +122 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +114 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI308X.json +213 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=bf16.json +82 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +82 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=928,device_name=NVIDIA_H100_80GB_HBM3.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=928,device_name=NVIDIA_L40S.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=96,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H100.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=2048,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H200,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=AMD_Instinct_MI300X.json +201 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=AMD_Instinct_MI350_OAM,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=320,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI350_OAM,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI355_OAM,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=20,N=1536,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Server_Edition,dtype=fp8_w8a8.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325X,block_shape=[128,128].json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=32,N=1408,device_name=NVIDIA_B200.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=32,N=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=32,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=40,N=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_A100-SXM4-80GB.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_A100-SXM4-80GB.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_B200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H20-3e.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=62,N=128,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1408,device_name=NVIDIA_B200.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H100_PCIe,dtype=fp8_w8a8,block_shape=[128,128].json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=896,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=bf16.json +82 -0
- vllm/model_executor/layers/fused_moe/configs/E=64,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +82 -0
- vllm/model_executor/layers/fused_moe/configs/E=72,N=192,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +138 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +154 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_L40S.json +173 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json +164 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/README +12 -0
- vllm/model_executor/layers/fused_moe/cpu_fused_moe.py +292 -0
- vllm/model_executor/layers/fused_moe/cutlass_moe.py +1052 -0
- vllm/model_executor/layers/fused_moe/deep_gemm_moe.py +387 -0
- vllm/model_executor/layers/fused_moe/deep_gemm_utils.py +416 -0
- vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py +420 -0
- vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py +434 -0
- vllm/model_executor/layers/fused_moe/flashinfer_cutedsl_moe.py +376 -0
- vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py +307 -0
- vllm/model_executor/layers/fused_moe/flashinfer_cutlass_prepare_finalize.py +362 -0
- vllm/model_executor/layers/fused_moe/flashinfer_trtllm_moe.py +192 -0
- vllm/model_executor/layers/fused_moe/fused_batched_moe.py +1012 -0
- vllm/model_executor/layers/fused_moe/fused_marlin_moe.py +821 -0
- vllm/model_executor/layers/fused_moe/fused_moe.py +2172 -0
- vllm/model_executor/layers/fused_moe/fused_moe_method_base.py +121 -0
- vllm/model_executor/layers/fused_moe/fused_moe_modular_method.py +136 -0
- vllm/model_executor/layers/fused_moe/gpt_oss_triton_kernels_moe.py +524 -0
- vllm/model_executor/layers/fused_moe/layer.py +2152 -0
- vllm/model_executor/layers/fused_moe/modular_kernel.py +1332 -0
- vllm/model_executor/layers/fused_moe/moe_align_block_size.py +174 -0
- vllm/model_executor/layers/fused_moe/moe_pallas.py +83 -0
- vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py +229 -0
- vllm/model_executor/layers/fused_moe/moe_torch_iterative.py +60 -0
- vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py +362 -0
- vllm/model_executor/layers/fused_moe/prepare_finalize.py +78 -0
- vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py +265 -0
- vllm/model_executor/layers/fused_moe/routing_simulator.py +310 -0
- vllm/model_executor/layers/fused_moe/shared_fused_moe.py +96 -0
- vllm/model_executor/layers/fused_moe/topk_weight_and_reduce.py +171 -0
- vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py +163 -0
- vllm/model_executor/layers/fused_moe/trtllm_moe.py +143 -0
- vllm/model_executor/layers/fused_moe/unquantized_fused_moe_method.py +559 -0
- vllm/model_executor/layers/fused_moe/utils.py +332 -0
- vllm/model_executor/layers/kda.py +442 -0
- vllm/model_executor/layers/layernorm.py +442 -0
- vllm/model_executor/layers/lightning_attn.py +735 -0
- vllm/model_executor/layers/linear.py +1424 -0
- vllm/model_executor/layers/logits_processor.py +106 -0
- vllm/model_executor/layers/mamba/__init__.py +0 -0
- vllm/model_executor/layers/mamba/abstract.py +68 -0
- vllm/model_executor/layers/mamba/linear_attn.py +388 -0
- vllm/model_executor/layers/mamba/mamba_mixer.py +527 -0
- vllm/model_executor/layers/mamba/mamba_mixer2.py +930 -0
- vllm/model_executor/layers/mamba/mamba_utils.py +225 -0
- vllm/model_executor/layers/mamba/ops/__init__.py +0 -0
- vllm/model_executor/layers/mamba/ops/causal_conv1d.py +1240 -0
- vllm/model_executor/layers/mamba/ops/layernorm_gated.py +172 -0
- vllm/model_executor/layers/mamba/ops/mamba_ssm.py +478 -0
- vllm/model_executor/layers/mamba/ops/ssd_bmm.py +211 -0
- vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py +456 -0
- vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py +700 -0
- vllm/model_executor/layers/mamba/ops/ssd_combined.py +230 -0
- vllm/model_executor/layers/mamba/ops/ssd_state_passing.py +157 -0
- vllm/model_executor/layers/mamba/short_conv.py +255 -0
- vllm/model_executor/layers/mla.py +176 -0
- vllm/model_executor/layers/pooler.py +817 -0
- vllm/model_executor/layers/quantization/__init__.py +179 -0
- vllm/model_executor/layers/quantization/auto_round.py +454 -0
- vllm/model_executor/layers/quantization/awq.py +277 -0
- vllm/model_executor/layers/quantization/awq_marlin.py +718 -0
- vllm/model_executor/layers/quantization/awq_triton.py +337 -0
- vllm/model_executor/layers/quantization/base_config.py +170 -0
- vllm/model_executor/layers/quantization/bitblas.py +502 -0
- vllm/model_executor/layers/quantization/bitsandbytes.py +644 -0
- vllm/model_executor/layers/quantization/compressed_tensors/__init__.py +3 -0
- vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py +963 -0
- vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py +2387 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py +35 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py +392 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py +55 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py +176 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py +124 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py +218 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_fp8.py +183 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_int.py +153 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py +138 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +200 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py +125 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py +230 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/__init__.py +0 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/linear.py +260 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/module.py +173 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/__init__.py +0 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/linear_qutlass_nvfp4.py +64 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/utils.py +13 -0
- vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py +224 -0
- vllm/model_executor/layers/quantization/compressed_tensors/utils.py +216 -0
- vllm/model_executor/layers/quantization/cpu_wna16.py +625 -0
- vllm/model_executor/layers/quantization/deepspeedfp.py +218 -0
- vllm/model_executor/layers/quantization/experts_int8.py +225 -0
- vllm/model_executor/layers/quantization/fbgemm_fp8.py +195 -0
- vllm/model_executor/layers/quantization/fp8.py +1348 -0
- vllm/model_executor/layers/quantization/fp_quant.py +420 -0
- vllm/model_executor/layers/quantization/gguf.py +687 -0
- vllm/model_executor/layers/quantization/gptq.py +393 -0
- vllm/model_executor/layers/quantization/gptq_bitblas.py +482 -0
- vllm/model_executor/layers/quantization/gptq_marlin.py +842 -0
- vllm/model_executor/layers/quantization/gptq_marlin_24.py +320 -0
- vllm/model_executor/layers/quantization/hqq_marlin.py +372 -0
- vllm/model_executor/layers/quantization/inc.py +65 -0
- vllm/model_executor/layers/quantization/input_quant_fp8.py +171 -0
- vllm/model_executor/layers/quantization/ipex_quant.py +470 -0
- vllm/model_executor/layers/quantization/kernels/__init__.py +0 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py +94 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py +105 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py +115 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py +323 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/conch.py +98 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/cutlass.py +119 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/dynamic_4bit.py +111 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py +161 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py +159 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py +200 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py +73 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py +97 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py +120 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/cpu.py +219 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py +140 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py +42 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py +105 -0
- vllm/model_executor/layers/quantization/kv_cache.py +146 -0
- vllm/model_executor/layers/quantization/modelopt.py +1637 -0
- vllm/model_executor/layers/quantization/moe_wna16.py +528 -0
- vllm/model_executor/layers/quantization/mxfp4.py +1175 -0
- vllm/model_executor/layers/quantization/petit.py +319 -0
- vllm/model_executor/layers/quantization/ptpc_fp8.py +136 -0
- vllm/model_executor/layers/quantization/quark/__init__.py +0 -0
- vllm/model_executor/layers/quantization/quark/quark.py +527 -0
- vllm/model_executor/layers/quantization/quark/quark_moe.py +653 -0
- vllm/model_executor/layers/quantization/quark/schemes/__init__.py +9 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_ocp_mx.py +343 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py +55 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py +179 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py +139 -0
- vllm/model_executor/layers/quantization/quark/utils.py +105 -0
- vllm/model_executor/layers/quantization/qutlass_utils.py +185 -0
- vllm/model_executor/layers/quantization/rtn.py +639 -0
- vllm/model_executor/layers/quantization/schema.py +90 -0
- vllm/model_executor/layers/quantization/torchao.py +380 -0
- vllm/model_executor/layers/quantization/tpu_int8.py +139 -0
- vllm/model_executor/layers/quantization/utils/__init__.py +6 -0
- vllm/model_executor/layers/quantization/utils/allspark_utils.py +67 -0
- vllm/model_executor/layers/quantization/utils/bitblas_utils.py +229 -0
- vllm/model_executor/layers/quantization/utils/configs/N=10240,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=5120,K=25600,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=5120,K=8192,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=51200,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +18 -0
- vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json +26 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json +164 -0
- vllm/model_executor/layers/quantization/utils/configs/README.md +3 -0
- vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py +333 -0
- vllm/model_executor/layers/quantization/utils/flashinfer_utils.py +311 -0
- vllm/model_executor/layers/quantization/utils/fp8_utils.py +1203 -0
- vllm/model_executor/layers/quantization/utils/gptq_utils.py +158 -0
- vllm/model_executor/layers/quantization/utils/int8_utils.py +489 -0
- vllm/model_executor/layers/quantization/utils/layer_utils.py +41 -0
- vllm/model_executor/layers/quantization/utils/machete_utils.py +56 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils.py +674 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py +452 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py +378 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_test.py +219 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py +467 -0
- vllm/model_executor/layers/quantization/utils/mxfp4_utils.py +183 -0
- vllm/model_executor/layers/quantization/utils/mxfp6_utils.py +142 -0
- vllm/model_executor/layers/quantization/utils/mxfp8_utils.py +24 -0
- vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py +142 -0
- vllm/model_executor/layers/quantization/utils/nvfp4_moe_support.py +67 -0
- vllm/model_executor/layers/quantization/utils/ocp_mx_utils.py +51 -0
- vllm/model_executor/layers/quantization/utils/petit_utils.py +124 -0
- vllm/model_executor/layers/quantization/utils/quant_utils.py +687 -0
- vllm/model_executor/layers/quantization/utils/w8a8_utils.py +516 -0
- vllm/model_executor/layers/resampler.py +283 -0
- vllm/model_executor/layers/rotary_embedding/__init__.py +292 -0
- vllm/model_executor/layers/rotary_embedding/base.py +240 -0
- vllm/model_executor/layers/rotary_embedding/common.py +188 -0
- vllm/model_executor/layers/rotary_embedding/deepseek_scaling_rope.py +165 -0
- vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py +215 -0
- vllm/model_executor/layers/rotary_embedding/dynamic_ntk_alpha_rope.py +43 -0
- vllm/model_executor/layers/rotary_embedding/dynamic_ntk_scaling_rope.py +68 -0
- vllm/model_executor/layers/rotary_embedding/ernie45_vl_rope.py +75 -0
- vllm/model_executor/layers/rotary_embedding/linear_scaling_rope.py +115 -0
- vllm/model_executor/layers/rotary_embedding/llama3_rope.py +54 -0
- vllm/model_executor/layers/rotary_embedding/llama4_vision_rope.py +80 -0
- vllm/model_executor/layers/rotary_embedding/mrope.py +397 -0
- vllm/model_executor/layers/rotary_embedding/ntk_scaling_rope.py +47 -0
- vllm/model_executor/layers/rotary_embedding/phi3_long_rope_scaled_rope.py +159 -0
- vllm/model_executor/layers/rotary_embedding/xdrope.py +102 -0
- vllm/model_executor/layers/rotary_embedding/yarn_scaling_rope.py +84 -0
- vllm/model_executor/layers/utils.py +251 -0
- vllm/model_executor/layers/vocab_parallel_embedding.py +558 -0
- vllm/model_executor/model_loader/__init__.py +150 -0
- vllm/model_executor/model_loader/base_loader.py +57 -0
- vllm/model_executor/model_loader/bitsandbytes_loader.py +822 -0
- vllm/model_executor/model_loader/default_loader.py +321 -0
- vllm/model_executor/model_loader/dummy_loader.py +28 -0
- vllm/model_executor/model_loader/gguf_loader.py +349 -0
- vllm/model_executor/model_loader/online_quantization.py +275 -0
- vllm/model_executor/model_loader/runai_streamer_loader.py +116 -0
- vllm/model_executor/model_loader/sharded_state_loader.py +214 -0
- vllm/model_executor/model_loader/tensorizer.py +790 -0
- vllm/model_executor/model_loader/tensorizer_loader.py +151 -0
- vllm/model_executor/model_loader/tpu.py +118 -0
- vllm/model_executor/model_loader/utils.py +296 -0
- vllm/model_executor/model_loader/weight_utils.py +1147 -0
- vllm/model_executor/models/__init__.py +44 -0
- vllm/model_executor/models/adapters.py +543 -0
- vllm/model_executor/models/afmoe.py +697 -0
- vllm/model_executor/models/aimv2.py +248 -0
- vllm/model_executor/models/apertus.py +569 -0
- vllm/model_executor/models/arcee.py +428 -0
- vllm/model_executor/models/arctic.py +634 -0
- vllm/model_executor/models/aria.py +655 -0
- vllm/model_executor/models/aya_vision.py +450 -0
- vllm/model_executor/models/baichuan.py +494 -0
- vllm/model_executor/models/bailing_moe.py +645 -0
- vllm/model_executor/models/bamba.py +516 -0
- vllm/model_executor/models/bee.py +157 -0
- vllm/model_executor/models/bert.py +925 -0
- vllm/model_executor/models/bert_with_rope.py +732 -0
- vllm/model_executor/models/blip.py +350 -0
- vllm/model_executor/models/blip2.py +695 -0
- vllm/model_executor/models/bloom.py +390 -0
- vllm/model_executor/models/chameleon.py +1098 -0
- vllm/model_executor/models/chatglm.py +499 -0
- vllm/model_executor/models/clip.py +1005 -0
- vllm/model_executor/models/cohere2_vision.py +472 -0
- vllm/model_executor/models/commandr.py +470 -0
- vllm/model_executor/models/config.py +510 -0
- vllm/model_executor/models/dbrx.py +485 -0
- vllm/model_executor/models/deepencoder.py +676 -0
- vllm/model_executor/models/deepseek_eagle.py +252 -0
- vllm/model_executor/models/deepseek_mtp.py +446 -0
- vllm/model_executor/models/deepseek_ocr.py +593 -0
- vllm/model_executor/models/deepseek_v2.py +1715 -0
- vllm/model_executor/models/deepseek_vl2.py +644 -0
- vllm/model_executor/models/dots1.py +566 -0
- vllm/model_executor/models/dots_ocr.py +874 -0
- vllm/model_executor/models/ernie45.py +53 -0
- vllm/model_executor/models/ernie45_moe.py +755 -0
- vllm/model_executor/models/ernie45_vl.py +1710 -0
- vllm/model_executor/models/ernie45_vl_moe.py +800 -0
- vllm/model_executor/models/ernie_mtp.py +279 -0
- vllm/model_executor/models/exaone.py +525 -0
- vllm/model_executor/models/exaone4.py +517 -0
- vllm/model_executor/models/fairseq2_llama.py +154 -0
- vllm/model_executor/models/falcon.py +544 -0
- vllm/model_executor/models/falcon_h1.py +680 -0
- vllm/model_executor/models/flex_olmo.py +155 -0
- vllm/model_executor/models/fuyu.py +373 -0
- vllm/model_executor/models/gemma.py +426 -0
- vllm/model_executor/models/gemma2.py +436 -0
- vllm/model_executor/models/gemma3.py +577 -0
- vllm/model_executor/models/gemma3_mm.py +665 -0
- vllm/model_executor/models/gemma3n.py +1167 -0
- vllm/model_executor/models/gemma3n_mm.py +811 -0
- vllm/model_executor/models/glm.py +23 -0
- vllm/model_executor/models/glm4.py +298 -0
- vllm/model_executor/models/glm4_1v.py +1854 -0
- vllm/model_executor/models/glm4_moe.py +738 -0
- vllm/model_executor/models/glm4_moe_mtp.py +359 -0
- vllm/model_executor/models/glm4v.py +785 -0
- vllm/model_executor/models/gpt2.py +397 -0
- vllm/model_executor/models/gpt_bigcode.py +339 -0
- vllm/model_executor/models/gpt_j.py +345 -0
- vllm/model_executor/models/gpt_neox.py +343 -0
- vllm/model_executor/models/gpt_oss.py +745 -0
- vllm/model_executor/models/granite.py +476 -0
- vllm/model_executor/models/granite_speech.py +913 -0
- vllm/model_executor/models/granitemoe.py +561 -0
- vllm/model_executor/models/granitemoehybrid.py +704 -0
- vllm/model_executor/models/granitemoeshared.py +328 -0
- vllm/model_executor/models/gritlm.py +245 -0
- vllm/model_executor/models/grok1.py +555 -0
- vllm/model_executor/models/h2ovl.py +554 -0
- vllm/model_executor/models/hunyuan_v1.py +1042 -0
- vllm/model_executor/models/hunyuan_vision.py +1028 -0
- vllm/model_executor/models/hyperclovax_vision.py +1166 -0
- vllm/model_executor/models/idefics2_vision_model.py +427 -0
- vllm/model_executor/models/idefics3.py +718 -0
- vllm/model_executor/models/interfaces.py +1148 -0
- vllm/model_executor/models/interfaces_base.py +243 -0
- vllm/model_executor/models/intern_vit.py +454 -0
- vllm/model_executor/models/internlm2.py +454 -0
- vllm/model_executor/models/internlm2_ve.py +139 -0
- vllm/model_executor/models/interns1.py +830 -0
- vllm/model_executor/models/interns1_vit.py +433 -0
- vllm/model_executor/models/internvl.py +1452 -0
- vllm/model_executor/models/jais.py +397 -0
- vllm/model_executor/models/jamba.py +609 -0
- vllm/model_executor/models/jina_vl.py +147 -0
- vllm/model_executor/models/keye.py +1765 -0
- vllm/model_executor/models/keye_vl1_5.py +726 -0
- vllm/model_executor/models/kimi_linear.py +658 -0
- vllm/model_executor/models/kimi_vl.py +578 -0
- vllm/model_executor/models/lfm2.py +516 -0
- vllm/model_executor/models/lfm2_moe.py +746 -0
- vllm/model_executor/models/lightonocr.py +195 -0
- vllm/model_executor/models/llama.py +704 -0
- vllm/model_executor/models/llama4.py +857 -0
- vllm/model_executor/models/llama4_eagle.py +216 -0
- vllm/model_executor/models/llama_eagle.py +213 -0
- vllm/model_executor/models/llama_eagle3.py +375 -0
- vllm/model_executor/models/llava.py +842 -0
- vllm/model_executor/models/llava_next.py +583 -0
- vllm/model_executor/models/llava_next_video.py +467 -0
- vllm/model_executor/models/llava_onevision.py +923 -0
- vllm/model_executor/models/longcat_flash.py +743 -0
- vllm/model_executor/models/longcat_flash_mtp.py +349 -0
- vllm/model_executor/models/mamba.py +276 -0
- vllm/model_executor/models/mamba2.py +288 -0
- vllm/model_executor/models/medusa.py +179 -0
- vllm/model_executor/models/midashenglm.py +828 -0
- vllm/model_executor/models/mimo.py +188 -0
- vllm/model_executor/models/mimo_mtp.py +294 -0
- vllm/model_executor/models/minicpm.py +657 -0
- vllm/model_executor/models/minicpm3.py +234 -0
- vllm/model_executor/models/minicpm_eagle.py +385 -0
- vllm/model_executor/models/minicpmo.py +768 -0
- vllm/model_executor/models/minicpmv.py +1744 -0
- vllm/model_executor/models/minimax_m2.py +546 -0
- vllm/model_executor/models/minimax_text_01.py +1010 -0
- vllm/model_executor/models/minimax_vl_01.py +396 -0
- vllm/model_executor/models/mistral3.py +637 -0
- vllm/model_executor/models/mistral_large_3.py +63 -0
- vllm/model_executor/models/mistral_large_3_eagle.py +165 -0
- vllm/model_executor/models/mixtral.py +599 -0
- vllm/model_executor/models/mllama4.py +1151 -0
- vllm/model_executor/models/mlp_speculator.py +235 -0
- vllm/model_executor/models/modernbert.py +452 -0
- vllm/model_executor/models/module_mapping.py +74 -0
- vllm/model_executor/models/molmo.py +1553 -0
- vllm/model_executor/models/moonvit.py +686 -0
- vllm/model_executor/models/mpt.py +335 -0
- vllm/model_executor/models/nano_nemotron_vl.py +1732 -0
- vllm/model_executor/models/nemotron.py +502 -0
- vllm/model_executor/models/nemotron_h.py +850 -0
- vllm/model_executor/models/nemotron_nas.py +473 -0
- vllm/model_executor/models/nemotron_vl.py +653 -0
- vllm/model_executor/models/nvlm_d.py +216 -0
- vllm/model_executor/models/olmo.py +413 -0
- vllm/model_executor/models/olmo2.py +455 -0
- vllm/model_executor/models/olmoe.py +494 -0
- vllm/model_executor/models/opencua.py +271 -0
- vllm/model_executor/models/openpangu.py +1051 -0
- vllm/model_executor/models/openpangu_mtp.py +265 -0
- vllm/model_executor/models/opt.py +426 -0
- vllm/model_executor/models/orion.py +366 -0
- vllm/model_executor/models/ouro.py +508 -0
- vllm/model_executor/models/ovis.py +559 -0
- vllm/model_executor/models/ovis2_5.py +673 -0
- vllm/model_executor/models/paddleocr_vl.py +1380 -0
- vllm/model_executor/models/paligemma.py +412 -0
- vllm/model_executor/models/persimmon.py +376 -0
- vllm/model_executor/models/phi.py +370 -0
- vllm/model_executor/models/phi3.py +18 -0
- vllm/model_executor/models/phi3v.py +737 -0
- vllm/model_executor/models/phi4_multimodal.py +1447 -0
- vllm/model_executor/models/phi4mm.py +1253 -0
- vllm/model_executor/models/phi4mm_audio.py +1296 -0
- vllm/model_executor/models/phi4mm_utils.py +1907 -0
- vllm/model_executor/models/phimoe.py +670 -0
- vllm/model_executor/models/pixtral.py +1380 -0
- vllm/model_executor/models/plamo2.py +966 -0
- vllm/model_executor/models/plamo3.py +441 -0
- vllm/model_executor/models/qwen.py +363 -0
- vllm/model_executor/models/qwen2.py +569 -0
- vllm/model_executor/models/qwen2_5_omni_thinker.py +1220 -0
- vllm/model_executor/models/qwen2_5_vl.py +1594 -0
- vllm/model_executor/models/qwen2_audio.py +473 -0
- vllm/model_executor/models/qwen2_moe.py +590 -0
- vllm/model_executor/models/qwen2_rm.py +123 -0
- vllm/model_executor/models/qwen2_vl.py +1593 -0
- vllm/model_executor/models/qwen3.py +332 -0
- vllm/model_executor/models/qwen3_moe.py +738 -0
- vllm/model_executor/models/qwen3_next.py +1390 -0
- vllm/model_executor/models/qwen3_next_mtp.py +296 -0
- vllm/model_executor/models/qwen3_omni_moe_thinker.py +1765 -0
- vllm/model_executor/models/qwen3_vl.py +1686 -0
- vllm/model_executor/models/qwen3_vl_moe.py +470 -0
- vllm/model_executor/models/qwen_vl.py +803 -0
- vllm/model_executor/models/radio.py +555 -0
- vllm/model_executor/models/registry.py +1183 -0
- vllm/model_executor/models/roberta.py +259 -0
- vllm/model_executor/models/rvl.py +107 -0
- vllm/model_executor/models/seed_oss.py +493 -0
- vllm/model_executor/models/siglip.py +1245 -0
- vllm/model_executor/models/siglip2navit.py +723 -0
- vllm/model_executor/models/skyworkr1v.py +953 -0
- vllm/model_executor/models/smolvlm.py +38 -0
- vllm/model_executor/models/solar.py +485 -0
- vllm/model_executor/models/stablelm.py +359 -0
- vllm/model_executor/models/starcoder2.py +366 -0
- vllm/model_executor/models/step3_text.py +555 -0
- vllm/model_executor/models/step3_vl.py +1149 -0
- vllm/model_executor/models/swin.py +514 -0
- vllm/model_executor/models/tarsier.py +619 -0
- vllm/model_executor/models/telechat2.py +153 -0
- vllm/model_executor/models/teleflm.py +78 -0
- vllm/model_executor/models/terratorch.py +319 -0
- vllm/model_executor/models/transformers/__init__.py +127 -0
- vllm/model_executor/models/transformers/base.py +464 -0
- vllm/model_executor/models/transformers/causal.py +65 -0
- vllm/model_executor/models/transformers/legacy.py +90 -0
- vllm/model_executor/models/transformers/moe.py +325 -0
- vllm/model_executor/models/transformers/multimodal.py +411 -0
- vllm/model_executor/models/transformers/pooling.py +119 -0
- vllm/model_executor/models/transformers/utils.py +213 -0
- vllm/model_executor/models/ultravox.py +686 -0
- vllm/model_executor/models/utils.py +832 -0
- vllm/model_executor/models/vision.py +552 -0
- vllm/model_executor/models/voxtral.py +842 -0
- vllm/model_executor/models/whisper.py +963 -0
- vllm/model_executor/models/zamba2.py +980 -0
- vllm/model_executor/parameter.py +642 -0
- vllm/model_executor/utils.py +94 -0
- vllm/model_executor/warmup/__init__.py +0 -0
- vllm/model_executor/warmup/deep_gemm_warmup.py +314 -0
- vllm/model_executor/warmup/kernel_warmup.py +98 -0
- vllm/multimodal/__init__.py +40 -0
- vllm/multimodal/audio.py +142 -0
- vllm/multimodal/base.py +26 -0
- vllm/multimodal/cache.py +830 -0
- vllm/multimodal/evs.py +294 -0
- vllm/multimodal/hasher.py +106 -0
- vllm/multimodal/image.py +130 -0
- vllm/multimodal/inputs.py +1036 -0
- vllm/multimodal/parse.py +544 -0
- vllm/multimodal/processing.py +2240 -0
- vllm/multimodal/profiling.py +369 -0
- vllm/multimodal/registry.py +357 -0
- vllm/multimodal/utils.py +523 -0
- vllm/multimodal/video.py +333 -0
- vllm/outputs.py +345 -0
- vllm/platforms/__init__.py +277 -0
- vllm/platforms/cpu.py +410 -0
- vllm/platforms/cuda.py +642 -0
- vllm/platforms/interface.py +656 -0
- vllm/platforms/rocm.py +513 -0
- vllm/platforms/tpu.py +275 -0
- vllm/platforms/xpu.py +261 -0
- vllm/plugins/__init__.py +81 -0
- vllm/plugins/io_processors/__init__.py +68 -0
- vllm/plugins/io_processors/interface.py +77 -0
- vllm/plugins/lora_resolvers/__init__.py +0 -0
- vllm/plugins/lora_resolvers/filesystem_resolver.py +52 -0
- vllm/pooling_params.py +230 -0
- vllm/profiler/__init__.py +0 -0
- vllm/profiler/gpu_profiler.py +216 -0
- vllm/profiler/layerwise_profile.py +392 -0
- vllm/profiler/utils.py +151 -0
- vllm/py.typed +2 -0
- vllm/ray/__init__.py +0 -0
- vllm/ray/lazy_utils.py +30 -0
- vllm/ray/ray_env.py +79 -0
- vllm/reasoning/__init__.py +92 -0
- vllm/reasoning/abs_reasoning_parsers.py +290 -0
- vllm/reasoning/basic_parsers.py +162 -0
- vllm/reasoning/deepseek_r1_reasoning_parser.py +67 -0
- vllm/reasoning/deepseek_v3_reasoning_parser.py +62 -0
- vllm/reasoning/ernie45_reasoning_parser.py +165 -0
- vllm/reasoning/glm4_moe_reasoning_parser.py +171 -0
- vllm/reasoning/gptoss_reasoning_parser.py +173 -0
- vllm/reasoning/granite_reasoning_parser.py +363 -0
- vllm/reasoning/hunyuan_a13b_reasoning_parser.py +237 -0
- vllm/reasoning/identity_reasoning_parser.py +58 -0
- vllm/reasoning/minimax_m2_reasoning_parser.py +67 -0
- vllm/reasoning/mistral_reasoning_parser.py +55 -0
- vllm/reasoning/olmo3_reasoning_parser.py +302 -0
- vllm/reasoning/qwen3_reasoning_parser.py +67 -0
- vllm/reasoning/seedoss_reasoning_parser.py +27 -0
- vllm/reasoning/step3_reasoning_parser.py +107 -0
- vllm/sampling_params.py +597 -0
- vllm/scalar_type.py +355 -0
- vllm/scripts.py +17 -0
- vllm/sequence.py +98 -0
- vllm/tasks.py +13 -0
- vllm/third_party/__init__.py +0 -0
- vllm/third_party/pynvml.py +6140 -0
- vllm/tokenizers/__init__.py +24 -0
- vllm/tokenizers/detokenizer_utils.py +198 -0
- vllm/tokenizers/hf.py +124 -0
- vllm/tokenizers/mistral.py +554 -0
- vllm/tokenizers/protocol.py +111 -0
- vllm/tokenizers/registry.py +233 -0
- vllm/tracing.py +135 -0
- vllm/transformers_utils/__init__.py +26 -0
- vllm/transformers_utils/chat_templates/__init__.py +5 -0
- vllm/transformers_utils/chat_templates/registry.py +73 -0
- vllm/transformers_utils/chat_templates/template_basic.jinja +3 -0
- vllm/transformers_utils/chat_templates/template_blip2.jinja +11 -0
- vllm/transformers_utils/chat_templates/template_chatml.jinja +10 -0
- vllm/transformers_utils/chat_templates/template_deepseek_ocr.jinja +14 -0
- vllm/transformers_utils/chat_templates/template_deepseek_vl2.jinja +23 -0
- vllm/transformers_utils/chat_templates/template_fuyu.jinja +3 -0
- vllm/transformers_utils/chat_templates/template_minicpmv45.jinja +93 -0
- vllm/transformers_utils/config.py +1081 -0
- vllm/transformers_utils/config_parser_base.py +20 -0
- vllm/transformers_utils/configs/__init__.py +84 -0
- vllm/transformers_utils/configs/afmoe.py +87 -0
- vllm/transformers_utils/configs/arctic.py +216 -0
- vllm/transformers_utils/configs/chatglm.py +75 -0
- vllm/transformers_utils/configs/deepseek_vl2.py +126 -0
- vllm/transformers_utils/configs/dotsocr.py +71 -0
- vllm/transformers_utils/configs/eagle.py +90 -0
- vllm/transformers_utils/configs/falcon.py +89 -0
- vllm/transformers_utils/configs/flex_olmo.py +82 -0
- vllm/transformers_utils/configs/hunyuan_vl.py +322 -0
- vllm/transformers_utils/configs/jais.py +243 -0
- vllm/transformers_utils/configs/kimi_linear.py +148 -0
- vllm/transformers_utils/configs/kimi_vl.py +38 -0
- vllm/transformers_utils/configs/lfm2_moe.py +163 -0
- vllm/transformers_utils/configs/medusa.py +65 -0
- vllm/transformers_utils/configs/midashenglm.py +103 -0
- vllm/transformers_utils/configs/mistral.py +235 -0
- vllm/transformers_utils/configs/mlp_speculator.py +69 -0
- vllm/transformers_utils/configs/moonvit.py +33 -0
- vllm/transformers_utils/configs/nemotron.py +214 -0
- vllm/transformers_utils/configs/nemotron_h.py +282 -0
- vllm/transformers_utils/configs/olmo3.py +83 -0
- vllm/transformers_utils/configs/ovis.py +182 -0
- vllm/transformers_utils/configs/qwen3_next.py +275 -0
- vllm/transformers_utils/configs/radio.py +89 -0
- vllm/transformers_utils/configs/speculators/__init__.py +2 -0
- vllm/transformers_utils/configs/speculators/algos.py +38 -0
- vllm/transformers_utils/configs/speculators/base.py +114 -0
- vllm/transformers_utils/configs/step3_vl.py +178 -0
- vllm/transformers_utils/configs/ultravox.py +118 -0
- vllm/transformers_utils/dynamic_module.py +59 -0
- vllm/transformers_utils/gguf_utils.py +209 -0
- vllm/transformers_utils/processor.py +423 -0
- vllm/transformers_utils/processors/__init__.py +23 -0
- vllm/transformers_utils/processors/deepseek_ocr.py +438 -0
- vllm/transformers_utils/processors/deepseek_vl2.py +406 -0
- vllm/transformers_utils/processors/hunyuan_vl.py +233 -0
- vllm/transformers_utils/processors/hunyuan_vl_image.py +477 -0
- vllm/transformers_utils/processors/ovis.py +453 -0
- vllm/transformers_utils/processors/ovis2_5.py +468 -0
- vllm/transformers_utils/repo_utils.py +287 -0
- vllm/transformers_utils/runai_utils.py +104 -0
- vllm/transformers_utils/s3_utils.py +95 -0
- vllm/transformers_utils/tokenizer.py +127 -0
- vllm/transformers_utils/tokenizer_base.py +33 -0
- vllm/transformers_utils/utils.py +184 -0
- vllm/triton_utils/__init__.py +20 -0
- vllm/triton_utils/importing.py +103 -0
- vllm/usage/__init__.py +0 -0
- vllm/usage/usage_lib.py +294 -0
- vllm/utils/__init__.py +66 -0
- vllm/utils/argparse_utils.py +504 -0
- vllm/utils/async_utils.py +310 -0
- vllm/utils/cache.py +214 -0
- vllm/utils/collection_utils.py +112 -0
- vllm/utils/counter.py +45 -0
- vllm/utils/deep_gemm.py +399 -0
- vllm/utils/flashinfer.py +532 -0
- vllm/utils/func_utils.py +236 -0
- vllm/utils/gc_utils.py +151 -0
- vllm/utils/hashing.py +81 -0
- vllm/utils/import_utils.py +449 -0
- vllm/utils/jsontree.py +158 -0
- vllm/utils/math_utils.py +32 -0
- vllm/utils/mem_constants.py +13 -0
- vllm/utils/mem_utils.py +232 -0
- vllm/utils/nccl.py +64 -0
- vllm/utils/network_utils.py +331 -0
- vllm/utils/platform_utils.py +59 -0
- vllm/utils/profiling.py +56 -0
- vllm/utils/registry.py +51 -0
- vllm/utils/serial_utils.py +169 -0
- vllm/utils/system_utils.py +265 -0
- vllm/utils/tensor_schema.py +255 -0
- vllm/utils/torch_utils.py +647 -0
- vllm/v1/__init__.py +0 -0
- vllm/v1/attention/__init__.py +0 -0
- vllm/v1/attention/backends/__init__.py +0 -0
- vllm/v1/attention/backends/cpu_attn.py +497 -0
- vllm/v1/attention/backends/flash_attn.py +1050 -0
- vllm/v1/attention/backends/flashinfer.py +1572 -0
- vllm/v1/attention/backends/flex_attention.py +945 -0
- vllm/v1/attention/backends/gdn_attn.py +387 -0
- vllm/v1/attention/backends/linear_attn.py +77 -0
- vllm/v1/attention/backends/mamba1_attn.py +165 -0
- vllm/v1/attention/backends/mamba2_attn.py +354 -0
- vllm/v1/attention/backends/mamba_attn.py +117 -0
- vllm/v1/attention/backends/mla/__init__.py +0 -0
- vllm/v1/attention/backends/mla/aiter_triton_mla.py +74 -0
- vllm/v1/attention/backends/mla/common.py +2069 -0
- vllm/v1/attention/backends/mla/cutlass_mla.py +278 -0
- vllm/v1/attention/backends/mla/flashattn_mla.py +340 -0
- vllm/v1/attention/backends/mla/flashinfer_mla.py +174 -0
- vllm/v1/attention/backends/mla/flashmla.py +317 -0
- vllm/v1/attention/backends/mla/flashmla_sparse.py +551 -0
- vllm/v1/attention/backends/mla/indexer.py +369 -0
- vllm/v1/attention/backends/mla/rocm_aiter_mla.py +275 -0
- vllm/v1/attention/backends/mla/rocm_aiter_mla_sparse.py +325 -0
- vllm/v1/attention/backends/mla/triton_mla.py +171 -0
- vllm/v1/attention/backends/pallas.py +436 -0
- vllm/v1/attention/backends/rocm_aiter_fa.py +1000 -0
- vllm/v1/attention/backends/rocm_aiter_unified_attn.py +206 -0
- vllm/v1/attention/backends/rocm_attn.py +359 -0
- vllm/v1/attention/backends/short_conv_attn.py +105 -0
- vllm/v1/attention/backends/tree_attn.py +428 -0
- vllm/v1/attention/backends/triton_attn.py +377 -0
- vllm/v1/attention/backends/utils.py +1149 -0
- vllm/v1/core/__init__.py +0 -0
- vllm/v1/core/block_pool.py +466 -0
- vllm/v1/core/encoder_cache_manager.py +343 -0
- vllm/v1/core/kv_cache_coordinator.py +570 -0
- vllm/v1/core/kv_cache_manager.py +408 -0
- vllm/v1/core/kv_cache_metrics.py +96 -0
- vllm/v1/core/kv_cache_utils.py +1471 -0
- vllm/v1/core/sched/__init__.py +0 -0
- vllm/v1/core/sched/async_scheduler.py +68 -0
- vllm/v1/core/sched/interface.py +187 -0
- vllm/v1/core/sched/output.py +230 -0
- vllm/v1/core/sched/request_queue.py +217 -0
- vllm/v1/core/sched/scheduler.py +1726 -0
- vllm/v1/core/sched/utils.py +72 -0
- vllm/v1/core/single_type_kv_cache_manager.py +801 -0
- vllm/v1/cudagraph_dispatcher.py +183 -0
- vllm/v1/engine/__init__.py +214 -0
- vllm/v1/engine/async_llm.py +874 -0
- vllm/v1/engine/coordinator.py +377 -0
- vllm/v1/engine/core.py +1421 -0
- vllm/v1/engine/core_client.py +1406 -0
- vllm/v1/engine/detokenizer.py +351 -0
- vllm/v1/engine/exceptions.py +18 -0
- vllm/v1/engine/input_processor.py +636 -0
- vllm/v1/engine/llm_engine.py +416 -0
- vllm/v1/engine/logprobs.py +189 -0
- vllm/v1/engine/output_processor.py +658 -0
- vllm/v1/engine/parallel_sampling.py +145 -0
- vllm/v1/engine/processor.py +20 -0
- vllm/v1/engine/utils.py +1068 -0
- vllm/v1/executor/__init__.py +6 -0
- vllm/v1/executor/abstract.py +352 -0
- vllm/v1/executor/multiproc_executor.py +888 -0
- vllm/v1/executor/ray_distributed_executor.py +8 -0
- vllm/v1/executor/ray_executor.py +626 -0
- vllm/v1/executor/ray_utils.py +465 -0
- vllm/v1/executor/uniproc_executor.py +183 -0
- vllm/v1/kv_cache_interface.py +404 -0
- vllm/v1/kv_offload/__init__.py +0 -0
- vllm/v1/kv_offload/abstract.py +161 -0
- vllm/v1/kv_offload/arc_manager.py +237 -0
- vllm/v1/kv_offload/backend.py +97 -0
- vllm/v1/kv_offload/backends/__init__.py +0 -0
- vllm/v1/kv_offload/backends/cpu.py +62 -0
- vllm/v1/kv_offload/cpu.py +86 -0
- vllm/v1/kv_offload/factory.py +56 -0
- vllm/v1/kv_offload/lru_manager.py +139 -0
- vllm/v1/kv_offload/mediums.py +39 -0
- vllm/v1/kv_offload/spec.py +66 -0
- vllm/v1/kv_offload/worker/__init__.py +0 -0
- vllm/v1/kv_offload/worker/cpu_gpu.py +191 -0
- vllm/v1/kv_offload/worker/worker.py +144 -0
- vllm/v1/metrics/__init__.py +0 -0
- vllm/v1/metrics/loggers.py +1268 -0
- vllm/v1/metrics/prometheus.py +82 -0
- vllm/v1/metrics/ray_wrappers.py +194 -0
- vllm/v1/metrics/reader.py +257 -0
- vllm/v1/metrics/stats.py +431 -0
- vllm/v1/outputs.py +237 -0
- vllm/v1/pool/__init__.py +0 -0
- vllm/v1/pool/metadata.py +82 -0
- vllm/v1/request.py +280 -0
- vllm/v1/sample/__init__.py +0 -0
- vllm/v1/sample/logits_processor/__init__.py +352 -0
- vllm/v1/sample/logits_processor/builtin.py +278 -0
- vllm/v1/sample/logits_processor/interface.py +106 -0
- vllm/v1/sample/logits_processor/state.py +165 -0
- vllm/v1/sample/metadata.py +44 -0
- vllm/v1/sample/ops/__init__.py +0 -0
- vllm/v1/sample/ops/bad_words.py +52 -0
- vllm/v1/sample/ops/logprobs.py +25 -0
- vllm/v1/sample/ops/penalties.py +57 -0
- vllm/v1/sample/ops/topk_topp_sampler.py +384 -0
- vllm/v1/sample/rejection_sampler.py +805 -0
- vllm/v1/sample/sampler.py +319 -0
- vllm/v1/sample/tpu/__init__.py +0 -0
- vllm/v1/sample/tpu/metadata.py +120 -0
- vllm/v1/sample/tpu/sampler.py +215 -0
- vllm/v1/serial_utils.py +532 -0
- vllm/v1/spec_decode/__init__.py +0 -0
- vllm/v1/spec_decode/eagle.py +1325 -0
- vllm/v1/spec_decode/medusa.py +73 -0
- vllm/v1/spec_decode/metadata.py +66 -0
- vllm/v1/spec_decode/metrics.py +225 -0
- vllm/v1/spec_decode/ngram_proposer.py +291 -0
- vllm/v1/spec_decode/suffix_decoding.py +101 -0
- vllm/v1/spec_decode/utils.py +121 -0
- vllm/v1/structured_output/__init__.py +338 -0
- vllm/v1/structured_output/backend_guidance.py +265 -0
- vllm/v1/structured_output/backend_lm_format_enforcer.py +177 -0
- vllm/v1/structured_output/backend_outlines.py +324 -0
- vllm/v1/structured_output/backend_types.py +136 -0
- vllm/v1/structured_output/backend_xgrammar.py +362 -0
- vllm/v1/structured_output/request.py +94 -0
- vllm/v1/structured_output/utils.py +469 -0
- vllm/v1/utils.py +414 -0
- vllm/v1/worker/__init__.py +0 -0
- vllm/v1/worker/block_table.py +343 -0
- vllm/v1/worker/cpu_model_runner.py +122 -0
- vllm/v1/worker/cpu_worker.py +210 -0
- vllm/v1/worker/dp_utils.py +250 -0
- vllm/v1/worker/ec_connector_model_runner_mixin.py +87 -0
- vllm/v1/worker/gpu/README.md +4 -0
- vllm/v1/worker/gpu/__init__.py +0 -0
- vllm/v1/worker/gpu/async_utils.py +97 -0
- vllm/v1/worker/gpu/attn_utils.py +189 -0
- vllm/v1/worker/gpu/block_table.py +314 -0
- vllm/v1/worker/gpu/cudagraph_utils.py +259 -0
- vllm/v1/worker/gpu/dp_utils.py +31 -0
- vllm/v1/worker/gpu/input_batch.py +430 -0
- vllm/v1/worker/gpu/model_runner.py +1007 -0
- vllm/v1/worker/gpu/sample/__init__.py +0 -0
- vllm/v1/worker/gpu/sample/gumbel.py +101 -0
- vllm/v1/worker/gpu/sample/logprob.py +167 -0
- vllm/v1/worker/gpu/sample/metadata.py +179 -0
- vllm/v1/worker/gpu/sample/penalties.py +154 -0
- vllm/v1/worker/gpu/sample/sampler.py +75 -0
- vllm/v1/worker/gpu/spec_decode/__init__.py +18 -0
- vllm/v1/worker/gpu/spec_decode/eagle.py +565 -0
- vllm/v1/worker/gpu/spec_decode/eagle_cudagraph.py +115 -0
- vllm/v1/worker/gpu/spec_decode/rejection_sample.py +83 -0
- vllm/v1/worker/gpu/states.py +309 -0
- vllm/v1/worker/gpu/structured_outputs.py +76 -0
- vllm/v1/worker/gpu_input_batch.py +971 -0
- vllm/v1/worker/gpu_model_runner.py +5360 -0
- vllm/v1/worker/gpu_ubatch_wrapper.py +472 -0
- vllm/v1/worker/gpu_worker.py +922 -0
- vllm/v1/worker/kv_connector_model_runner_mixin.py +309 -0
- vllm/v1/worker/lora_model_runner_mixin.py +212 -0
- vllm/v1/worker/tpu_input_batch.py +583 -0
- vllm/v1/worker/tpu_model_runner.py +2196 -0
- vllm/v1/worker/tpu_worker.py +351 -0
- vllm/v1/worker/ubatch_utils.py +73 -0
- vllm/v1/worker/ubatching.py +231 -0
- vllm/v1/worker/utils.py +365 -0
- vllm/v1/worker/worker_base.py +377 -0
- vllm/v1/worker/xpu_model_runner.py +48 -0
- vllm/v1/worker/xpu_worker.py +198 -0
- vllm/version.py +39 -0
- vllm/vllm_flash_attn/.gitkeep +0 -0
- vllm_cpu-0.12.0.dist-info/METADATA +300 -0
- vllm_cpu-0.12.0.dist-info/RECORD +1600 -0
- vllm_cpu-0.12.0.dist-info/WHEEL +5 -0
- vllm_cpu-0.12.0.dist-info/entry_points.txt +5 -0
- vllm_cpu-0.12.0.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,1600 @@
|
|
|
1
|
+
vllm/_C.abi3.so,sha256=RTSzIqs60oGJdX3bq0W_HsG4T5aB-jfK4_T_I5DYuiU,33563712
|
|
2
|
+
vllm/__init__.py,sha256=fS_Nsr5gWhdic4rOVRUVgy1PvdSFt-iIxjh_wb1-KHY,3881
|
|
3
|
+
vllm/_aiter_ops.py,sha256=4z29GEFL-EiHp0dEW3E4Fg5cgpnfKEwI1bTTY6qRADA,30570
|
|
4
|
+
vllm/_bc_linter.py,sha256=2F7ZE_cba80XNDfbrZKVBunazE7ZDxVMtpOUdEFdH3w,1105
|
|
5
|
+
vllm/_custom_ops.py,sha256=dhNI82k9i669CJ5eugUsgLooBPgghvJKujpGTdwKn8Q,86422
|
|
6
|
+
vllm/_ipex_ops.py,sha256=L8DTX14Xfc7WFfckWdCM5X6B3oMJSJ63UrC7Fj9g50Q,14935
|
|
7
|
+
vllm/_version.py,sha256=VDAgmYWykomGcTucvPJWNS0ePk26QojGHvaE9chtgGc,706
|
|
8
|
+
vllm/beam_search.py,sha256=XUQRXltedVFtJRp43dKHKn87VqKeG5tr494D0yHemHM,2593
|
|
9
|
+
vllm/collect_env.py,sha256=7peWZtL6DVINkwdvI59rI7mHs0WfT3WEvlbsSjzeNow,28050
|
|
10
|
+
vllm/connections.py,sha256=LpQUe9gGRiBCIGY6RWUGi_7d8ql6tO2jYNecU1EJR6c,5350
|
|
11
|
+
vllm/env_override.py,sha256=FkeUiVHGa_VDP7CNPu9Sn7NzdECBfA9K39eM0vwyqUk,13808
|
|
12
|
+
vllm/envs.py,sha256=xBB1Cl7wSZjQhSovrAxjKpb26TXHadIpQcZVi3MNUWE,77393
|
|
13
|
+
vllm/forward_context.py,sha256=bzTGTprH83_ejByyqUUhOsEHc6SN7bAL9HRTQuDO_zo,13416
|
|
14
|
+
vllm/logger.py,sha256=sybtD6xmg7UttpqLJ2Y9j4-3KVl7PujCXHd6BLhENhw,10265
|
|
15
|
+
vllm/logits_process.py,sha256=LrREP4uv0gPh2VQcG4t-4hedJoRoJWkywUAMOIrG-VE,4340
|
|
16
|
+
vllm/logprobs.py,sha256=uHUJbySQJ02OFp-kgr0gB_ZXnfuAm6SDHwHZ-rRQlqI,7907
|
|
17
|
+
vllm/outputs.py,sha256=qhKihxRd0aVm8rL8DvViVzBiuoFrOX24HH_Kn31k_CI,12563
|
|
18
|
+
vllm/pooling_params.py,sha256=yYEtFxLm0_Lmkf6Y9Z5YQPMChsNumjJmnYC0hBdy0Cg,8789
|
|
19
|
+
vllm/py.typed,sha256=F5LUrt0voM87SNuuOky2X9veCVDqJUgRg_VohYqDigY,65
|
|
20
|
+
vllm/sampling_params.py,sha256=zjUaz5_zbLFrD5h4Z5gAGgXTSLdkT5K9LidXohdvEG4,24466
|
|
21
|
+
vllm/scalar_type.py,sha256=s8CZpZru6-4vEexIofKsJzhw5OBjVuvueG6b6yb6A94,12573
|
|
22
|
+
vllm/scripts.py,sha256=d2RU3e6Qi_xY7QUD44uqsdz8DdBR-_zQnFf4rYUW_iw,504
|
|
23
|
+
vllm/sequence.py,sha256=1_wfrC7M7xMnerklKjmf2AcQe9ttQPhMkq6_quGa7kw,3489
|
|
24
|
+
vllm/tasks.py,sha256=8s7iKgpdisoALAsu98kCxHNMYP6ebdp8uRpWvd_Cu68,437
|
|
25
|
+
vllm/tracing.py,sha256=BaBpIGie6_A-ee_XEzu_-aGWkGt_stgeq_b1M3Q8kb0,5043
|
|
26
|
+
vllm/version.py,sha256=vXpCd2tjC2EeL1-kaYvJfh9PJYPDXMskbsLnvUPIMxM,1339
|
|
27
|
+
vllm/assets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
28
|
+
vllm/assets/audio.py,sha256=gDEsheV3FDEIX9U5xGdllwMYB1qF5_QYpU8Fj36zkP4,1185
|
|
29
|
+
vllm/assets/base.py,sha256=SErfS4p7zJUe_sJBBwR539_1dy49vsBwl0tAi5aPRHY,1215
|
|
30
|
+
vllm/assets/image.py,sha256=W2qpY_yGQa3x67Oag1u3Hazpu-rPxB3SEJcOB0qA4Bk,1483
|
|
31
|
+
vllm/assets/video.py,sha256=7ulapb3jq2MqKxEVrhzPWgIbcv-CDEfjYMA1cSWPa4E,4487
|
|
32
|
+
vllm/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
33
|
+
vllm/attention/layer.py,sha256=jq7ypRuvvp2WPyxTKeTP8WxhIyhhwFp6emRMVTStUQs,35339
|
|
34
|
+
vllm/attention/selector.py,sha256=mI8cpVZgKDkgFMQfVxhWpGgzAaNBdusOnn9oAa26pxo,8437
|
|
35
|
+
vllm/attention/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
36
|
+
vllm/attention/backends/abstract.py,sha256=quVidkpHd6euk7d8kMPNTNLykKcEgJP1B6ctXpzgOcI,14244
|
|
37
|
+
vllm/attention/backends/registry.py,sha256=1SeonV-JfY3Ar8LOE0bGGUM7ixrQhI3Asg9-RN0ZXUY,10519
|
|
38
|
+
vllm/attention/backends/utils.py,sha256=_Z7h3rbFlbw6zEmd9wOTtvrx3OF8gZ-7N2wo0yp81oo,857
|
|
39
|
+
vllm/attention/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
40
|
+
vllm/attention/layers/chunked_local_attention.py,sha256=KYEklnHHJTYnOibI5nfLuLezub9-t2vDsr6kKnKIMsw,4237
|
|
41
|
+
vllm/attention/layers/cross_attention.py,sha256=AHySzV3AVLg-11-q3ifZLN2_klJBIzx2-XcAqSiwK5I,6307
|
|
42
|
+
vllm/attention/layers/encoder_only_attention.py,sha256=p7rH1yRLdPI5oMvnewxrBwX0vK9an18U2v6JYvMrplQ,3073
|
|
43
|
+
vllm/attention/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
44
|
+
vllm/attention/ops/chunked_prefill_paged_decode.py,sha256=iT-VbCwzjyaNLH98vnqo3H-ASyNOQYcSLu8BoGs4BiY,13068
|
|
45
|
+
vllm/attention/ops/common.py,sha256=_v4nUo8OUrwYx6k-d0d8ClbksqU4ZP9vEjwV67MQYUw,13701
|
|
46
|
+
vllm/attention/ops/flashmla.py,sha256=Zthte13CPZ8HjtPYmqMKjHFtPW9kUZXsu7htIRkR9P8,8314
|
|
47
|
+
vllm/attention/ops/merge_attn_states.py,sha256=SEVz4_z-x2DC1hqtGdkjkYs8olYmGjZmpwnV-oo81Ns,1657
|
|
48
|
+
vllm/attention/ops/paged_attn.py,sha256=tY3DkiH7gZF4KMLRUds_mi_a3ez7FiSbqt6ps05e_PQ,1413
|
|
49
|
+
vllm/attention/ops/pallas_kv_cache_update.py,sha256=wbl56j_Wv9PEseDhkjZcKurNO-CV785P8fRsjVR10ho,4190
|
|
50
|
+
vllm/attention/ops/prefix_prefill.py,sha256=yYrV900OQWKvYBDPhuq2lUci7gXnqJxfErAugrRwA0M,25201
|
|
51
|
+
vllm/attention/ops/rocm_aiter_mla_sparse.py,sha256=n7CWX0Amq66_JcDYkGREZmz4WVeMkJxHmh1wbFdk9Uc,7673
|
|
52
|
+
vllm/attention/ops/triton_decode_attention.py,sha256=9v1XfYlUcrX7j4aYDYKEud8DCVsdltKavp3ucYe1bco,19515
|
|
53
|
+
vllm/attention/ops/triton_merge_attn_states.py,sha256=4fOT2PY6AocmhvwAYt5Zu1PFIQ9lWAdqCxWd24YMW6c,3982
|
|
54
|
+
vllm/attention/ops/triton_reshape_and_cache_flash.py,sha256=R62WxvWZeCdOOHDWl4Fl5565xWz5fdXN9aay2aJ6Vhs,5968
|
|
55
|
+
vllm/attention/ops/triton_unified_attention.py,sha256=0m-vgM-ZCSd-HddgTGZs-U9nBoQthk0uqsINFdw-sGg,32453
|
|
56
|
+
vllm/attention/ops/vit_attn_wrappers.py,sha256=m8yaKBM7hlbMlwqzPm0jBNX9wshdgwGTYqgBW-ZQSRc,3924
|
|
57
|
+
vllm/attention/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
58
|
+
vllm/attention/utils/fa_utils.py,sha256=LmoQpOAD1-NHbdBOCQ5HD_kcjddx7Y7FSK2C6TaqSQ0,3707
|
|
59
|
+
vllm/attention/utils/kv_sharing_utils.py,sha256=o4YaEd_bjYU6fQq0L5dEdhz9r4aZP1uJ6RBrVwtdX4M,1615
|
|
60
|
+
vllm/attention/utils/kv_transfer_utils.py,sha256=-dUtRw8Zu1hBTcMuemUe3zQjzjQ5UeN2gndokVENtuU,2009
|
|
61
|
+
vllm/benchmarks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
62
|
+
vllm/benchmarks/datasets.py,sha256=i_vuzD3gotFcrHFyuG_3OSUMLUu5NQBq0oPXkzrJuZQ,120063
|
|
63
|
+
vllm/benchmarks/latency.py,sha256=ubZUzbP14GlHMIVJETQq9YFyC_4ROGX2Oo2Kkq4QU9w,5869
|
|
64
|
+
vllm/benchmarks/serve.py,sha256=iIAfBWmH2J0fGfqG5RsrKl3iPaoNW06cyZzj8wDgFiA,55498
|
|
65
|
+
vllm/benchmarks/throughput.py,sha256=EWszDhrlwSVGUkvVJ7VlSmu8y7Q3yQzuJf_NcbSljF8,28814
|
|
66
|
+
vllm/benchmarks/lib/__init__.py,sha256=BlbNrv7ga0LXYeHLKKiey2woiGh5MkW36g7QG6L6BN0,142
|
|
67
|
+
vllm/benchmarks/lib/endpoint_request_func.py,sha256=6JoTGH3VnTu6IaFusduLvZhBS8dQcnkQmwlxM7ojbQQ,26362
|
|
68
|
+
vllm/benchmarks/lib/ready_checker.py,sha256=QXyydJaq4m1EFdHtpuobeHykIKnwgOawe-ZZbS-jweM,2346
|
|
69
|
+
vllm/benchmarks/lib/utils.py,sha256=YMFxp0A81__5oZJ8wp-PyqOlbYGuxovcVMZzR6v9XJo,2449
|
|
70
|
+
vllm/benchmarks/sweep/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
71
|
+
vllm/benchmarks/sweep/cli.py,sha256=bqyJ0NJrCW46-ENf_XHHdXtR0tyKkVdI-yIyIZ5L76g,1337
|
|
72
|
+
vllm/benchmarks/sweep/param_sweep.py,sha256=Iz6RzAe08vJ1B7ig1ncGf4SF-q2nnG2c1KCT0pGzmrA,3035
|
|
73
|
+
vllm/benchmarks/sweep/plot.py,sha256=ZaW0MIImMqB6NDFmHdvNLE1Ud2L0HuSJJSWVmDDw6Wg,16469
|
|
74
|
+
vllm/benchmarks/sweep/plot_pareto.py,sha256=MnyM4Lyw-eWe9bIkWXH9Bmgy3gBAkY63JYfhrNVfbU8,10959
|
|
75
|
+
vllm/benchmarks/sweep/serve.py,sha256=GEMphF4Aiqht19yuT1EQnzgx4vKnSK4Pr-ymE-7KsEI,13050
|
|
76
|
+
vllm/benchmarks/sweep/serve_sla.py,sha256=GVq10xa6quOr_BJi1u4FYXib1LcXEFTksJCBih6lrU4,13978
|
|
77
|
+
vllm/benchmarks/sweep/server.py,sha256=QAT4ixDPla1lCbWcKMPksQj5fM5uiAOq7HWsrU94Bpw,3588
|
|
78
|
+
vllm/benchmarks/sweep/sla_sweep.py,sha256=AuxpVkWFrfJPFFcFYMAa_5RdIHNvdwpW-X2WRtsD0rE,3674
|
|
79
|
+
vllm/benchmarks/sweep/utils.py,sha256=YzhiqE4jmEN7TzUnzQXnlm8TLERkNjgoQ_SF6jJ8hB4,232
|
|
80
|
+
vllm/compilation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
81
|
+
vllm/compilation/activation_quant_fusion.py,sha256=HcKJLon0bK7VSPHQV-fxSTDbefeW_-G7dAH_9fP-tjo,6492
|
|
82
|
+
vllm/compilation/backends.py,sha256=aEyRnIcuwZhpIow-sXpvaVynGSaTvkAGcZZ0HvFbSdw,31458
|
|
83
|
+
vllm/compilation/base_static_graph.py,sha256=XP6OBtuEqkLNQc3ZPr6TrwCzokLIARBCBXUw4pIrUjo,2007
|
|
84
|
+
vllm/compilation/caching.py,sha256=e3hSb4_TuH096esHEydK9ZFWOvMoFTAtDirzL1ImPMU,6843
|
|
85
|
+
vllm/compilation/collective_fusion.py,sha256=p15SUc9wMrkJo3mSG3BOaBnVpqyofmEKzkjQMDgnFp4,44308
|
|
86
|
+
vllm/compilation/compiler_interface.py,sha256=8VoHWFz8vfqmRV-4EBsSb5IYeduPo5ziQsSDq_gvDS8,24472
|
|
87
|
+
vllm/compilation/counter.py,sha256=Nr75qGYyNzHhCvpWa1SWxPxZme5h1sSNNNEtYYJxknM,1638
|
|
88
|
+
vllm/compilation/cuda_graph.py,sha256=a1GPTU6cN4hshys5WlCVkyJej6n5XFsYgswaX7oStHo,9050
|
|
89
|
+
vllm/compilation/decorators.py,sha256=WGp5cj9-rztxio6dZNgIKeqe1mC4KosQU0dkKOUrbtA,23738
|
|
90
|
+
vllm/compilation/fix_functionalization.py,sha256=gW4rX9NbVnqOgqC62svzHAtaza6MEeMrEdBzHz0hRAs,10545
|
|
91
|
+
vllm/compilation/fusion.py,sha256=pmFZXc0ckZIAEffmNMyF3kbiFIFD1clxw9WkuIp0E54,12481
|
|
92
|
+
vllm/compilation/fusion_attn.py,sha256=pOjGQEXn7zKEeNvhGYdJ60AUC0lHfedyYXMsLP_TUcc,12233
|
|
93
|
+
vllm/compilation/fx_utils.py,sha256=w89dD5KnsAMXJmIiQOceZfEkySmnXgObNRsfXJgbvIE,3185
|
|
94
|
+
vllm/compilation/inductor_pass.py,sha256=UlOj0qwyB6FJdvUTOh22Iw5oaUbGFWAI4dGuBjDHzfE,3983
|
|
95
|
+
vllm/compilation/matcher_utils.py,sha256=ny2YuE6QNFFc4GA_oEA4BQOe2TLqyjqZG3wkePAHH94,9994
|
|
96
|
+
vllm/compilation/monitor.py,sha256=tmsTH8SVaKV2TpMbfcVEqBxxKawBON-pgACP0VGRLDE,2100
|
|
97
|
+
vllm/compilation/noop_elimination.py,sha256=_RnMhU5GCjo18ISBwBkarAPS0SUfJSAigbcPIcHFJ_Q,5351
|
|
98
|
+
vllm/compilation/partition_rules.py,sha256=wVUBgr73FzDfyIVhAIt2wgpnEZhGsaA8Unuw_B8_xRI,2213
|
|
99
|
+
vllm/compilation/pass_manager.py,sha256=r41ZQt_1dvIGMGpxi8zuVPlwNxvaJc0YdXSAvHMPwh4,5079
|
|
100
|
+
vllm/compilation/piecewise_backend.py,sha256=NOJ3UPFfAEqZyDSE6aW-5VeJP1QE7J_RH4JNZLP-nYE,4422
|
|
101
|
+
vllm/compilation/post_cleanup.py,sha256=z0Jbq_dQDFzRTrUZUcvE5prvDUxQ7ItogQrEnYdxVzE,758
|
|
102
|
+
vllm/compilation/qk_norm_rope_fusion.py,sha256=myW_oO7JwqGxaOPvRzElPnz1qQrZMs-LG93CkF7KXd4,8524
|
|
103
|
+
vllm/compilation/sequence_parallelism.py,sha256=qkihTBh3a1JL6HoiDjCjkEixkDfV-tnxChxugTgqkMo,14029
|
|
104
|
+
vllm/compilation/torch25_custom_graph_pass.py,sha256=9r4T74gV7PxjalJDxyDOOGPyCc8xUWMPAe_gYdTWgwI,1413
|
|
105
|
+
vllm/compilation/vllm_inductor_pass.py,sha256=v_bRjbaI1G8Wn4UkSPULHmECLvuPCT44Nphmsf-NP40,6490
|
|
106
|
+
vllm/compilation/wrapper.py,sha256=IpuwPUQsH3NCWbeerFcHbKGqHae_D51_arBlk7BYg7E,10506
|
|
107
|
+
vllm/config/__init__.py,sha256=zv74dRyPFfyx1m-EHUiEYqpGlOTdpe1NdbEthZgK-kI,3002
|
|
108
|
+
vllm/config/cache.py,sha256=BFnUAkqU60gTUf05SYUFB0Cxtxguo7Tq73Xo6fw_uqs,10204
|
|
109
|
+
vllm/config/compilation.py,sha256=X5n7WEEHGoiyORXQyrZYAg5zjlXZW_xhoonUsrPv0xc,47965
|
|
110
|
+
vllm/config/device.py,sha256=Ilhly88mxXGjDAD6iDRqg4pbBEJKX8OSu-IKqi3RyCc,2773
|
|
111
|
+
vllm/config/ec_transfer.py,sha256=_D5VNYNy8CU7IrTkDm9IB5PF9Y4CBCqzyijl-kYgWpk,3863
|
|
112
|
+
vllm/config/kv_events.py,sha256=-JSREpsV49ohD7songzjiHiLhJguL2v1r4_cx7po--0,1645
|
|
113
|
+
vllm/config/kv_transfer.py,sha256=cbLTBd4xG0eM2jZGv7ffVPocjqDD_WuK8qutrY9Ldr8,4042
|
|
114
|
+
vllm/config/load.py,sha256=B3pHwaKzjaIDKXvXr5JLNHsoL0lHCx2xXN5GQ2anJN0,5751
|
|
115
|
+
vllm/config/lora.py,sha256=viqi3wqJpEUmkVGmXgRHj9-Rzjc-LUJMEO99GXwRToQ,3716
|
|
116
|
+
vllm/config/model.py,sha256=zUmZIrZu6ZLOwQ_Rhqr50eJrBbbCj-bKr2u1foNbEKc,91427
|
|
117
|
+
vllm/config/multimodal.py,sha256=0H5_x_J-4jWI1u6iJLCUH-IGmJK2Ku0BUKRoOLDOoBI,9985
|
|
118
|
+
vllm/config/observability.py,sha256=2TsuzBVFJCnK5-jIrQLESUbX8XQ3EA-rQIk77FACxyg,5356
|
|
119
|
+
vllm/config/parallel.py,sha256=1r3G3jCvmn1HxsWYdcx5HxyCcMqvjajezEwBl3767cI,27550
|
|
120
|
+
vllm/config/pooler.py,sha256=XnvDq5yxFP3roAPqS6yPP_jwDblPmC-fdGl6M6_dWkY,4201
|
|
121
|
+
vllm/config/scheduler.py,sha256=ja5FZe7U1aCqfyIFZpMQr2mDM0GnKseQhA1F9DPa1p0,12345
|
|
122
|
+
vllm/config/speculative.py,sha256=koirWHCVYiNW49cKQbBXAP3mrZoMEiyUaU0xDWrvcQc,28668
|
|
123
|
+
vllm/config/speech_to_text.py,sha256=nNeiXvk1d16si_w_w8eEREEKeylq1b_gSyNFfH_OFJs,1462
|
|
124
|
+
vllm/config/structured_outputs.py,sha256=QhCd91kv3V0lF-lb-HsuPgHsD1fKOOAuSdeCxkzsSqI,4048
|
|
125
|
+
vllm/config/utils.py,sha256=j06bPpHCDywdUctl5vu_o8KbQAVZA443kZIyVCZoFUw,11181
|
|
126
|
+
vllm/config/vllm.py,sha256=egUUxGMDPoCJTItFxpsOlpBuKsDrZXjD-j8f2KyLhD4,58933
|
|
127
|
+
vllm/device_allocator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
128
|
+
vllm/device_allocator/cumem.py,sha256=tIx6IZI6r4DMS4MbhuAdrcLM5hN-BCFjoGLSsXBX6hs,12483
|
|
129
|
+
vllm/distributed/__init__.py,sha256=l_KMMLMmYq-MqxY5OeTuQjA38RYwdS4TtVy8JafQq3E,191
|
|
130
|
+
vllm/distributed/communication_op.py,sha256=PD-Kxg2zjs6JHTncHi9vGUetQ4aFiT0uV3fQcjIL0bg,1323
|
|
131
|
+
vllm/distributed/kv_events.py,sha256=3z_NXsaQoCKWInLhKzQlAJHKhv6UIsyrtSJ-4NzhP-Q,12437
|
|
132
|
+
vllm/distributed/parallel_state.py,sha256=iru16NHBgXOSFHmz3CxaFPIaJlso8QbGbFkXveo_Lro,65161
|
|
133
|
+
vllm/distributed/tpu_distributed_utils.py,sha256=LHc2lCK_zeODmV5loJV7Eq9Pg8hfplEh4aWN-A-nawo,7585
|
|
134
|
+
vllm/distributed/utils.py,sha256=Q9_wTnhTgMQWk3cPYdGFQJdg4B6VyFVeoCPigIKPfXs,20792
|
|
135
|
+
vllm/distributed/device_communicators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
136
|
+
vllm/distributed/device_communicators/all2all.py,sha256=RUfFZpEIxXmCKrNkIKZnVQysUQf7uY24MB24fw9q--g,16263
|
|
137
|
+
vllm/distributed/device_communicators/all_reduce_utils.py,sha256=FXN49WKCqJM3WKxMlQntN1xVwrlss5IjrGRXjfIaoYY,12324
|
|
138
|
+
vllm/distributed/device_communicators/base_device_communicator.py,sha256=mwMTx-DdFEdPyTEUbaPghlCuodhNboqRGKaJ9QQmM0I,10711
|
|
139
|
+
vllm/distributed/device_communicators/cpu_communicator.py,sha256=IyRrYtDIw9suqbBxpKBYgvKOKdEk7egpnOeQtk3keQ0,6966
|
|
140
|
+
vllm/distributed/device_communicators/cuda_communicator.py,sha256=y5o76GD9r6WGsMCrdxz9MxQ085sTWvaI1VXF6ZBfVOg,13439
|
|
141
|
+
vllm/distributed/device_communicators/cuda_wrapper.py,sha256=Yj-IHZt2nWAksvsmi88JAC8XNYht8Ylz748guEujWMc,8411
|
|
142
|
+
vllm/distributed/device_communicators/custom_all_reduce.py,sha256=qwIMODFiNFmXGFWjr9wyzXZ6dl6WASbya1wEqAEmXP0,12857
|
|
143
|
+
vllm/distributed/device_communicators/mnnvl_compat.py,sha256=A5UvRWaIyPRQkw4dSd4Mq6sy2I655Wf0bHkKM7aPMZc,830
|
|
144
|
+
vllm/distributed/device_communicators/pynccl.py,sha256=IZRiSwMlWK-yS5cwGBPr7kn4Ov4XSVhA61aVP5ggpxs,13902
|
|
145
|
+
vllm/distributed/device_communicators/pynccl_allocator.py,sha256=SU2hhkqueFQAC5GdvEZyEhxriN0ueUNpRh-n4pXRWxw,6247
|
|
146
|
+
vllm/distributed/device_communicators/pynccl_wrapper.py,sha256=iG602w2gqZOwuhULKP_PF2ywJBN-ZDcE11jJEQdhAZI,18840
|
|
147
|
+
vllm/distributed/device_communicators/quick_all_reduce.py,sha256=IxoLQ89rCXr_SbJPLWDK7t-w23EUzv2zWEO7C_QrdkA,10887
|
|
148
|
+
vllm/distributed/device_communicators/ray_communicator.py,sha256=Myw39lSVtgVk1h21m8LTDKAjatwzRC0BRkeQvemuyJc,9122
|
|
149
|
+
vllm/distributed/device_communicators/shm_broadcast.py,sha256=YnHR3eB7_aYl4KxNrgyHuNDQYMZM4IJnaG_eiAO4xXQ,30277
|
|
150
|
+
vllm/distributed/device_communicators/shm_object_storage.py,sha256=4OET8UnO1l2u24FmndJS9JEqnp30gs94lpO3S60Se4g,27538
|
|
151
|
+
vllm/distributed/device_communicators/symm_mem.py,sha256=fgc15QF836cFul6AQ8dJDI-xw8P5_wK8qLnczYOoHV0,5395
|
|
152
|
+
vllm/distributed/device_communicators/tpu_communicator.py,sha256=FDCGHBnwSRm8kBjUiZ6RFXmloBBlwLrDEqpV-5mgRZQ,4025
|
|
153
|
+
vllm/distributed/device_communicators/xpu_communicator.py,sha256=eHZdPFturEqH1WUJC-Yy56jY9jsY0CRiUY8B3JzarSo,3423
|
|
154
|
+
vllm/distributed/ec_transfer/__init__.py,sha256=TfKcHCVJ27cpYAxvVMFyrBZe40qJfxEX6GeWdCOcIoc,348
|
|
155
|
+
vllm/distributed/ec_transfer/ec_transfer_state.py,sha256=60Iu-N4qVnjSa2kXaysANPa77HX-cYomPTu7GRk5Evw,1152
|
|
156
|
+
vllm/distributed/ec_transfer/ec_connector/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
157
|
+
vllm/distributed/ec_transfer/ec_connector/base.py,sha256=L6ZTjzL6kIXUyRVsA6ldI4AahpRSbEL3NAMTqwJJf60,8029
|
|
158
|
+
vllm/distributed/ec_transfer/ec_connector/factory.py,sha256=KWz7IKBKQh2s1xeTu92VbMVIaDTM4UaKNjiUJDI2qPU,3089
|
|
159
|
+
vllm/distributed/ec_transfer/ec_connector/shared_storage_connector.py,sha256=NhXdHEnwqcrihsc2P_bRLyPzeQDgneMAwluJqkUNeyY,7322
|
|
160
|
+
vllm/distributed/eplb/__init__.py,sha256=84KX6CIcar6LmWgwmA7huMJaUKlCdFQ6sCEnCQJ8geY,213
|
|
161
|
+
vllm/distributed/eplb/async_worker.py,sha256=sZQLHttEwCVF_0RGWMV2hqx5EQfG3bsvEga-7jjpykg,4211
|
|
162
|
+
vllm/distributed/eplb/eplb_state.py,sha256=W3PHLwScOLsi_qH4WWIUERrp3eurpxGzYWHlLMywHDU,45491
|
|
163
|
+
vllm/distributed/eplb/rebalance_algo.py,sha256=L3Nu7_zjzRKLsJsdLz-Cz1BKC6pOpoMX-_e6AhDmPxE,9230
|
|
164
|
+
vllm/distributed/eplb/rebalance_execute.py,sha256=ya8hQKaxiJLnh5kV04pjyL0jiy6Bjk63fKKnNYUntj8,19482
|
|
165
|
+
vllm/distributed/kv_transfer/README.md,sha256=cKIw6vXYSxBlf0wWwO7haP82CX2oB2QzW0-RxZE5mT4,2007
|
|
166
|
+
vllm/distributed/kv_transfer/__init__.py,sha256=wb5OWOxpI7rmB6NVrSKJHHQPBWpp_3NYseEOo_0mgOo,552
|
|
167
|
+
vllm/distributed/kv_transfer/disagg_prefill_workflow.jpg,sha256=fOFUEx-2Fm1uxHCGopvCREaRqdvR87Z7C0bMqEVH3Iw,142656
|
|
168
|
+
vllm/distributed/kv_transfer/kv_transfer_state.py,sha256=jFrtqPkifgETZZpoqUzdJhK74GMRWnxRCv_mZC4C99w,2290
|
|
169
|
+
vllm/distributed/kv_transfer/kv_connector/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
170
|
+
vllm/distributed/kv_transfer/kv_connector/base.py,sha256=KuKixI9XMfNTMWanVED-kedkMyMFtdcT34QO26lweJ0,370
|
|
171
|
+
vllm/distributed/kv_transfer/kv_connector/factory.py,sha256=xK_kbFs_YdMkpHnKmsvNPLW94yArS-gUlYqmCG7ACW8,6942
|
|
172
|
+
vllm/distributed/kv_transfer/kv_connector/utils.py,sha256=TY10RE9_B9AuPuckcE8u9-FB9x4Mj7Gorr4OuNwwQWs,10553
|
|
173
|
+
vllm/distributed/kv_transfer/kv_connector/v1/__init__.py,sha256=XGVYgVwmenrlulLD3EgNx0CglBC1YgbOFRPKN-cB7yA,508
|
|
174
|
+
vllm/distributed/kv_transfer/kv_connector/v1/base.py,sha256=BUP-YguyP0VL3Te-9cpUgSg4mk-V9w0njvsjKgSu6g4,20177
|
|
175
|
+
vllm/distributed/kv_transfer/kv_connector/v1/decode_bench_connector.py,sha256=XgtiVSMfZYOovmBREkunH9bSycIn0x_55nk2VFs9fOo,15551
|
|
176
|
+
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py,sha256=n6PqbqTkSH9nbMnzY0uBOHjyNtI5tX1WTiRO8keDZEE,7681
|
|
177
|
+
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_mp_connector.py,sha256=2AZdixXYpyH8603pmbbXlVD1yExPzNJheMaBZz980fs,31727
|
|
178
|
+
vllm/distributed/kv_transfer/kv_connector/v1/metrics.py,sha256=MHOmGh1qtGGIVXbAMJQWJOae1ZJ6L1oZRs0P_dgGXYk,7064
|
|
179
|
+
vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py,sha256=JlC_klqrSQobd3ilfWB1Yj1P-SoYUL7_ytIeMHDZX0I,17731
|
|
180
|
+
vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py,sha256=DNSySecTEdWlid1oz-59Yfr5_wob_f69BoDkMANfZEo,103094
|
|
181
|
+
vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py,sha256=lRD79usaq9wowh50ITbzciiGkJhsqbqvwv7lRu-sTWA,20645
|
|
182
|
+
vllm/distributed/kv_transfer/kv_connector/v1/shared_storage_connector.py,sha256=cpqzLw0mGmbcuSGRbLnX3xkXxNrIdHmEC6oD553oRu0,17112
|
|
183
|
+
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/__init__.py,sha256=k3tOaUj8P0IjtWcZ0CGxO3iE8IuALduzLpW5ejYJAFE,426
|
|
184
|
+
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/multi_process_adapter.py,sha256=4BVvAVoYhfna4tH9VfruVEUyifpTpQznUwlAyg_wk3Y,12444
|
|
185
|
+
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/utils.py,sha256=aSe-GgW3-PvuMFkabphG9wB-LDVMXuYn5GqLFv2dONo,8206
|
|
186
|
+
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/vllm_v1_adapter.py,sha256=s_D9omgN69FCkZqavOPZMmG3_XrhfzwKPxvQKugO2wU,51915
|
|
187
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
188
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py,sha256=_gzY8fDQdp0XUylpVwqdKUKLYySCP0yWowk4s7cpgYc,19308
|
|
189
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py,sha256=gdHYw55Qm1z8cz5cWoq76siI8tL6tewzYldcxNCG2s4,23390
|
|
190
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py,sha256=A2mMTFKJ1zBYEo0gPhe166-ms1S_gAaL4Zs9tULMbTc,9225
|
|
191
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
192
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/base.py,sha256=Tm4t3_GYEW4x4QgWq3asuIPHfoStJmxnWagwyKloMxc,6191
|
|
193
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/mooncake_store.py,sha256=b1SD1nrKU5LmdGCHE2oDl_qk_Ywz0sJxyUxaqNCN2VE,5614
|
|
194
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py,sha256=sV2v7QElLTyuGZBuaOF1-U9IFjLkzE9Swvxunucims8,9023
|
|
195
|
+
vllm/distributed/kv_transfer/kv_pipe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
196
|
+
vllm/distributed/kv_transfer/kv_pipe/base.py,sha256=nU-YDmWz3DYq3-PyJd6mMymC_1itJxBLeLIv-Ely7Zc,2102
|
|
197
|
+
vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py,sha256=ua69E5af9jBvkv85FOB32GEs3oM9azHuTE83WvriMs8,12108
|
|
198
|
+
vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py,sha256=ZtwzoNwntpeIqeX3lVweUCl6AY3ZfLB5NYUzVcOcpk8,9604
|
|
199
|
+
vllm/engine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
200
|
+
vllm/engine/arg_utils.py,sha256=Qjwtw_bgSqBGV6SkLJkMDQh2LMdmTM7NYNFkM-TI-vo,87950
|
|
201
|
+
vllm/engine/async_llm_engine.py,sha256=B4Xf26qGXnF7yc06F_OM2CH8k5CLUU34tjUEafnIg2U,197
|
|
202
|
+
vllm/engine/llm_engine.py,sha256=h0FBz_1vf8ThMr1PHUQVus1sEQH-N8XZsiQwNZrs1W0,212
|
|
203
|
+
vllm/engine/protocol.py,sha256=MxIudO1AZHGg8dMqTdhGo5p3BiJZxk6fmYq03tDGkq4,5426
|
|
204
|
+
vllm/entrypoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
205
|
+
vllm/entrypoints/api_server.py,sha256=oYUrcvccxfZ-Wh2ALlA-3E7GT83I6L1TIwmOzJMvpQs,5783
|
|
206
|
+
vllm/entrypoints/chat_utils.py,sha256=ovJAJNh94VCAGsFf6zUpV6IO9spm2TNA-GalqtrVZo4,64808
|
|
207
|
+
vllm/entrypoints/constants.py,sha256=ZX2zFNKkQjQM46StHeaSFaQIJEToSYcyJ7EBr98ZpWs,335
|
|
208
|
+
vllm/entrypoints/context.py,sha256=JlaNWzq_CDe1k8FzB0PlRhcZg3-FR2owWP44EdiFXQ8,21116
|
|
209
|
+
vllm/entrypoints/dynamic_lora.py,sha256=SFQD4z0XPKwtKvldOxikG1v8xj2uyWz52fPgVh3zCvs,2119
|
|
210
|
+
vllm/entrypoints/harmony_utils.py,sha256=DMNEkTlz1bbSH8FPYzaTKQQAsgTeW5rGSj3IU5HCRc0,20139
|
|
211
|
+
vllm/entrypoints/launcher.py,sha256=AKCjD0uDH5IHLEnyUI8qjhihRIowyMJ8k77rvUmtiZI,6064
|
|
212
|
+
vllm/entrypoints/llm.py,sha256=FyA-G8zf1bpgJ5wOCRi6Npccs8JptBf7OMN6FmCLb90,74129
|
|
213
|
+
vllm/entrypoints/logger.py,sha256=KYayEwEnv1ImBsZTcQ_7okyNqvkKjFqpZcv8SJYT5sg,2537
|
|
214
|
+
vllm/entrypoints/renderer.py,sha256=hmLtoxG4w_xRtGR03hpDAzKqgP2otoO5Feev2pU3NBk,15014
|
|
215
|
+
vllm/entrypoints/responses_utils.py,sha256=3xguly6ghdVPvsSJOgBL3vTarvGqaEUGCjul6bNs3oo,5158
|
|
216
|
+
vllm/entrypoints/score_utils.py,sha256=TrIsGtZIzpottUJOIyJ-mijrVRnVAjBCHno2QdgLjOk,7785
|
|
217
|
+
vllm/entrypoints/ssl.py,sha256=P6ApVGAQFLHERnJeoLNpZk-HQI1nNqWdlF8UAQpnC48,2712
|
|
218
|
+
vllm/entrypoints/tool.py,sha256=6WuSW4x0IVzh4ZM6hbu5ESMeJkwwIsF7_XYOYqnvN-I,4634
|
|
219
|
+
vllm/entrypoints/tool_server.py,sha256=GbGIKW3-kQZ-o9xKWGKlAQd3oWPLHh6kMQj7nKHd-cg,7692
|
|
220
|
+
vllm/entrypoints/utils.py,sha256=ej4UoclYGwVWuvKLlU_J_aOfjQw95O96li71POOwgSM,12245
|
|
221
|
+
vllm/entrypoints/anthropic/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
222
|
+
vllm/entrypoints/anthropic/protocol.py,sha256=nGkTR2TQtcy52uJJM8cJNSQtASDCChhgpQ6_-z_A59s,4284
|
|
223
|
+
vllm/entrypoints/anthropic/serving_messages.py,sha256=MlZJzclRBGYg06wdNkpcqTq2UMnndobPAJoShoycChY,19965
|
|
224
|
+
vllm/entrypoints/cli/__init__.py,sha256=7yL1JNi3jwUtykSxiULk93tN1lqykU-XdMbtBWtjU0A,582
|
|
225
|
+
vllm/entrypoints/cli/collect_env.py,sha256=H9qpqasc2FRmAQUvmRV5WuCxJqdj-ouYAQ2CMpN_ihk,1106
|
|
226
|
+
vllm/entrypoints/cli/main.py,sha256=vHRDDzGjKK2ZE9EWyGn--jpfBWewDtiYFDab9srDc78,2468
|
|
227
|
+
vllm/entrypoints/cli/openai.py,sha256=J28gD13rwUqI_IwDh0VGB3Jp5E2g67ILsKjPyYc6Bzs,7864
|
|
228
|
+
vllm/entrypoints/cli/run_batch.py,sha256=8ChYNc3UbbCVEbtp_tTbgR32_jVq3WRJgO1RzGhP8yI,2242
|
|
229
|
+
vllm/entrypoints/cli/serve.py,sha256=sjfXeDQW_zaWE6yX1YnhgHfNuWPa2jVOpmofHWqbywE,9001
|
|
230
|
+
vllm/entrypoints/cli/types.py,sha256=On70PbJbmYXWTQZaL3EbI7I-fd1eIE21FAhKuHnTcfo,812
|
|
231
|
+
vllm/entrypoints/cli/benchmark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
232
|
+
vllm/entrypoints/cli/benchmark/base.py,sha256=3KVCkfdN9VsNhP4RniGqJi02pzIEW4IMIktMFgwU1Y4,674
|
|
233
|
+
vllm/entrypoints/cli/benchmark/latency.py,sha256=ruUvsQxW_zv19NxZe4dhdVRjmBl2Gipa7o0aGp3VN-I,653
|
|
234
|
+
vllm/entrypoints/cli/benchmark/main.py,sha256=aoHKd2EJPtmCcZv3G7TBBWXbYR_bi1-qUDpn9I0AFeY,1847
|
|
235
|
+
vllm/entrypoints/cli/benchmark/serve.py,sha256=v735WpqjlGE846KvCqAlrb6eAdysihhNZNX5SDL2Tac,635
|
|
236
|
+
vllm/entrypoints/cli/benchmark/sweep.py,sha256=kHcCsBsGQwNC_bdhIdKs9ykJawLbRCrZF-HT4NFCjkE,629
|
|
237
|
+
vllm/entrypoints/cli/benchmark/throughput.py,sha256=Sb73dvXCAs_P7rk3sYkEbKIezlA8cCF7piMX1HA-xEc,652
|
|
238
|
+
vllm/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
239
|
+
vllm/entrypoints/openai/api_server.py,sha256=x_HMTVqstb_XbMQT2ypkNpHetaCXDI_3ZnsdbGXHtuo,68070
|
|
240
|
+
vllm/entrypoints/openai/cli_args.py,sha256=vunq2FOygqUjzwov6lew12OKkMesb584kJWzQy9otjo,12943
|
|
241
|
+
vllm/entrypoints/openai/orca_metrics.py,sha256=qLJmaC4SWLSfvGtwOECR8DexnCXBVqYZuENYINORYgI,4509
|
|
242
|
+
vllm/entrypoints/openai/protocol.py,sha256=NzSey-q2KH7C1T8pMVTgrfKDbSpHg5Cl9_NoWqsZV1Q,88144
|
|
243
|
+
vllm/entrypoints/openai/run_batch.py,sha256=XN5i78ft-3XeTiPAXCLWThVga72elrhapxUmA15WHmM,21412
|
|
244
|
+
vllm/entrypoints/openai/serving_chat.py,sha256=hFDBX1CukouCZsm6dRVweQTM8gaVF1BNGp_CjYsmNGU,79001
|
|
245
|
+
vllm/entrypoints/openai/serving_completion.py,sha256=1FK9OjqE0KvKYLoDChJNUhIUgA0DQ34yR1WcwyJ6HTw,29438
|
|
246
|
+
vllm/entrypoints/openai/serving_engine.py,sha256=K24HB2WXanKn4GEZzAPke76SvcbGSwE6uzgIm68fTfw,52718
|
|
247
|
+
vllm/entrypoints/openai/serving_models.py,sha256=l5Xme5t-zgp8XKHdCeDiT_-cAYN78jw6dxPCU00-mFc,11406
|
|
248
|
+
vllm/entrypoints/openai/serving_responses.py,sha256=k3icEwORBMWGiQMK5a1s1JGpDIviY4TdgQhG_DLNYDs,86862
|
|
249
|
+
vllm/entrypoints/openai/serving_tokenization.py,sha256=JQirDyiGpSOAxmeYACbVcOgoSNjURJI1vyFwE2aB9jM,7453
|
|
250
|
+
vllm/entrypoints/openai/serving_tokens.py,sha256=MHQ8SMwKM0qyA67iNkOV1x8EiRiHgCakiEKxMkoddkA,10527
|
|
251
|
+
vllm/entrypoints/openai/serving_transcription.py,sha256=YX736nt0BGXvMpj4lzypDjrAA8FBh2n3t5yFELASaWw,5986
|
|
252
|
+
vllm/entrypoints/openai/speech_to_text.py,sha256=1xfLtUQB5v3TjxMhNUAL99EQBxOR2M3Nal6udVarYwM,22684
|
|
253
|
+
vllm/entrypoints/openai/utils.py,sha256=GediW7ToZ71oiChH9nc6r7_XeTfuBo5K-yFDFWkYIA4,1608
|
|
254
|
+
vllm/entrypoints/openai/tool_parsers/__init__.py,sha256=eVVn57wdfoV3PLrJcODkMQW6RErjyOhnAbio3GJurkU,3260
|
|
255
|
+
vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py,sha256=XX4B6bl6Pewa95BpNle_9nS0gKThQMCC_XLIFf3ydoI,9679
|
|
256
|
+
vllm/entrypoints/openai/tool_parsers/deepseekv31_tool_parser.py,sha256=PD4JyZuMkqqt1n82IuxCVZ9U3SMEcGOCtEPd9UjBC00,16456
|
|
257
|
+
vllm/entrypoints/openai/tool_parsers/deepseekv3_tool_parser.py,sha256=JuJOY_jQNCeXlqLsjnknoFNKkpc0lR3g7o2n8jJ6-jI,16554
|
|
258
|
+
vllm/entrypoints/openai/tool_parsers/ernie45_tool_parser.py,sha256=I12l7D7r7p59Ws9dz0N2oapLcBLcyALdYnn9xQBRspc,8357
|
|
259
|
+
vllm/entrypoints/openai/tool_parsers/glm4_moe_tool_parser.py,sha256=9IZsnbjhXK_RQv6uQUJjbPJXvMcqM0PEwJ8HrB7zQJk,7507
|
|
260
|
+
vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py,sha256=MmOmPOFcCOcj8sFAh1zopft9lg4mVs2MkbdoNwBfyjs,11024
|
|
261
|
+
vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py,sha256=cIxNPXmX9qjTDmneIWowe0GiOapNL8v7dAn8SlklxT0,10280
|
|
262
|
+
vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py,sha256=QZs0AFB5edOKLFRZsOULvARGVl7T007fIs87iV-ctn0,21190
|
|
263
|
+
vllm/entrypoints/openai/tool_parsers/hunyuan_a13b_tool_parser.py,sha256=sFwQJOMgRTn0h-bO2VKorvRlFJpMZPOHKS3urxvFgwE,16714
|
|
264
|
+
vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py,sha256=D_-gTqIiHYvQNIqOo1rhnGE70fFJk9bzMXqqUv1IE28,9107
|
|
265
|
+
vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py,sha256=5g1KDIpvxBiVtRKSELiPh49ulGAN5ddRk3njELPrIKc,13711
|
|
266
|
+
vllm/entrypoints/openai/tool_parsers/kimi_k2_tool_parser.py,sha256=Vjct8SSbczCT0_HfYIo82iINYH8rmRgcPFGfy9RBt0g,26170
|
|
267
|
+
vllm/entrypoints/openai/tool_parsers/llama4_pythonic_tool_parser.py,sha256=G6ID7HObcZmdY2SUHW_gguXoDlR7bdXrBeqmth9xlnU,12834
|
|
268
|
+
vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py,sha256=ZjJNe8_mFMKG1_O2NrXu91s1jnvxP6eS0bsHS-loQu4,13668
|
|
269
|
+
vllm/entrypoints/openai/tool_parsers/longcat_tool_parser.py,sha256=_vv0WkfYVNQff3SlYEi_UXPQdnNDj3DI6Q5dODzVK0Q,1306
|
|
270
|
+
vllm/entrypoints/openai/tool_parsers/minimax_m2_tool_parser.py,sha256=E8ESQSbXsMi_jfCaDHzekuXhlfWVotd-JgNW9Iyvuyo,26683
|
|
271
|
+
vllm/entrypoints/openai/tool_parsers/minimax_tool_parser.py,sha256=ck4JiSuJ1z7r67-JJs0qZMQwNPd6DoymdEeHQdX2g34,28519
|
|
272
|
+
vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py,sha256=FuVEAclj4yoKlAXWww3HhREeIzeGwRcv6iKqu2n5jp4,16422
|
|
273
|
+
vllm/entrypoints/openai/tool_parsers/olmo3_tool_parser.py,sha256=ZjqzgSCjWDRJXKznS1LYkma1vA6TEPxcq3llqtwGo64,13937
|
|
274
|
+
vllm/entrypoints/openai/tool_parsers/openai_tool_parser.py,sha256=4iGjqhS4S8i8G52vBFA8EEGRi1Go2VtiOlkyfnuLGGw,3458
|
|
275
|
+
vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py,sha256=z7FS-G-FYgTqxJwKgY_2GkK29v-R6lwIv2Ly5XhATZM,4031
|
|
276
|
+
vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py,sha256=IpITSRHECxaOkNqn1UBuLUogpiOLGIu6BxnvL-MGh6Y,12216
|
|
277
|
+
vllm/entrypoints/openai/tool_parsers/qwen3coder_tool_parser.py,sha256=Mw9g2tPhp-ov6ZXDMLqsXk8BqNEzuirjGYVU2FMHDr8,32751
|
|
278
|
+
vllm/entrypoints/openai/tool_parsers/qwen3xml_tool_parser.py,sha256=Nwh9mUgCRCluNsvSO3ayEIi9R8ouc9AUGIdwKLr8MwQ,53804
|
|
279
|
+
vllm/entrypoints/openai/tool_parsers/seed_oss_tool_parser.py,sha256=UQ-D7kpJQDSe1Rn7EKtqhnwRLRExE-UhUsYACWgO2LY,31351
|
|
280
|
+
vllm/entrypoints/openai/tool_parsers/step3_tool_parser.py,sha256=eHKtjopzh5OzgjvLHY2xepEplO4LFZT8tf1JXh3EfZY,12106
|
|
281
|
+
vllm/entrypoints/openai/tool_parsers/utils.py,sha256=5VZCLxbxuOP8FtiFjYneEb7PKtQyLJBVp247IaxsHyQ,7444
|
|
282
|
+
vllm/entrypoints/openai/tool_parsers/xlam_tool_parser.py,sha256=O1ZlxQduH3vcSlYsuoWnjulyXITGVTrL0bYAtzUwGbg,24637
|
|
283
|
+
vllm/entrypoints/pooling/__init__.py,sha256=RKBcmpHb7TKxlpGmPQvC8FkTe-axbQmyjh7jYLRVhac,674
|
|
284
|
+
vllm/entrypoints/pooling/classify/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
285
|
+
vllm/entrypoints/pooling/classify/api_router.py,sha256=CC2u38foFQavU6rkk6d1_qYJ8lzLFsxHNZlyJV6TA9U,1810
|
|
286
|
+
vllm/entrypoints/pooling/classify/protocol.py,sha256=liPaeGzy_xnxr2w9wdcsgjOOpEY9MCSkp2NLd2QDf_E,5874
|
|
287
|
+
vllm/entrypoints/pooling/classify/serving.py,sha256=jqwYdsP038i7KFjVekcSwSe5NnRklATmawkSSx2HysQ,8294
|
|
288
|
+
vllm/entrypoints/pooling/embed/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
289
|
+
vllm/entrypoints/pooling/embed/api_router.py,sha256=UPMa4T2COal8XfC1RS9AcmiA-qbrAk3r7Y4--CzevwY,2249
|
|
290
|
+
vllm/entrypoints/pooling/embed/protocol.py,sha256=m9mwkKWQc0XEGkgX7TN7M7hAQh5vQkzBwK86u-nyw7s,7347
|
|
291
|
+
vllm/entrypoints/pooling/embed/serving.py,sha256=vFl_yERJQAzbCZ6lrffOlEqelX43pl4DohEWZ_i_Ss8,27045
|
|
292
|
+
vllm/entrypoints/pooling/pooling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
293
|
+
vllm/entrypoints/pooling/pooling/api_router.py,sha256=G0E1fSIFZvnkGnbLiVYBsnFUcGs73nQmg_-MkOouW_k,2253
|
|
294
|
+
vllm/entrypoints/pooling/pooling/protocol.py,sha256=rYzEF3EwVSabdaXao_bgG3807mN1fhVQi64ysL9wPcM,4704
|
|
295
|
+
vllm/entrypoints/pooling/pooling/serving.py,sha256=MknoM4dpmV7PmvM7X2VlwvoeVFwdiLBtyas054h-VJI,13032
|
|
296
|
+
vllm/entrypoints/pooling/score/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
297
|
+
vllm/entrypoints/pooling/score/api_router.py,sha256=u7bKJebPmQl2vpBN7IqVtGTO_U6Gu6gxV9-20BrKVdI,4838
|
|
298
|
+
vllm/entrypoints/pooling/score/protocol.py,sha256=IgLrfeTYhT3xHlJ981cBIFiCldwNeqDKkQUX402ZILA,4184
|
|
299
|
+
vllm/entrypoints/pooling/score/serving.py,sha256=KrIm56a5msf87EIeVGRa-BNs-2ByZXa9x_IAyhht_KM,17201
|
|
300
|
+
vllm/entrypoints/sagemaker/__init__.py,sha256=Fh71s9Oigag26xVp42xT7JCAr_dvDRGnjoRhEV18cwk,155
|
|
301
|
+
vllm/entrypoints/sagemaker/routes.py,sha256=rxU95gH1jmmkD1YOfLginaoFRy1t2eqGAJ4Wx7PiXUA,4551
|
|
302
|
+
vllm/inputs/__init__.py,sha256=mOYaFF0JBFeIgf4cs5_kS5d7zk4yA_TRBxhfOncKhGw,959
|
|
303
|
+
vllm/inputs/data.py,sha256=vCFClf9AbX4bNhc6_3jit-xg5rRbdRplEPaxxHloRcE,11465
|
|
304
|
+
vllm/inputs/parse.py,sha256=kIpN6UrnUM1sDxip3f5TkaeiFe_Gl1mUr2h0cFCmfcs,4257
|
|
305
|
+
vllm/inputs/preprocess.py,sha256=9tCRckCeXtQL3aT9RmuSFqJW8nzyE5-a2L6pZOEXlBk,24592
|
|
306
|
+
vllm/logging_utils/__init__.py,sha256=Rup1dtcYw-n2RvQt0Ka37rCagFdvfmzx4UFOmi3XTpo,363
|
|
307
|
+
vllm/logging_utils/dump_input.py,sha256=jqfKTqU2b2O4g5I_P2snzPuuIFlSTYg33BjZ5P87-JE,2914
|
|
308
|
+
vllm/logging_utils/formatter.py,sha256=3tQ1N2oDuzXPRCcasRAIPJhz4SF3_gBEfXz8IcSuz9Q,4649
|
|
309
|
+
vllm/logging_utils/lazy.py,sha256=I5YcIP9S9ru8q5kC3h0Vqaf1nX9A9xxUSP6KTcvWxcU,508
|
|
310
|
+
vllm/logging_utils/log_time.py,sha256=ea9dQUzQAu_f5juFfGVeOX403d4yGVqiBmI35gmpqdQ,864
|
|
311
|
+
vllm/lora/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
312
|
+
vllm/lora/lora_weights.py,sha256=gmnlIUfNtzeoOvPBAVhI8r-qfCyPloTajp_PzklqQKs,6971
|
|
313
|
+
vllm/lora/models.py,sha256=gfz19pp0eslh176HsDjPj8DnaNHwBS3ZWAjt8VkZWsM,36070
|
|
314
|
+
vllm/lora/peft_helper.py,sha256=rLbCLj-UsjXFD2wXD18hOAtzP_389FwcpozeItzgRvk,4678
|
|
315
|
+
vllm/lora/request.py,sha256=OIU4IXeoLkewhawohV77tXhDTBzaklm0ELvPPXaNbQE,3149
|
|
316
|
+
vllm/lora/resolver.py,sha256=SvNATAduYkVIuFA59Q5pPTuPjmLQCg-IH-_35u2mn98,2880
|
|
317
|
+
vllm/lora/utils.py,sha256=JblhaBCsIH19AtgWUMsOsSt2Xv1rKt-7RzNw7OMGbsg,10667
|
|
318
|
+
vllm/lora/worker_manager.py,sha256=gPmAxKsHyycYTrMx25mOvfN4Yds9sKF97d3RI80GnP0,10721
|
|
319
|
+
vllm/lora/layers/__init__.py,sha256=koQoPRXNT76UlfpT4yNwFpXY8eIZyzk3fmSRH8EWda8,1610
|
|
320
|
+
vllm/lora/layers/base.py,sha256=djqVQ30rFpuG71V8nIj4QARsbEDzjfeosBk9jTt98Ts,1825
|
|
321
|
+
vllm/lora/layers/base_linear.py,sha256=V7WXfGq5P2b0GwQPBdBUiB2BONRb6cBCY6bZ1KXAKjA,5734
|
|
322
|
+
vllm/lora/layers/column_parallel_linear.py,sha256=4OHIu9At_tNoV1mV0lyMT17rn0Uu1fhom-9BzdETyPU,19929
|
|
323
|
+
vllm/lora/layers/fused_moe.py,sha256=hM2vjolLTW9ckbvLmkZULcJD0uVt8Uggw-whUXsIK40,27831
|
|
324
|
+
vllm/lora/layers/logits_processor.py,sha256=1c3bDxki-82ZjotsTDTwWuooLnd2CqZQs7TKdjeH998,6447
|
|
325
|
+
vllm/lora/layers/replicated_linear.py,sha256=oswJbpelrd1Smiz1AV9zlLRcZb62XW700uporDliAJE,2205
|
|
326
|
+
vllm/lora/layers/row_parallel_linear.py,sha256=y6MpIbqGU3eSv50nlzuaSDRZdyUfwUJp66E6Fwct8GM,6187
|
|
327
|
+
vllm/lora/layers/utils.py,sha256=ORPW8yXs2tImWp4iGakeYqoefp6LW9fuRQRp18YKHxE,2305
|
|
328
|
+
vllm/lora/layers/vocal_parallel_embedding.py,sha256=xznlBgx20SFUxFHr6nRgieJlg2uyVVSmc1X8thQvoA0,4944
|
|
329
|
+
vllm/lora/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
330
|
+
vllm/lora/ops/ipex_ops/__init__.py,sha256=GoE4WbwmiV3lmZ9BvAzF6HribyiAa62lEsRdAOORl3g,259
|
|
331
|
+
vllm/lora/ops/ipex_ops/lora_ops.py,sha256=sQTAhgirQaxWxhc3xTdSlDBfZKUUJaY4MwISeBBXOEg,1344
|
|
332
|
+
vllm/lora/ops/torch_ops/__init__.py,sha256=T8KI4Uy6j2AJOjjfe_9HYZmuSO9xp0G_GTCdvHyJiNE,426
|
|
333
|
+
vllm/lora/ops/torch_ops/lora_ops.py,sha256=M7wqynKevDeeFyXDwcqHDnCqOyePCtPSpiHm7I7pnCA,3888
|
|
334
|
+
vllm/lora/ops/triton_ops/README_TUNING.md,sha256=vRdibcgJphUomT22SAtQSrEf7LVROHwHgugGjqpBqY8,3078
|
|
335
|
+
vllm/lora/ops/triton_ops/__init__.py,sha256=-IQeOBrAW7uCUQQVUt5zjjL4PyqB1in1AJei7ezUpNM,598
|
|
336
|
+
vllm/lora/ops/triton_ops/fused_moe_lora_op.py,sha256=zEbbFm2KCH9-0WMqrzZ_DbpdADf36Gmu_25sUVYaM4g,19579
|
|
337
|
+
vllm/lora/ops/triton_ops/kernel_utils.py,sha256=YiE1F7sojPFFF06QsVSeaDN19Fpo4X1MhFSoX4F8EXA,10375
|
|
338
|
+
vllm/lora/ops/triton_ops/lora_expand_op.py,sha256=0T8MQkWC1A-AgUudjjTZPsGmzaj5mamEXDyZBytUqH8,9417
|
|
339
|
+
vllm/lora/ops/triton_ops/lora_kernel_metadata.py,sha256=_7kOuoEYIx7lGOzFPwp6idbExJm6tN__CBUATMr41JY,5407
|
|
340
|
+
vllm/lora/ops/triton_ops/lora_shrink_op.py,sha256=Olu1MoQ24II09hKTLUGhG33BQtoKpRmLhdOj9LM8ZYk,8871
|
|
341
|
+
vllm/lora/ops/triton_ops/utils.py,sha256=sCiYwaSL9CGh6rVT70wpeqh6vsozJu-Z8XBEDKpYoHM,9744
|
|
342
|
+
vllm/lora/ops/xla_ops/__init__.py,sha256=EbrQj03YWghRsJGDiwWghqJ_yNeYsczL8Z9UuizHxgU,258
|
|
343
|
+
vllm/lora/ops/xla_ops/lora_ops.py,sha256=ZkV2n8L8MVQWCVqNUtFtqPaIcy-wkQk7HAsXRDDoV3M,4245
|
|
344
|
+
vllm/lora/punica_wrapper/__init__.py,sha256=A5cDJmdCPRBN23kwLfemRlWI4YA-t_7qIxeoeimCkT8,313
|
|
345
|
+
vllm/lora/punica_wrapper/punica_base.py,sha256=puiggPyTCXaKXmmrsYiiRiDnVym7Ig4BYjdlmnEXMaU,15734
|
|
346
|
+
vllm/lora/punica_wrapper/punica_cpu.py,sha256=qJLetoy4aPyQazVqbEq0pOOr848ox_hXvO3AOIH4XR4,10817
|
|
347
|
+
vllm/lora/punica_wrapper/punica_gpu.py,sha256=QUrzpFAGuvBZZXLlQJqzbnSJxIXJzh7gmGZZQ-ljq_k,12909
|
|
348
|
+
vllm/lora/punica_wrapper/punica_selector.py,sha256=-IyHqLvTPs5onKUXacOqS9J03otlfaT8J7yj4iD_YRs,818
|
|
349
|
+
vllm/lora/punica_wrapper/punica_tpu.py,sha256=3zMy7ayyvEqyP5e-WnX3DaE_WMkBFAMNZuE9aP5C7g0,12348
|
|
350
|
+
vllm/lora/punica_wrapper/punica_xpu.py,sha256=tUpbNjlqObOWv3msA3ExE49xjjfx7FTYz_-LyDFJEtM,8770
|
|
351
|
+
vllm/lora/punica_wrapper/utils.py,sha256=omm684H29vAOXrC4ny19kmKFRk0_-pIAMTR87CmRMXw,5517
|
|
352
|
+
vllm/model_executor/__init__.py,sha256=HldmuFnAddB5kxjNzrqSLCTBGzvOHJ3VPdN4xI13sEo,333
|
|
353
|
+
vllm/model_executor/custom_op.py,sha256=y0I1l7C9UhZ3Q1PgWxiQZpkteam64_U249j12FR2bWY,7441
|
|
354
|
+
vllm/model_executor/parameter.py,sha256=zo3JRXFPq62Dg8624hZygs3zAq-W8MwJirmY1qwHkTY,22854
|
|
355
|
+
vllm/model_executor/utils.py,sha256=NkZQcA5s0skOZsv-NIgGJ2cn2qH2Y6JhFIIiDnZquVA,3484
|
|
356
|
+
vllm/model_executor/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
357
|
+
vllm/model_executor/layers/activation.py,sha256=-Nc5z_INkBqQSzPP4fWuobQ3xJoLnsbJ_C6Ei8ln2Aw,21783
|
|
358
|
+
vllm/model_executor/layers/attention_layer_base.py,sha256=L6w8vuzUcssauMGLf1D0Ysi1ZRA4gA8e7c6uSkr08yM,980
|
|
359
|
+
vllm/model_executor/layers/batch_invariant.py,sha256=RDZsyyBHfaj7x8gxe1RgnXSnCCJUPudIdZnfaAXvZTU,33393
|
|
360
|
+
vllm/model_executor/layers/conv.py,sha256=cFgVH2XA7zEcHceyzMv9ZjM8KvgcdVBN3zC1n0hbwac,8021
|
|
361
|
+
vllm/model_executor/layers/kda.py,sha256=sM-x4ZHFwkLsCZTbCnJy9FtTgcyAkJAAPjdwjwIyz5E,15504
|
|
362
|
+
vllm/model_executor/layers/layernorm.py,sha256=ly_FRF4zymmim4o8xfv-huqd1q_DjLM58j5QQ2HPwTE,13887
|
|
363
|
+
vllm/model_executor/layers/lightning_attn.py,sha256=yknJVad9ilzRGFdFhvjkoe_xEiffNp_KopUsd32Qzf8,20864
|
|
364
|
+
vllm/model_executor/layers/linear.py,sha256=lWucztYwZxBgRELBK0G-Zm_YKJWvmOw0g3ED_oopOvY,56807
|
|
365
|
+
vllm/model_executor/layers/logits_processor.py,sha256=yUVukCx0lBtFP7-2rfEsSSw-po25YD0GW-WF6beyHGo,3840
|
|
366
|
+
vllm/model_executor/layers/mla.py,sha256=mRHs6x0VrSQnp1nSS-LlMUHdBm0I6-UUnuNJvgWXbRI,6357
|
|
367
|
+
vllm/model_executor/layers/pooler.py,sha256=iZjEZXwJ7p-uO8SJVJTXp-f-Gff7JVBM-5TS2Xt78iU,26626
|
|
368
|
+
vllm/model_executor/layers/resampler.py,sha256=kK_gbASYVbvMoPPN3petUTfNGK8DkdNdihYnFx-JLn4,9877
|
|
369
|
+
vllm/model_executor/layers/utils.py,sha256=FI3DqvZAPjDcmESgiQv5MHWDwx8Nw_x_nWmEehneprc,8024
|
|
370
|
+
vllm/model_executor/layers/vocab_parallel_embedding.py,sha256=6Btumz_IkeCVvpgVICMEeG55wnQizWJl7ViPMooWpaE,22034
|
|
371
|
+
vllm/model_executor/layers/fla/__init__.py,sha256=Xbv6P8KG7bLpcOF17zPO5PYYHImweE9aiYYgGyMS9U4,391
|
|
372
|
+
vllm/model_executor/layers/fla/ops/__init__.py,sha256=Tx9ajmbsCCptuJofX-QpCC_Ut2SwZBTT56SUjGXGNs0,642
|
|
373
|
+
vllm/model_executor/layers/fla/ops/chunk.py,sha256=NJFnrsO_TdmXwAsyAmyUptSMxrVCH69T_xHjDp6DRko,8925
|
|
374
|
+
vllm/model_executor/layers/fla/ops/chunk_delta_h.py,sha256=rSBPoldJnPs9MHO_XOCw_E-fy-R5H8vA38zsSQjI9CA,11864
|
|
375
|
+
vllm/model_executor/layers/fla/ops/chunk_o.py,sha256=ucfFMons_gjoof5N36dImFVcWDZpeBjHVxdFMI1XOTw,5095
|
|
376
|
+
vllm/model_executor/layers/fla/ops/chunk_scaled_dot_kkt.py,sha256=_i7MMGO66MjD1RYQFDqNpa9yGknPyHBOTEDwChc9hFw,4653
|
|
377
|
+
vllm/model_executor/layers/fla/ops/cumsum.py,sha256=qhS_Lny-roiECMEDvtWBE2RpiFYDKjqWxwQONRdL2gA,8224
|
|
378
|
+
vllm/model_executor/layers/fla/ops/fused_recurrent.py,sha256=jZyUUmgmaq75r_Mg4nYSewk3pK-YP8tWcWhFTktQ5TA,13064
|
|
379
|
+
vllm/model_executor/layers/fla/ops/index.py,sha256=cg2IV5Tn7cvDzPw8fTdI96sIYFy87tk960b0nPJFXSE,1221
|
|
380
|
+
vllm/model_executor/layers/fla/ops/kda.py,sha256=7eRv3Hs8oOWM1_nnrBC1kERDSUixaax_-RHDKjQz5xE,38297
|
|
381
|
+
vllm/model_executor/layers/fla/ops/l2norm.py,sha256=HfUKWKl1EvrUKcowbDu4E5QPQCgZbPFumK43eli0Q6Q,3978
|
|
382
|
+
vllm/model_executor/layers/fla/ops/layernorm_guard.py,sha256=nfQwy29Wu6Pt3X3ZL3oPVqxhzITarzf7AmxjBzaKDWI,12449
|
|
383
|
+
vllm/model_executor/layers/fla/ops/op.py,sha256=atkZKsyTmBUTa68GnRk0VfEVfKAbmRoFLYtQlf8_JBM,1712
|
|
384
|
+
vllm/model_executor/layers/fla/ops/solve_tril.py,sha256=ARfbUgKOHld2Zbq3VlgjP07bjczFSCCQc0MRLmABcV8,19385
|
|
385
|
+
vllm/model_executor/layers/fla/ops/utils.py,sha256=7zOakRwlL0cVsyqpZeWcknuuIs76WvuR4-2TzdlL9AQ,6357
|
|
386
|
+
vllm/model_executor/layers/fla/ops/wy_fast.py,sha256=TqyZCDUrAUo0ZFdtHPRY4ntUxavxsYsAGGj0m23oyiI,4372
|
|
387
|
+
vllm/model_executor/layers/fused_moe/__init__.py,sha256=sVno-BF-Rb62IyVrnkRyyJDL-3exuOxcPqqyvycWtFA,3345
|
|
388
|
+
vllm/model_executor/layers/fused_moe/all2all_utils.py,sha256=7DH6zKYe8dPk9imLdZmxQ9s29gWCmHLEw-Uv6ykUZAU,5948
|
|
389
|
+
vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py,sha256=uAQeX9mm5c-mi_0WHMWrQKYC-b-t4JB7xcAklowvvBE,14815
|
|
390
|
+
vllm/model_executor/layers/fused_moe/batched_triton_or_deep_gemm_moe.py,sha256=3IsUrQEa-xv6i4kcrQKY8txc59p1q2C-s9qv6lF0JMw,6070
|
|
391
|
+
vllm/model_executor/layers/fused_moe/config.py,sha256=wJfaswWDKT1BusECcSBba_smTngJhNHJHKuPF-xP1Ks,31720
|
|
392
|
+
vllm/model_executor/layers/fused_moe/cpu_fused_moe.py,sha256=x5XbsZIQ3OiampD_K2ag7yGhJO4k32_9z3AzOpJF6vk,10695
|
|
393
|
+
vllm/model_executor/layers/fused_moe/cutlass_moe.py,sha256=M1LBG0_OS2h5DK8Z1mf8KNvxQlCKKMue-aATKuDFDQU,34903
|
|
394
|
+
vllm/model_executor/layers/fused_moe/deep_gemm_moe.py,sha256=K9CRhD4ua90OSgHO6vagg0KFQIfp5obUihRFbY6v8Cg,12957
|
|
395
|
+
vllm/model_executor/layers/fused_moe/deep_gemm_utils.py,sha256=4QdWHqornCJ6vQqa7m_neRlKUYs58xawpGcG3XYiNLc,12824
|
|
396
|
+
vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py,sha256=3jXq-FQ7m1aASduI-35O_isUZcPe-3jHtkbPv4h038s,14791
|
|
397
|
+
vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py,sha256=i54CE6GYPsECmo5L3LVak2V0lf6upBoV0mTPTYCsS6M,14994
|
|
398
|
+
vllm/model_executor/layers/fused_moe/flashinfer_cutedsl_moe.py,sha256=Vet2B50T8wD6ySg0XgjgekLDRmkR91SfyLBcicxm_7g,12943
|
|
399
|
+
vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py,sha256=scSk_NF4-pfll7jEkt8qdDAtUSpxlRxYO8G8kZfSmpI,10765
|
|
400
|
+
vllm/model_executor/layers/fused_moe/flashinfer_cutlass_prepare_finalize.py,sha256=6N_KQtguaJVJK8n46l-geXAwi4vPFxTEpnK1kyHuLDk,12210
|
|
401
|
+
vllm/model_executor/layers/fused_moe/flashinfer_trtllm_moe.py,sha256=YMv1Opt0C_LfIDEsk1FsQ0gJkY8btWk1R1wi5R4ORpg,6481
|
|
402
|
+
vllm/model_executor/layers/fused_moe/fused_batched_moe.py,sha256=frQD9kNlwawFbMBYI1lh6HW8VUTZULgoLdZPwOh4o_Q,32100
|
|
403
|
+
vllm/model_executor/layers/fused_moe/fused_marlin_moe.py,sha256=xBxiUwtuZFc7eDgS3ZvNbv1Owj32hZJNv87IruMdK6I,28310
|
|
404
|
+
vllm/model_executor/layers/fused_moe/fused_moe.py,sha256=q4rp16-ViNR_6PxgjL44rc93wJ_CUqIzLHT6LUCFG-E,75333
|
|
405
|
+
vllm/model_executor/layers/fused_moe/fused_moe_method_base.py,sha256=feR3xyjnlVoprEe9WaKboot0SeMQpps3VabCz0P7wpE,3837
|
|
406
|
+
vllm/model_executor/layers/fused_moe/fused_moe_modular_method.py,sha256=CbAfwRvhLgvJsfGOQAiAFuX_i1iUJupl1MDPTZqeJ6A,4639
|
|
407
|
+
vllm/model_executor/layers/fused_moe/gpt_oss_triton_kernels_moe.py,sha256=zIv0GVfn1H4f6JiFL6Q5qN7S4cZMbslr7w4keM2qPAk,17435
|
|
408
|
+
vllm/model_executor/layers/fused_moe/layer.py,sha256=mWUBs0TrcK_zaK1C3xwnmVOf5QynAmfOMjLGwk1OTYI,85960
|
|
409
|
+
vllm/model_executor/layers/fused_moe/modular_kernel.py,sha256=F9ZmcQSSFXZb02lWJLDIkxjtZ0UQGwY9W_A9sk3nia4,48684
|
|
410
|
+
vllm/model_executor/layers/fused_moe/moe_align_block_size.py,sha256=RCLkxgqt5g5ouCUZHg7IwLzCPXw8LwCmQ9tuZVqOarY,7605
|
|
411
|
+
vllm/model_executor/layers/fused_moe/moe_pallas.py,sha256=7WcySwfOiFkyw-udjrWKjIdzYgcB47NGK3reblL0wrI,3118
|
|
412
|
+
vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py,sha256=WftEGpSesMQmjg5sbvko3LGHuDl8EpySliW5X10Xiwo,8196
|
|
413
|
+
vllm/model_executor/layers/fused_moe/moe_torch_iterative.py,sha256=u_cFfZnz34AliNgZWfQUltCTXP_yTg4NjFxKb0r7zU4,2154
|
|
414
|
+
vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py,sha256=cEP8YRKHP4l4lcf2m-dNuQmgF5jCRIqEexp2aC44oe4,11776
|
|
415
|
+
vllm/model_executor/layers/fused_moe/prepare_finalize.py,sha256=lgLNuMPBLi7ELtcU-tDmXhForCmlT6UbqNXNje6UTO8,2647
|
|
416
|
+
vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py,sha256=9_d-7nwKC3PJtyfLSJHvDH6fAq8_KI2-4lV2gu9UWGc,9216
|
|
417
|
+
vllm/model_executor/layers/fused_moe/routing_simulator.py,sha256=TY1mPAGcG6SKjRh2kt-wvM1sn6Xd6bHmYmuXjAovBbA,10724
|
|
418
|
+
vllm/model_executor/layers/fused_moe/shared_fused_moe.py,sha256=uUf8M9pYcHT-VQMZI1ZUlPolOfSwYXPt_fE5qrh59r4,3391
|
|
419
|
+
vllm/model_executor/layers/fused_moe/topk_weight_and_reduce.py,sha256=sLKn82zPW7Yij8Bcrt4sXW78SyuwIwDELfiqsXaTxsw,5801
|
|
420
|
+
vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py,sha256=zO6a9hD6tkx0dcohItDS5hEjUCPlQq0q9P_-rNZ__N0,5215
|
|
421
|
+
vllm/model_executor/layers/fused_moe/trtllm_moe.py,sha256=2OUD7vd-ptjUFtIT-9QNdsxT6IKldivr_T5Rr1_JSoQ,4660
|
|
422
|
+
vllm/model_executor/layers/fused_moe/unquantized_fused_moe_method.py,sha256=Q2ZzSWrJfdIGDlz6WCwNL6-fNOPcOmUYrTHZ0Y0Bejo,21536
|
|
423
|
+
vllm/model_executor/layers/fused_moe/utils.py,sha256=Y_J7w47cIXgx51N1SeG1KJEUfUbut6CZiYScsyv6xLc,10855
|
|
424
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
|
425
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=hH5rRN9Wtyv35azxMzyUMHWtiKgOHev5tNjIG8j6dsE,2751
|
|
426
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=qPumkNxaHMvVBnEjPe_Xiuz9ICb6Hqc-9I1DAR8s3gA,4130
|
|
427
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=s47lb8VLnyxMgWlqcIR4BdPBsjKWL4olXF49uZvygzQ,4140
|
|
428
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=SkuSt9_xoUgmwy-EIOMJ5DT3pEm7g4dMh78fZSyCaKU,3244
|
|
429
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=gzfjrYDcS0vsACq7ONGVkNA3FqVjr3e89q9fO9kokkg,4133
|
|
430
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=sIaUmqgtlHW1lvmycafqWUAKyyLuf1L4t_ixzOiVmlA,2744
|
|
431
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=yl2lRcoGAKs1OQVKR2JX2C0VkpwUiCXGc_BTvh6h-r8,4146
|
|
432
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H200,dtype=int8_w8a16.json",sha256=NZUb5kQi0HyBrzhRyPl6pdKwB4F6KqHcJepwHWbxsYY,3248
|
|
433
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=H0K4_O1CMbNLi-srcycT3lSl4JaBl3EGF89GY5Rj9MU,4130
|
|
434
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=arPqstZMzZjz8BNpY3alKT4vGCJyUj5I2hEeK02aq98,4152
|
|
435
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=XcoSAxPTaefnIozjfToNebc2wdctRQQRc0Ju0d-QglY,3243
|
|
436
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=wjnQ4v-dflJMR3iFDHBuZI_1R0xXjsNoWc2kHu6C8JI,4135
|
|
437
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=7WHPz_0fxeI3Ed0D9VIpZVoeN9RtJVVARvptfcmQu40,4146
|
|
438
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=KPpfnhkIzT9JiiHDLakJlQvoNIzmCCq5NLpoKjZxaOU,3253
|
|
439
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=2kWS9Qvy5Q3mvUFmbPVures5iZAriAXsy8WrtE5wu00,3727
|
|
440
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=D2dn9vXyN4FCKsZCf7VYgAWLedCx8XpPjbkQVVAvwAA,4737
|
|
441
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=2kWS9Qvy5Q3mvUFmbPVures5iZAriAXsy8WrtE5wu00,3727
|
|
442
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H100,dtype=fp8_w8a8.json",sha256=IAD1itR3hNQyHzj6AyfNj7G974sVQEaYafewGm_OKdU,2747
|
|
443
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=l3y3uQkhlA2_7cbrDHsRslWXR9NzgtkD_BEQckJ-Of8,2746
|
|
444
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H200.json",sha256=2j-E88dNQghnJuIrCLwUn7QfUI66tieoCt6TIYjMvHQ,2743
|
|
445
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1856,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=mFxdW1jiRGxoW09LjL8rRHxgiJXXPgtGCCtjmj83UII,3272
|
|
446
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1856,device_name=NVIDIA_L40S.json",sha256=-wcihTQoV82En7NC9eU2QNlm46fjjdAW9ywahwBLzus,3281
|
|
447
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=5QqFljwwA8OaPlFnXy1zogl5oi6aE0OqN39xk2IUC64,3245
|
|
448
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I3k416HbXU_rYb8scD8gAI4fuBlElHl06PM347Qa11w,3253
|
|
449
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20-3e.json",sha256=CoC3pMKx0vkjI9T6rqRLTIwbDskxljTj31fCHI34B5w,3232
|
|
450
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20.json",sha256=RgV8C4F1LO09h01YsgF_eqX6GNoBtC7ulPfJRUUbg_g,3241
|
|
451
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H200.json",sha256=nsNEuDNks0tVLfQfIm7xxFwEeptTfQcoa9fJy0NS8xQ,3247
|
|
452
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=352,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=LCN-mYQ8xqL_ewIGV95k6EC_dfJtcdfQZp8uZR9Air4,2721
|
|
453
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=PvRpT_brUV3Y3zMfWEcsXMmdrYKjiq2qI9iHejPhhsU,3743
|
|
454
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=MCTOhQ01id6YjPtWbG6Mw5dlU1xtilsiq3HAstGn36w,3258
|
|
455
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=3o_aYn580j2L0ZPdKSTLqrYnginfBOFNhCksS5qxeNA,3258
|
|
456
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qbqjisJ4oKmcYzumHPRk5UyOzsdi8J6xas82UWHMeAI,3263
|
|
457
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=PflsK6VWRhwGaDKSIQ9vD7NMHcKLg3B4wENarR0aIq4,3252
|
|
458
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e.json",sha256=gkimxy2r78McckKxx4U4R3xahTI1KMH2pMOdUFOUdu8,3234
|
|
459
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20.json",sha256=vS2DRIDOqWyiBvbG6H746ownfkD1F8Aj2YZ0ET9xll8,3232
|
|
460
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=MlpzcrkZo78kFYr6cqmh4lBdpxKcEvlzqvRf0bmeduQ,3264
|
|
461
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200.json",sha256=xqhl748it8GV2KXX0XixitE_ywnsKksqK8AGL7tAgT8,3254
|
|
462
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=FsWbV4Q6AzAtgegVuENBDz2ZcSJsqNiwUIVfQbpP7hQ,3244
|
|
463
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=lvXUPgtRxDuNn7ESRNEzT7V2qStb5z8bAOGCOzP8q_U,3256
|
|
464
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=W8C1GtP4K43SK9128U52DD5WWofvPleAJE4us2Qju1k,3251
|
|
465
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ZrC8J_AmZWNx30UDrXG6sHWtFY6FNVPsNywLhEBQdi0,2530
|
|
466
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=rN55MyeJ8U6VGNRg7lwC3aa8BgjxdzVg-CofcZ7LTyk,3743
|
|
467
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI308X.json",sha256=SDxGApRr0Nl8Thz-99Y3vKEz2Aw60juCGo7zSQriMKg,5021
|
|
468
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HqskM2MV6SPZ5LskeOY50lOjFP0DFdYrgRpZFmTpWTo,3256
|
|
469
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=L7y3Ev8CbIF-68FWhoMvK9HH72bj6r6-09__zxK-fvo,3257
|
|
470
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=IuvyC8TNhCVAmUZfLSoETsyCKsmejKXrs_0zuwFLPAU,3265
|
|
471
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Nd2qn9-7yjO6vAQSHAuetP4ytysnd6UxekL8UADiLKg,3254
|
|
472
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json",sha256=10Ntu2aVD5vGLonx-jW0qNw-tgZWdZmzMGx7utDVeng,3237
|
|
473
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RFH5FcN2ZCPk6DsxviTti1Q8JU5jzBRFXvUQNgOvnmI,3265
|
|
474
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200.json",sha256=JraM-Nvbg5V_TJkSl6UPFYZN1zHHoIbr2pAcksenoTY,3248
|
|
475
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=bf16.json",sha256=PxeEH6PFy8bFefjyrPS1ikD_-kywMALWnSrGbpSjMQo,1804
|
|
476
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=-DrgCsN-PW9kWkr-bK4817zIuyxUa-CQxlONN1-QQAs,1798
|
|
477
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=928,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=iplHjPj366nNBu44ZHlCRe7aMaV2T4QthXINmkWi218,3269
|
|
478
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=928,device_name=NVIDIA_L40S.json",sha256=l59WyUnnymmJQykoJzEvvkzwlhIlmyEeVtvCFRzXGRM,3279
|
|
479
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=96,device_name=NVIDIA_H20.json",sha256=JtcHRlPz8xQEAqJ9EWI63oYvdmjQFG6VTHqtt85VOSA,3221
|
|
480
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=f3iM3xm8hGUirJ4ilAIPO6Pe9bs4sm3qaRKMswN9SKE,4731
|
|
481
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=Pux4G7sjfPL22uOJU6t35TXe-VU3OaoPA97TDj9_wZQ,3251
|
|
482
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200.json",sha256=he873aoOy7KfFg-uMoTFV4IP7Yk0Dk7mOTuLCTqwZZc,3250
|
|
483
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H100.json",sha256=Bq57MPQXuSib06u6OwiEmSzOr3XvPYoD6ohYDJaBnII,3244
|
|
484
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=95zLafBGPI4zCLqdsIjH7mgblYiBBTzGCItFRtKiQQw,2749
|
|
485
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H200.json",sha256=h63zG698KnzeDHL20MfxJ3cKiROnBd7GVZ-a6WgbcCw,2738
|
|
486
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=pCCKkdUzzuBVtljyk7AEIAbeDf12DUiieXaODZXzm5E,3254
|
|
487
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=trX2-c4N6hTTD6zFNi6A2bT3FkhxKjkM2rPl-o1K9ss,3250
|
|
488
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I4d56uD7E1JMXD9RAxq3FebdPquDsnNEkVaIY9Ctm9w,3246
|
|
489
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ypuAxMQ7JESPXLBltt68wly2wTrJzlnobhUMip6xAmc,2751
|
|
490
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=tUptlureu5QgyAEedtx5sm7CFudXAE6fIXepOb9gfas,2745
|
|
491
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=HUWDnLXTE_gHIeMSNJtgxrx5QK3ctTZYRtNim1TJUYg,2750
|
|
492
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=h57svdmDlZC_D8w9XWjPRS8ciYVkJiPEYfhrD2NRVVY,4127
|
|
493
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JmXhUnhX6YOy8RsmT0zFLGyNCpRBPV2q2Db9Y9ctZeE,4144
|
|
494
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=k7JkvPualha73fUM4GeVI822m-Zfl0P1c8DIw2b4R5A,3253
|
|
495
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=vvf0vmcIHMqctQ_X8j1LqlmkuImr46rDUCnl-apb6r0,3039
|
|
496
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=_4U3pXWYERfwF0Ig8UTSCmeEI1vKH2irHMEBov6ZNqA,2751
|
|
497
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2048,device_name=NVIDIA_H200.json",sha256=Lc8Wquo4hmXGkUq_HCxkxW1fzDnvE6jHZSEc28-i7lA,2741
|
|
498
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=G4PKqWxh0MlBhg7QHKj0m--_fP3Ll0gs7VJaeg-NIDM,3254
|
|
499
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=bKX9AvcxN6k-i3RUmHSchZZ3rjoYRYb4iBqhCI4L3MY,3257
|
|
500
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=bWR6XBZ4nJ_ROg8rEgrQGc04I3BDbwILDHMZxATO-H4,2740
|
|
501
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json",sha256=iUuPfTcmuEDLjHm-lUfJp_-b0mhnf1_RxRglKLJ83Jk,3259
|
|
502
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=AP6-GeoO8OtIcGA2kvJseui10HsvmFSjg5bHAaZ_aQ4,2753
|
|
503
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H200,dtype=int8_w8a16.json",sha256=KVACMsHRnkumqwKwAGIFFvogtqoPZ7XC6iM5KOZD6uU,3248
|
|
504
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=_9HO7SaR6aQeh6vqCDpo3kjHnGJ9BVKLiMwYYgd3SmQ,2913
|
|
505
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=2ONiQSa9odzdPe1dIgBpP24l5z-5wB1eos06xOj0V_Q,2738
|
|
506
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=Twkm9DVNxijpowfvioJ_4cKwIIlAWdyNWO9TA3gxAHs,4149
|
|
507
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=1xLr3PpmuUJD912yjzGoMmgvJQlazSao0V4f8nIJBT8,3254
|
|
508
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=THQWP1o2bWhnJh0rq3ZIVvs_sagIJgoK4x3pJbiFbHk,2910
|
|
509
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=o1pR3rNpO1eW4BHOKpPIQLjviw4P2X5Fr4HQBcdHA-I,2747
|
|
510
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=iySqae0zI_PRBLqV-vfSCwDS4Jxcl5QjWa2NnhndL0U,2752
|
|
511
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json",sha256=tDqh_env5r2Z3r9WLMH8fJ1oCGb83L7RrHk2eoH02-M,3258
|
|
512
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Ha6zrvORRUe8TH4DmVVnHKQIbxX6BnUmPER5rtWJz-U,2748
|
|
513
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ydsFUdXdVE_ZSScVhUxvxOFwKG-nkTraNeN69wqzxIM,2903
|
|
514
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=AMD_Instinct_MI300X.json",sha256=AFLeub_dwZHc4qEtvkQW03mfG9fdgeuqTTiP4qC8i1M,4767
|
|
515
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=AMD_Instinct_MI350_OAM,dtype=fp8_w8a8.json",sha256=RmeFztUNysKjmg89emtghZlGWl9uKqmlMupww44Q4j4,3735
|
|
516
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=TtDngG7ljrU5RtWZ7g-xxdBT3uEuawiKhP8EwPr97XM,3254
|
|
517
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H20-3e.json",sha256=u09XGUdUQqSDasrUgOQeu7ydp5ft5US1oSM0iT-BT3M,3235
|
|
518
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=UVpaplev1WCtwa80V-InUtof7OuHfe9owQthaTfqK80,3299
|
|
519
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=320,device_name=NVIDIA_H20-3e.json",sha256=JBO_l8hfxCbiQ_PvoqS3Xxqlz9i5PP7QFfXjGKLf7bw,3237
|
|
520
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=Hjpi5BF5UjT0R0uuluIeZMWihlAM9zyWdV5Y2BJu0_w,3730
|
|
521
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI350_OAM,dtype=fp8_w8a8.json",sha256=KudLj1Md-XBFWsivs_7aGg-UQno7H6tzxyYqHQKoNg0,3734
|
|
522
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI355_OAM,dtype=fp8_w8a8.json",sha256=6QmGz-7RZzAT1-XS2twHGAbEpjm2Tpkn7qjfBMqm76g,3736
|
|
523
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_HrEta1vlWll_2c0v6RpEIUQirMD1QaOMU81VaJh9Nc,3254
|
|
524
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HvSQqJi8Lb7NBGmvp9YeF8k3nB0t94DJ-LvCX6Spjyk,3255
|
|
525
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=EZV3ffICZEq6X16UNFpHL7kOuV_qmj1L8fJu_F1c-DM,3260
|
|
526
|
+
"vllm/model_executor/layers/fused_moe/configs/E=20,N=1536,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Server_Edition,dtype=fp8_w8a8.json",sha256=JrbI8lzY5deo9Lx1rw7noHf1jzPcOv9vcni__wDnZ5E,3288
|
|
527
|
+
"vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=rKQwdgkictjg9DjBFVzHq9LOMlX_Ul27jllTABjaUtU,3252
|
|
528
|
+
"vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qKcB2Ka8jkahKCNF215Ec6rCoy31OrElDL1ZHNgCs3M,3252
|
|
529
|
+
"vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=K1aeYxtOM4niB6auzCEBVudmKIKNzHPjMoFeQt_KD-A,3263
|
|
530
|
+
"vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=rtOl3v_tR1iCF-Em0KihtLFzK5qLtndPK-jKCERLbNg,3264
|
|
531
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325X,block_shape=[128,128].json",sha256=fT7fwjuit4HbbyREYV3ECJ9Rm88FW-V54e27nG9nA_Q,4741
|
|
532
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fT7fwjuit4HbbyREYV3ECJ9Rm88FW-V54e27nG9nA_Q,4741
|
|
533
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=HNvrgcXxV-eVMLwb7zY_R5KgJ7uBz-YIyQsKq1lWnWA,3263
|
|
534
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json",sha256=bHJEVy-CeImiY9JBRCMlHfHPAUi5xO7ENxgVVboN2Yo,3258
|
|
535
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=PnNmKSRFznCIUzZ4ZfaYTrMHeF2_kCQr4_bsEy_9Zu8,3259
|
|
536
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json",sha256=0Vlxxzp4wrvkFj-NF4OAsJAaPkm-hhisJg0tgNl-W9g,3254
|
|
537
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0aSYzpv_cBAlpWCPrfGgNTCfae1KdKQnT56E8XFQl7A,3262
|
|
538
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Lqom_VMIPduSZTZQdeL2Wl_x3r9q6RmI9bojJrYwQZ4,3255
|
|
539
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fd2p65T9OboKIgw7MQc4IdKaJsoO73Nu3VQiKjV6Ffk,3261
|
|
540
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FUGuYbs_QhqKfErofvbTUplhAVN465A7NR_-ryXvebE,3741
|
|
541
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bpDPbTyrXLyCSy-o0diveVVeVUF_xj-fdSzCzWmEcKA,4733
|
|
542
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bpDPbTyrXLyCSy-o0diveVVeVUF_xj-fdSzCzWmEcKA,4733
|
|
543
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=skSJdv0Pr4rba5ODxp-fHZ6dpxn8KkvACGzNf74j81I,3257
|
|
544
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=wMt0NyoRSdACdmS1Qi3qFiu6GiFX-4lVvbGEno1W4zE,3252
|
|
545
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=mtm7RgEBEJJkHsOis9BtAFo1OCk3vBbt7l7eumDzd7k,3263
|
|
546
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kfEjBrcwt21QRzimrgY_SQ0syJVJzx0AcWQcKQ3j5sQ,3254
|
|
547
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Vz1g-YtTWcv573EYaR7LzhJlRyonaMsHPT2MMjuRJ9k,3270
|
|
548
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=JnqtO0t2HBcQECdYavi18mu9_MwblGr4zfRcW4zU7_c,3265
|
|
549
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=b9odBjWC1mjQRIIZIFV8UPMTVE4axTP8vkmOXfdUids,3296
|
|
550
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bpDPbTyrXLyCSy-o0diveVVeVUF_xj-fdSzCzWmEcKA,4733
|
|
551
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=l8y606GTM4Xnd9CBdhjt7LuA_1KLQS41PInHKNfZAZM,3242
|
|
552
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=rVORXxNsxy4WmO5SJR8Sd4k7vozKqhYf50wZNCMeQzs,3239
|
|
553
|
+
"vllm/model_executor/layers/fused_moe/configs/E=32,N=1408,device_name=NVIDIA_B200.json",sha256=PoVwSGuqyF_0DrRTrggdmlfhUn2dmSbc-pP4PjMEF4k,3278
|
|
554
|
+
"vllm/model_executor/layers/fused_moe/configs/E=32,N=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=r0vxILYelmq7KarzO-3yjv9fA0Z4ORzCo7u_UgWbdXQ,3292
|
|
555
|
+
"vllm/model_executor/layers/fused_moe/configs/E=32,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=IOYqUudflMQ7PBGNxFYihtuVqb-J4eVp5BmL_OnIFS4,3287
|
|
556
|
+
"vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ZvsFOizI7EY5V_V5gdjyTgbdJfeKrbxhISxcppSfduo,3255
|
|
557
|
+
"vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=1XFStvhg3yV7cMwJcpbLfaCY2B3nqZNrJgohJn0ma5g,3254
|
|
558
|
+
"vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=iXoa10iZi9EQ5jAiMIu3hCemsvjiWVBtn4rKVarVCCA,3256
|
|
559
|
+
"vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=BdVjlDZWnX6_rduBTQWfc6Gb4o9z8JRlI5XF00CnJC8,3255
|
|
560
|
+
"vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=KPI0AqxGlxtJ18tj-NiFjBleS_ihwmLSt5pg3GXGJ-c,3255
|
|
561
|
+
"vllm/model_executor/layers/fused_moe/configs/E=40,N=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=pwoiPdk-veNV7Um7os7sG5UrRjKgOsbyxMfQG4z4r9g,3285
|
|
562
|
+
"vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=S3nHQ7okmQlkuz7gQnHmZWcQQnFDacB4Lz1isbdZ49k,3258
|
|
563
|
+
"vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=86ajYfCiq1urzJxcPrvyx884njCMKizCrS6hfx69WPM,3252
|
|
564
|
+
"vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=86HDa0gqUZkPaOJLmuax-j-HBC7t5P48NuKMpH5Uj3g,3262
|
|
565
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=qZgSX927zWhvdQc7KjSBZt-Wk11LTwFIK8UtEU9AFJM,3274
|
|
566
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200.json",sha256=NBj9yhhUWHpNcvwYhPtBKEn1It7BbrnRMRN6Ji2Iazo,3234
|
|
567
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json",sha256=XP1z8IdGklVXVkMIbCtAzWj8nUz65GIZaqZvBvD7v4M,3242
|
|
568
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=7FM4MDavNVOcEOFldsZs5H-E5O6EIAHDY9n-aiLY_Kg,3238
|
|
569
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H20-3e.json",sha256=DaChAo79RafXGjpAOeO1CQ9DazPk7Vazb5bAEyDOYSA,3233
|
|
570
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H200.json",sha256=BB3qPMREaACzWHmhvcETQHLDYGX7GXTKr1E5cm29uC0,3235
|
|
571
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200.json",sha256=0avMzgfoHRzULbxIdzI1SVCWUSBP10kKvxy-3Mv_y_M,3243
|
|
572
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json",sha256=yIEwME0J6ZNfGq13Vj7OA9DmUyKdFZzFj8uaLVb2Yp8,3246
|
|
573
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=YopFXEwMf6qpCwrQ5OdJtGVsDvvaQFUcEuGGIFvmS4w,3286
|
|
574
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=pnK1HQ2B5ECqCBolRa5Yb4qAClVoJ2pidBnPy3GBLeY,3244
|
|
575
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H20-3e.json",sha256=q5AAAH8gIaU--3mXhSF1VdFTFHNAy5c-gUvYcm9qhEg,3235
|
|
576
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H200.json",sha256=he8rleYTT40kpshJW1FsdiyR0nRU367CqytS-9-UZNs,3243
|
|
577
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200.json",sha256=LcMD2JddiX488ddRCsh0cXaf3my0VT0IweqQDyTWZwc,3245
|
|
578
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json",sha256=44VdfyrLo-gl23cMeSqSfoGrsqWcjv5-lXwU5y5spE8,3250
|
|
579
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=SyMqNl2wL11cbj95x14YynB4YwyQlaOf1yPPIK0jcJQ,3249
|
|
580
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H20-3e.json",sha256=npr855kvWlHILzi5M0sjYjofPAO9bf6WCF2oZZ4u3to,3236
|
|
581
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H200.json",sha256=xR_v4wy8_ae9fGyuTnhWY0d29NwC9ChPKvdCK5_PS2Y,3244
|
|
582
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=9M3IlMbbIrCvfhQQHsY08NAOoaR8pdd57E30JYPKlRk,3264
|
|
583
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_B200.json",sha256=femFBZsNptZ6DlQ32dpBu4zhFxaG-kcs4MFPTxipui0,3234
|
|
584
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H20-3e.json",sha256=iVnryOC43Rirq38PwPxzIHrWvf6pA4wHZtf1HOgGtlI,3232
|
|
585
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H200.json",sha256=K1HkIsowgSbvwtAppZZPudYIIni_waoSxDkARTCEQso,3238
|
|
586
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json",sha256=4UXbsSNHmrSWnD85SdRMLp4cFGRufndzJjB6hoQPclU,4736
|
|
587
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json",sha256=p6TKUp-KDeLB9E9LqThR1e7J2-ogSXPJojISdHgCxaY,4727
|
|
588
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json",sha256=gHxtmO_uvpueLVlsJgXBVE3_pS1S9EeRxNmHG_ZQszg,4729
|
|
589
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json",sha256=tVdpbIU1scsylx6oz3IADhkcwvZaNqw-_QVb7a6oVX8,4732
|
|
590
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=128,device_name=AMD_Instinct_MI300X.json",sha256=_Mn_3ZuKGqNnXtcUUZA0rr29c_lcp-b32uw57oYHgVM,4721
|
|
591
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=AMD_Instinct_MI300X.json",sha256=2eFdAHTU_YTTVad_OEcYZcSbtm5gtlHg4ChxU_v1a_k,4725
|
|
592
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=sCmfFCa-I5Nft9ap-ScL0PVEKZFibkhtVslbFs_NLQ8,3234
|
|
593
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=AMD_Instinct_MI300X.json",sha256=kKu6HpksA-NKVS4CA2ivjlAQEshl1HEufQ0Qt-lTZGM,4732
|
|
594
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=KmYAPOgz-2qn2c5lY8u9XRy8i8HNkmOR5m45TIuwt4s,3235
|
|
595
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=6QPLhZurIqcMVdy3w0Dd7gLViKxsyJRBz-qd8agpi6Q,3248
|
|
596
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=WPu80-OWyEJBy1hdnewLN1H1neFW8UVJrqyeDGegXc0,3250
|
|
597
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=PaFLbT5ftJiiVSOVkq_DH01EcbIs0sBVkCd9PdYYmw4,3253
|
|
598
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ozS2ECxk-Dsd4Y9DgCGGwDwJlCf5T20ANf5gnTUMuSc,3252
|
|
599
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=KEN6xt8pgPH_FbLT2fsAD4s03_V-Z9GXuEC4IKe3cPg,3262
|
|
600
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200.json",sha256=w18R3eHB4oUhfbcCXjHyDvp0RiDSeCrfM-VFESim2hQ,3253
|
|
601
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1408,device_name=NVIDIA_B200.json",sha256=4MqYiUxVPLgkiaTl1vZ5Q5wCwsLYNp7O2-kbOSYmKjI,3277
|
|
602
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=Nm3LPD8JxBYGflI42Cy-xyxZlBLrGvVbnkf9NUmx92U,3250
|
|
603
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=iz4W1UAV1fcz1ZFh4hNQSLJ_F1MdXW-V3msy7t0WrRM,3262
|
|
604
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=dYpKgvuG7Jji0W0zg_E9NfIojStBAdBcKd4B3nhimqk,3263
|
|
605
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200.json",sha256=CXiHlGpea5cEGmFi28Jec34uxEZITF2XldVFcJteZX0,3251
|
|
606
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=hLFfmEnpHDZlwBlx7TzfxbjCEywqHEuhjllVR7g9yMY,3259
|
|
607
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20.json",sha256=g3M9w0Noi3DyQB7fcr3jUM62_LKZvTwbY2GtzDGd9_o,3251
|
|
608
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=W1q4PfievvgJ_SiPsDhOsR0Q0eJKb4o8JZhMcVhC-_4,3264
|
|
609
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tku4-yTbIr0H5TNrm1Pq3tJJFYTXqHpdzJDSEF3bk9A,3238
|
|
610
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=HJcV-Tzt-yojzNQkPCgi84B44F_RppXxOIicRyg20-U,3264
|
|
611
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200.json",sha256=bM9g-XpirsThO3Q2x8ChSx3PPtHuHRXLvVMnTWt8jLI,3243
|
|
612
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=9vB_5KLq88zBCNpyz6LE7qAo2eS_sgTNsOh6awGnjT0,3235
|
|
613
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20.json",sha256=b6lqVlPt68GZ1wlYu3UtC6zkXnnnKwh4tKGltXNvTVY,3235
|
|
614
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=oxOKFDrgmw1YmgxTtRa1uoe3p09ylTLrkj_jOTqNh1Q,3249
|
|
615
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=-B6gZAEYLwMJZOnpO81pTxqs-YVKs_144Nn9BSLaMh0,3247
|
|
616
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=GPjPHicomrS7ntHu7nnvgNXcHCoUw9vhyTUewkXpppo,3252
|
|
617
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ObHUCUAgHTnld8Cq9Dy1n3ilmbBzyNC4jZcz6YYhMXA,3264
|
|
618
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=WegYsHl39QVlHu_4EZJSrgA4LQ5fYxSVNWFhoL6W2Rc,3251
|
|
619
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Hrlas0Nt7d3JMr1vTpI3OVgkzxqcRziSMfFf_U5pQ58,3267
|
|
620
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200.json",sha256=J59rmqF8NQWkqmay__ahA3t3IwaPXNu5AVNLnTaDfYA,3252
|
|
621
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H100_PCIe,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=d_tIZcrWnGVvgmXBpIbsFMAKKC9-1eP6nbZSqWgzOm8,3288
|
|
622
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=0bH7NZ6VmBBycMus6v7sDXCXtort9awuEpttLLMTZms,3242
|
|
623
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20.json",sha256=VptbMpckYKHKYMJZS-EaO9G0cSL6nciL9XyeHiZN4Fg,3237
|
|
624
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=896,device_name=NVIDIA_H20.json",sha256=GNbp4W4MBoHHN4-0sXJovY0lX6rHfZzGyKicrumupGQ,3225
|
|
625
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=bf16.json",sha256=AbwYfuQiAbPJb3Okwd-BCTWs2P2Ao9REEh2sFOkoMuo,1804
|
|
626
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=FiUQOl86K_LlCd_RmJR3BpDM8whX07CE6Q-6pp1rR9w,1797
|
|
627
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=192,device_name=AMD_Instinct_MI300X.json",sha256=r36dUUfR5rv7yS_I8W56z99VAa8LIfaNRQko_97R14c,4720
|
|
628
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=AMD_Instinct_MI300X.json",sha256=XMMCswkzdQxVfOBDM0KXG_ryA9JnX4hFKhF2QspifsY,4724
|
|
629
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=56iA4xNOSuaGWgz2Qg-NiROhpdoBMto4NVUnisUsyD8,3238
|
|
630
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=AMD_Instinct_MI300X.json",sha256=68SI7XVkxHS0k9ApTW1-nSnIqOtbe8rmatNexWRFyqU,4736
|
|
631
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ICdOnZoM8waiOVeVYP18QiPDSbtg9Q6yO-OrO0-2xtI,3242
|
|
632
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=X8FVPE7rLblDs_Dw_Iu-KDw9H7PaC417EHyVclYjfv8,3733
|
|
633
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json",sha256=FsIv5bqSpkWbxK2dBfg1N6tX9epZ55ZhgkJCD7hENlY,4733
|
|
634
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=CnjQX3SlQn6fIGsX6P_dbNO0TYgAd-sVUb1FfDcDFUo,3732
|
|
635
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json",sha256=fnO-v4YqBz0vUo0UtOTTD0n7VDG_ivczeQ1tR6Qm9f0,4734
|
|
636
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=V_sgDtEtGEuBsGVa0maYJHhhGqe1NE7l-1ek2ed9WP8,3082
|
|
637
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=QaITFIJU4UsrOBXaGdPYJwTmYJ0nT9kiiqeUiZzvd1k,3270
|
|
638
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200.json",sha256=CC_jsMhXzrYne7eIOroDa0fCBKNnffiaVW2TKd4P-ek,3260
|
|
639
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=LgHbxG1kQV36zZPkJcnurHYzwAjMh04lvEHEsfzS1t0,3732
|
|
640
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json",sha256=_fcdkmWvdMqHiH8ZAGke-zXhH7qVPQx5CmKELW5hRCA,4735
|
|
641
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=mVH8Rl4sLATinf7_0A9lTS83kv1E7Cm9oC0BL-pc9n4,3732
|
|
642
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json",sha256=JKYW21c0CzR0fgE5ZnYp6C1sY_tVRlm8L_lgak5V5zE,4736
|
|
643
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=yTf2R9cngSf4OafucAYlDDn4-bftaMFKaY7qhaBZPqQ,3739
|
|
644
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json",sha256=_1eVE7ok935L2V43-3D3bVNWSVaoViia19sh0VrXmXM,4735
|
|
645
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=5exlPUKvZxGDR0UT4_Dn5fp-_ZETJ6_Dbw_Vk1u8bbE,3735
|
|
646
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json",sha256=18v6YruKbQ95pXPV8ocV4VdM1zNw3aZFp3WByeUkNSM,4736
|
|
647
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=AffDc0_51ML8HiA3757zbD10TZJdUsUDIYIqO4g0yUw,3250
|
|
648
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=IEYBNjt9HGnzoOVSWvL0A0jUqq926QD0_BvVYR4RA1Y,3252
|
|
649
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=Ns9Y12aZbJnFhcG3nwb67bDqqiQAo9tdTAIe8K2Ajz4,3255
|
|
650
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=uGSLFPZXK_JQ3GTDUAEiIecDor1yjbC3bJvMolF0Xl8,3267
|
|
651
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200.json",sha256=8q6ol5JQBWj6yVfzFOn7Gz5MSXTaW9javL7qQmYVOwg,3245
|
|
652
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=6jRC0oOpVpq5c1xePFKNRy-Xtmb038i4LE9N2zao2W4,3730
|
|
653
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json",sha256=cFWeyNJtEbs-Bfohgzclxo1rcYGU863oV0BzJyQ4T0w,4734
|
|
654
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=SMtsqtQeqcyy8aNwl9hPxRvx_XQdT7I3SBDNJ3OIvwY,3728
|
|
655
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.json",sha256=ZyOFJB6GUgGZsAjjT43XJwG8P-QrZ5yTvmgzQP7ThQY,4734
|
|
656
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=HOxWmCI2ifHmWc0or2y8nEen86jDeLDov1-tuMzuhxo,3256
|
|
657
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=csHezh0HGWaNwrblGzMgcE95hqbqjWS8HImLRJYr_ts,3266
|
|
658
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=_5weLBinQCDzyV75hHKIT95Y0ce94KWft2_5BC6EkbQ,3254
|
|
659
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=BTpwe2RgMbzP9MTtbcJ16I1IAK0ghD0rauWEea8TOKE,3446
|
|
660
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=DlatRLPaSr8HJuO50gRZ2lzXoelx55EP3SDUdgIT2v4,3269
|
|
661
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200.json",sha256=TXSOoqvi-x8H13xPqrB9qz2T3opEGA-2D0v_4n5BEG4,3259
|
|
662
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ro3drDpWAdeXH7IjMvx8wYGhIuDPOl0bpbJaIB5Msns,3732
|
|
663
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json",sha256=w_R2LL8k5jNVUARcqvSgGLvNoQiQC0Mh73ciqSIAz54,4734
|
|
664
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=hjDoTXRmEFLKhhmBFEjPowQus_z23ISonxFljql3c9k,3732
|
|
665
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json",sha256=AdOTy7ASetdAXUhNM8buoU8_rLLjcUYF0m8RGFrLWRo,4733
|
|
666
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=Ru460ZgnUP4U8OsJfwF8n-AI-gfcolNR3_qzoxG6DtY,3254
|
|
667
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=K6BGrKw_oHTAtHjsZldcjp-BUM1dIecKXrrRn9OpRGs,3254
|
|
668
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=4aK_plqztXcJ-hs5_PsAvM0jclMzcO3hd3zTo0FhDro,3251
|
|
669
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=qqFoMaObuO8pFWcSb9q0wYsdC4eSCO7B-_ruQhR1N9M,3264
|
|
670
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=-5nkLIunjG1ghPoUEtt2AXEQw9oGiilP7K3UvQv9CqE,3252
|
|
671
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WKzddrIXo-KavpuXuouW3aLLAptu5Q4XJUb5K2PLgDM,3262
|
|
672
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200.json",sha256=ad1ZkkSyLJwRGb4Kf24qg5hW_DPmt0BXrKR85oAiV34,3257
|
|
673
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_L40S.json",sha256=qX5_yErBEwDRzhv2FvxrS3pEMa8zn0GHzLp5TUMX90g,3872
|
|
674
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ysRCWmxV20K2BYD9XEUtxwREFGtA3QHI191vHRA0k_Q,3733
|
|
675
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json",sha256=L8VA1sfygHoyLJ-Ybfs8DP5c0YWFmMkwxHT8yJ9PEFM,4732
|
|
676
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=FJWpDLr13XF3hHiHfJykpjbLiP7Ccu2en3U6BL-QwXw,3732
|
|
677
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X.json",sha256=FnVcfzf5gXkQRt0XgsRzIQVbDPaUDOwWJX_9qOlyvRc,4731
|
|
678
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=DxYu8regZOSFu8ugFGA_QbwWK4g8xwQUZF9a_nNY4Cs,3255
|
|
679
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=obzfE_9XgsbFNfC9biYOHxR-V_Bgc7PKT8qZZJaiJJc,3262
|
|
680
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=qwKy8oaMsd3QrXgQbM_x9xcfYiHK_Ou1CEwDPL5Gbgo,3259
|
|
681
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=qUifbWbE4cOKZbIHWmmLx68VRaslQX69eZHwRIQx-7I,3269
|
|
682
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200.json",sha256=JT-ZMLhAqqzSkqivOW5ATTKRlyyaFQkqQDnaPS4DE10,3262
|
|
683
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=QsR-Xr9vyuiArMTSo-dX-1DFgATfqwIGOzFuQJAuE_Y,3734
|
|
684
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json",sha256=EtVorGY4khTEuimlqZu0AAlPz84PH3ZkDZmVpxLtgQw,4735
|
|
685
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=D3wX0_s_ylo3nLIUfaWZmGYtMvX7oiieOLMdQ9k7mng,3734
|
|
686
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json",sha256=JPdO0azlh4yUvbpC9dEHYpRT11ELEr5LXBSb5XP4E_4,4735
|
|
687
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=BAJnXTZoewwCtzJLUPJ0oYuALv640MvDuLseGcsYaaw,3252
|
|
688
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=-Tj7ImS6ZFDof_0VTyq7kVm8XD9B54RD6CUOPSf3Jjg,3265
|
|
689
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tme0ydWzIxdABZLk4tU8G_X2dJUYGGZNkQzNGcmcvUc,3261
|
|
690
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=g6Ivy4wvadaCAMJ4ZElbUU-CwyTMdbaa49M7IVQhVjk,3273
|
|
691
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200.json",sha256=GstQosPPHUn_I2DV3eMGtn3xXOw6kl1hb8L0EvRsbEU,3261
|
|
692
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=kF4Fx0yHUmiMSLFNXT6xqAEA4AgCaHOoy_3irv4dNss,3732
|
|
693
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json",sha256=uOlVzTdJl_4VrRK4wmxIb8JKfveFZRjO9syjw_oEeL0,4732
|
|
694
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=plnx7r9jkcYXkhvapbeeNvUg3NMGdGsIgIPSrfVy2qU,3733
|
|
695
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X.json",sha256=UC-iTgh8_dUSXRaYHOIhDH31KOiJmcfqM_Bv_UBf3ks,4733
|
|
696
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=sY2nWMPh9lsIkhPCjkHO245wpnfFbrHmzdcZDVFPVww,3265
|
|
697
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WQLKugnKzlQ0avf1N-41lRHtG6wJ56DfVPv_nip6NBc,3273
|
|
698
|
+
vllm/model_executor/layers/fused_moe/configs/README,sha256=W2yIZkP9O8GGlg97We9BJfTtWUtPbuz5ZH3esrrjBX0,572
|
|
699
|
+
vllm/model_executor/layers/mamba/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
700
|
+
vllm/model_executor/layers/mamba/abstract.py,sha256=NCKMGO3DAB5RO17TV5kGfzKGVIb2_vb2PlU3jxv_cko,2433
|
|
701
|
+
vllm/model_executor/layers/mamba/linear_attn.py,sha256=jzyAKLuAjU95agGZE9pyZv61zK2XI5d-FxXucIWs_Rg,14397
|
|
702
|
+
vllm/model_executor/layers/mamba/mamba_mixer.py,sha256=LIxloUP5G8nk5NKyR0Ex8s70y4izBhUeM15ysrS7GIo,19843
|
|
703
|
+
vllm/model_executor/layers/mamba/mamba_mixer2.py,sha256=FKfRbUklyWcBOn65jWCYD_w3zfuXc4EXXzp9QdDFOGs,37509
|
|
704
|
+
vllm/model_executor/layers/mamba/mamba_utils.py,sha256=UevD33ksJN7oTSto0uUpHUZQfv2EVmMMW8YQgtKuoFA,7511
|
|
705
|
+
vllm/model_executor/layers/mamba/short_conv.py,sha256=StCwhWpIuD3zp4qnHji6ew-KtkN-HjoRdXfNrnxoJTM,8442
|
|
706
|
+
vllm/model_executor/layers/mamba/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
707
|
+
vllm/model_executor/layers/mamba/ops/causal_conv1d.py,sha256=q-isreyIw522evOyXtC2ij80eK4IyejfhsLOZxIu9P4,49540
|
|
708
|
+
vllm/model_executor/layers/mamba/ops/layernorm_gated.py,sha256=KA5JRI8jEStDEkN6U6dqaOBQSCWugxUelAhZISZyf7A,5228
|
|
709
|
+
vllm/model_executor/layers/mamba/ops/mamba_ssm.py,sha256=uD__R1MjEURDEiubfvKIUqftP9Z-COIsSBvmVHHj-Js,15494
|
|
710
|
+
vllm/model_executor/layers/mamba/ops/ssd_bmm.py,sha256=mlQ258Jsexnb5vHGh09YW0l-rF3SZM4H1R29o3hb2-s,6842
|
|
711
|
+
vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py,sha256=Yow2h10PSWWKvrwT3TRz7UZTCq--99j7MZToXN59aCc,15550
|
|
712
|
+
vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py,sha256=6-0Dl2-frs5av7ra-H0xHWPupVaSo0Vex4d5vZVq41Q,24226
|
|
713
|
+
vllm/model_executor/layers/mamba/ops/ssd_combined.py,sha256=oKPphPh0wjU3XT3k5U2t9cHb4jDLuYzIQuWK9w0sOcs,7353
|
|
714
|
+
vllm/model_executor/layers/mamba/ops/ssd_state_passing.py,sha256=OWIEJ6WjdYHbX_7HRzhPt50oejUjvzhBTST6bQPhjas,5275
|
|
715
|
+
vllm/model_executor/layers/quantization/__init__.py,sha256=2gYfALFul_M0V4YTQxkFpQ6qEGA3Xa8IgUY9m_dDUWg,5714
|
|
716
|
+
vllm/model_executor/layers/quantization/auto_round.py,sha256=zXxPKBK_SghxULSckPl6Bun8LpT8r7pr7FyJ6GbXza8,16827
|
|
717
|
+
vllm/model_executor/layers/quantization/awq.py,sha256=ndAuoaJlJI2cL-sTCDeT5LEanOXo_VhABBCyv1PLGtM,10022
|
|
718
|
+
vllm/model_executor/layers/quantization/awq_marlin.py,sha256=0EtNoNLb7jXD7ETB-7wLyAMWFg4Uc2YVzlPcctp2U4U,26508
|
|
719
|
+
vllm/model_executor/layers/quantization/awq_triton.py,sha256=fRH9rX5jDSqQtdmcrXwxtPtQEiKxTUdPkAJmtvW_zng,11620
|
|
720
|
+
vllm/model_executor/layers/quantization/base_config.py,sha256=1iCxfCdxsz4ZJ64SzDK6QUsDsW50jJgb8Q3K4K8C0yk,5765
|
|
721
|
+
vllm/model_executor/layers/quantization/bitblas.py,sha256=QGNzQWDLRRvohawjWVUVMLoK9_GyKDEEjVDm70qQLgY,17358
|
|
722
|
+
vllm/model_executor/layers/quantization/bitsandbytes.py,sha256=C6hlp3comlMq-bgxQ4KTm38oapT6ladfzBLp9zoo-xk,21843
|
|
723
|
+
vllm/model_executor/layers/quantization/cpu_wna16.py,sha256=sKGxw3NqDGG80hXUhibYzOSAsqZuthmmiywy0LDXhBA,21710
|
|
724
|
+
vllm/model_executor/layers/quantization/deepspeedfp.py,sha256=f8fKA4ZPKhEFCuv7jcZIrC8IQd6wXDecddoWbMSkCzE,7278
|
|
725
|
+
vllm/model_executor/layers/quantization/experts_int8.py,sha256=ujpbQaSiY9xelP2LHWsKXgQGu5slkTfzaV4j59tZ4Jw,7703
|
|
726
|
+
vllm/model_executor/layers/quantization/fbgemm_fp8.py,sha256=2SZDxFbn1T_FVhR6hGj-c-6oyGw7fJQqTHbpSkY4PCI,6621
|
|
727
|
+
vllm/model_executor/layers/quantization/fp8.py,sha256=qgZIbn3EbwQft8nxxLnBUwDlC0wa_m8jMHBjuOTLssA,55496
|
|
728
|
+
vllm/model_executor/layers/quantization/fp_quant.py,sha256=lp6PRY-Hwu5QfUChi4yJ3z9shstEnQzUHLlkEnDNN6c,12858
|
|
729
|
+
vllm/model_executor/layers/quantization/gguf.py,sha256=dlQ4oERek62mgEAA9TgoOIWNTrW_nO5BqQb-oKXzNNs,23658
|
|
730
|
+
vllm/model_executor/layers/quantization/gptq.py,sha256=ZuszLML4Og7f8eTZmdEEwCZAAeNj9YjA9wz46wIR46E,14814
|
|
731
|
+
vllm/model_executor/layers/quantization/gptq_bitblas.py,sha256=rPSt1jT8dyqdslSyGHd_hDB3uIUVRalCbA3SHMs0R3I,16626
|
|
732
|
+
vllm/model_executor/layers/quantization/gptq_marlin.py,sha256=4Rr9I8W7lLWMYdGGI5JhNI5yjMqA0_ehGst5Q6eu8ik,31621
|
|
733
|
+
vllm/model_executor/layers/quantization/gptq_marlin_24.py,sha256=PNVtvV2PCMPU_J1UtXlzrZmeOMfEXEfR5_KSYLZlUoY,10559
|
|
734
|
+
vllm/model_executor/layers/quantization/hqq_marlin.py,sha256=XvtWwpRWWwXG-ihjyOD-jRi4MJhVnIybrm-H-DQAkec,12502
|
|
735
|
+
vllm/model_executor/layers/quantization/inc.py,sha256=mJJ0pQCm-rFafcbsv-0BBK9AooCtQ4nK5OdpPQfg2Ds,2252
|
|
736
|
+
vllm/model_executor/layers/quantization/input_quant_fp8.py,sha256=6ep_71E7Yc0Y3-1DCOWWcRI-Kz32MsITjulFLpQf3Jk,6484
|
|
737
|
+
vllm/model_executor/layers/quantization/ipex_quant.py,sha256=SWUBYdOEVkqO176ZMybgwEOLiHLxOiODV6UlKSjL5eY,17492
|
|
738
|
+
vllm/model_executor/layers/quantization/kv_cache.py,sha256=K0Kn8peguLbNHvkl25ZK8WH-_hCMn8OS1O7D4XZMxjg,6210
|
|
739
|
+
vllm/model_executor/layers/quantization/modelopt.py,sha256=i2jSXBFEYapf6URHgFlvs9n1t4DJ4JcH3myz9m_-Fv4,62603
|
|
740
|
+
vllm/model_executor/layers/quantization/moe_wna16.py,sha256=Io0vciPOAhUOtL3vy_uJ3Jppafrworph-MR3XWr7G34,20765
|
|
741
|
+
vllm/model_executor/layers/quantization/mxfp4.py,sha256=1m48E1tsIhJMBhZHIc7KbeZOmeQe8js6fsENu0U4GlM,47492
|
|
742
|
+
vllm/model_executor/layers/quantization/petit.py,sha256=2HAoBRMEo8ycxaim16mX9myhN_4crVcnq_Z3J2Pt5K8,11560
|
|
743
|
+
vllm/model_executor/layers/quantization/ptpc_fp8.py,sha256=KFL09instchp8zU6roq3b5fCSzw9QV2nJRVT8HiDm14,5088
|
|
744
|
+
vllm/model_executor/layers/quantization/qutlass_utils.py,sha256=lLu6gVZoWiitJh0VXCPIAXpizT472Eyqi0GcSriVFx8,5641
|
|
745
|
+
vllm/model_executor/layers/quantization/rtn.py,sha256=ZpGVoEudN5VoXFYozgJ5yl5RMOINW-lUqr7JTGZf6kM,20623
|
|
746
|
+
vllm/model_executor/layers/quantization/schema.py,sha256=bOHc_0KCkTYR4BhpgGG6Sc1g0legFhDyt8S9HjjFItw,3807
|
|
747
|
+
vllm/model_executor/layers/quantization/torchao.py,sha256=y1F-T5v7SFyT7ktl9HH-q5rW92oa7DZY8Q2MK8CON_A,13454
|
|
748
|
+
vllm/model_executor/layers/quantization/tpu_int8.py,sha256=NG9vRjqpPFdPPmH8VJagcqInBYTKNslUNBVWfGQwq40,4681
|
|
749
|
+
vllm/model_executor/layers/quantization/compressed_tensors/__init__.py,sha256=PRLyXFLYk26eH3Y5R_HtJSmz_eK5Fw7C-1liuvMlz3I,108
|
|
750
|
+
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=vxyYZzZ0A-bIJb-HGW1kgdbHh3BNiBjM5HNGRpRPnoE,37287
|
|
751
|
+
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=Jk92SbvZM7nYJF8ZLdoOBHozvHvYOWNomE43eg2Zxso,93103
|
|
752
|
+
vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py,sha256=TkQU56VWuQL9mzvskUDn65wqCGo2jDDfHl3O-WSniK8,7113
|
|
753
|
+
vllm/model_executor/layers/quantization/compressed_tensors/utils.py,sha256=MGBWAxDxZxB37rkc2nvxCg-PPhz--akasm86cdODMcc,7563
|
|
754
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=e-cfknR2aOVB5hznA58BE2_zqXxBoAJXCmozfrc-ook,1380
|
|
755
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py,sha256=T9Q0a6UphFHPh1zD0SU2VFFuipS7Il0gAmIsPT6wyXQ,14327
|
|
756
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=UfHG3dCxyrZjzdqdgDkmlcsUkbKWqwmEzQrwWGAfq_c,1552
|
|
757
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py,sha256=p4tFtmPGqUj8UCMxn7r4VoO0UBXlSs8HC9PPR6bqUyg,5610
|
|
758
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py,sha256=93toDuZyglexh_fkhjRoSnSRoXKwYHmB-mgbX8wvYnA,4262
|
|
759
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py,sha256=S1mVj-nFKK22Fl5k1hi_TXweUWcDGZ1ba0DaHxDBdWw,8044
|
|
760
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_fp8.py,sha256=b09jYa6gRK33_nSl88Y9khXbxNnoLByP-DnIIWQuTzw,6396
|
|
761
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_int.py,sha256=RTtbNo3-YEN8AsLeoXSinr8PxJ1eKV2HGas7rVBRG1c,5153
|
|
762
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=iuFaXLeGOoPVyzGXX7ZgXCIs9BmcKXtkKOyg3Zn0NmY,4995
|
|
763
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=TUOn6G4VqLFcNOzmX-fuyj15lipAp8_ghgX-T8ygRoM,7289
|
|
764
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py,sha256=4C5gkE5jf1UGSxcFV6_3eYlmasxkXHG2VZ4bg-SKeW0,4534
|
|
765
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py,sha256=BKCklpQiH2_i2vwhhWaz1TK24B5c4-PAybtqgNTMEp8,8001
|
|
766
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
767
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/linear.py,sha256=5-7G8oPqHqKUB-rPxL6zJl4zxDBqp_42FeRJpwbczGM,9548
|
|
768
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/module.py,sha256=J1QrXE8c4orA-UC3lhz8c9Qj85JT1-JfsI3Y9Qfn7aA,6277
|
|
769
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/utils.py,sha256=zOt-O0AsZ978entPoKuAqg2gzEgMVK5FmW14GVBLfso,349
|
|
770
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
771
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/linear_qutlass_nvfp4.py,sha256=LeSahYO4dwi5fkLE-q-6-lZ4Uw7j8w4pzEae0uUpFUY,1877
|
|
772
|
+
vllm/model_executor/layers/quantization/kernels/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
773
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py,sha256=dvSBv9nYGrOiSEN3udSv2ElQYpf7vQorIjA61b32D2g,2825
|
|
774
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py,sha256=aUTIpuzLXH0BSeIiMlJvqzxJ9mFtjJQJtM4aMlbf2CM,3778
|
|
775
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py,sha256=qzAUeUHkdQaV5AgjKZjbARrkHo8j9O1lGzkWUAg6jB4,4167
|
|
776
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py,sha256=Ur0Qfg5Eh1CUnIW9g8NvHAbvST-kFNyFfFyACJvwknA,12137
|
|
777
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/conch.py,sha256=hpCmB90lYFC2P-HTX-fznDIs_MbpYxhDEAw57Ky7mdU,3266
|
|
778
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/cutlass.py,sha256=rxqQNpCBceXBmpvBkknbLgbqnqePhCmkzingRswcwts,4270
|
|
779
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/dynamic_4bit.py,sha256=HDtGt3LLwLkNFOsoYmhjnis5h7e-dGHPdCCeAY56-FE,3938
|
|
780
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py,sha256=VGmhBP9IuV5xSoUB_O_IkFMyt0KGpqiDo5XmPsPwEFY,6213
|
|
781
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py,sha256=gdBdme4JUaZ_YcrKTzJ1JfdoeX_oG9e0SSQa204AvTI,5726
|
|
782
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py,sha256=8jtWzLHC9jJjBM9kp7d-JWpHrAQqVGegrGAgiowjY3E,7456
|
|
783
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py,sha256=e6znbeey3aanpeg61C6gO5euhwDuzDy6pH-A0rOCMeY,2005
|
|
784
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py,sha256=jpd4yNfgQXIFHVy-J3Zxr3X1KIDSmW3qg8ictrm-Hhw,3615
|
|
785
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py,sha256=wpb2ssbeewS29Ayb8eBkW7ozdRTVkLfIkJYN-8kcaz4,4600
|
|
786
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/cpu.py,sha256=Kp8rLPuuFdgq3b7xs8q55kdz9DWJcggGF3gedqvIb00,8003
|
|
787
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py,sha256=HVQmITW0w08icugokpqhfe5mSyjLVN1I7NrUNMAgmGE,5422
|
|
788
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py,sha256=Xjrl8P1PiuP13Jc_7GrJKoWvYXnW3V3pGUSG1EIjwjI,1291
|
|
789
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py,sha256=6f4RJLPwQ5XgjBs47Wx3j8_qiihzJseThDYE_MtPm-w,3889
|
|
790
|
+
vllm/model_executor/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
791
|
+
vllm/model_executor/layers/quantization/quark/quark.py,sha256=G1gHgz21bmiJwA0qxjoiUtDq9LCgEjWP0PRiWzRwjiQ,19948
|
|
792
|
+
vllm/model_executor/layers/quantization/quark/quark_moe.py,sha256=m8IPH7AZZ6cHc-dvJiMNFf4H-pjN6EQGpFxdkZiAnIM,25411
|
|
793
|
+
vllm/model_executor/layers/quantization/quark/utils.py,sha256=lOvhDC7p5Oe21iNAz2gAt2g_msZE9L7UhmPx7T_NIJY,3510
|
|
794
|
+
vllm/model_executor/layers/quantization/quark/schemes/__init__.py,sha256=A699VuIbNQcvuANSmPjZSu9SmSHuqKfSQhvn9Y7GlpE,343
|
|
795
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_ocp_mx.py,sha256=23bL0DQ4g_1B_t7RYtuoEuOMewkWcZQR2kDaXCwnnfg,12559
|
|
796
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py,sha256=VMPNUJAQ6PqGlGmVD0wUx3a2NstTp2aC5Dx6w5ZTHn0,1516
|
|
797
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py,sha256=AcxbIOddblmpdnjCd_xtexp9Ea8qnAz0K4C0LpR5LYQ,6757
|
|
798
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py,sha256=147BnUsGz5tKSVecKUn9BxfA7aWc_UXGSaiIaqhGKXY,5036
|
|
799
|
+
vllm/model_executor/layers/quantization/utils/__init__.py,sha256=ifoIA36ObRUZOBfRBb2Y9xEGV5lLuc0xe_6HYLxV8Y0,232
|
|
800
|
+
vllm/model_executor/layers/quantization/utils/allspark_utils.py,sha256=-VRplxaZTs52TJRNpTtpjm0pp9f51_S1t1muD76v2bk,2285
|
|
801
|
+
vllm/model_executor/layers/quantization/utils/bitblas_utils.py,sha256=TiKCRtacJQAEroE63vfmeeaGFLEsVQnEtG5lOv16dlk,7640
|
|
802
|
+
vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py,sha256=K4Cmf9jq0BUju3hugNAIeNMnjPY6KWkclyvFg8JJY7Y,11812
|
|
803
|
+
vllm/model_executor/layers/quantization/utils/flashinfer_utils.py,sha256=J3cOIhvESLk0S6UKcaVWFCKUGbOc69WYhBbw5OAEiZs,11216
|
|
804
|
+
vllm/model_executor/layers/quantization/utils/fp8_utils.py,sha256=zhc7nfPzxm3E2nFXUCMZOZYIYd9kRVlAuzx-MnQZevo,39025
|
|
805
|
+
vllm/model_executor/layers/quantization/utils/gptq_utils.py,sha256=-0GnKH51q6vGtt42RhlbGRkvDI4Yhta4QBG1FlWWV5w,5886
|
|
806
|
+
vllm/model_executor/layers/quantization/utils/int8_utils.py,sha256=tlXWgz7xy2vJSX-z-yH8kpznoMNXYCZqqc0UcYcyczk,14753
|
|
807
|
+
vllm/model_executor/layers/quantization/utils/layer_utils.py,sha256=CvEUZEj2ZFt7oxcDaRklOJo0IFc-llCiA2bVjybRKFc,1574
|
|
808
|
+
vllm/model_executor/layers/quantization/utils/machete_utils.py,sha256=Wv5uFC2UuuoBC_X1YGFOORBf23Zl_Yp5Ck_hFQIbRUA,1699
|
|
809
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils.py,sha256=5l1qqgoLQjXY22_n9_10ch1RPXhayxGYO-_gQuryDKk,21996
|
|
810
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py,sha256=uD_VmYNvYRrxqa4WPjaLXVon2RGRPd6FfUiTIqy9m0o,15366
|
|
811
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py,sha256=C-qPx4Y-dX1M8ZxqS_Xi3bqN6FDRTUuD-axGUjdT8EE,13417
|
|
812
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test.py,sha256=D8c0-obb1g9qQVAMptBTTF_2SzHzXR5sIV9ant1_-1M,7011
|
|
813
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py,sha256=DXy1fCTnTEhQtMg7C-AKwL5oTDvwdDwM7iZjSZ1NbMU,17248
|
|
814
|
+
vllm/model_executor/layers/quantization/utils/mxfp4_utils.py,sha256=WGwZxcLFKgiUhyta91fbqECeTue6fbS535AveM8bdIU,6142
|
|
815
|
+
vllm/model_executor/layers/quantization/utils/mxfp6_utils.py,sha256=3ccQ0AmjiDMVtIyZ-G5WZ778QDKbpbRqjv8vfNE9u5I,4533
|
|
816
|
+
vllm/model_executor/layers/quantization/utils/mxfp8_utils.py,sha256=KyD72E8jsbF-bHSHdYFkY6Aseqsa9aiTmlQfIjcnHnw,754
|
|
817
|
+
vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py,sha256=rFpYWNmA1DD4I536b0U0FgjB4zBVDSpN6cpeldjssvw,4633
|
|
818
|
+
vllm/model_executor/layers/quantization/utils/nvfp4_moe_support.py,sha256=j7GSrXDgbAoThCeAE4CAnKZknFO1oObZXp4Q6KCfm2o,2093
|
|
819
|
+
vllm/model_executor/layers/quantization/utils/ocp_mx_utils.py,sha256=WGqf-4DcMRs65l6wZsZNixc9KzRJSRl3fRpk_XIA4v0,1770
|
|
820
|
+
vllm/model_executor/layers/quantization/utils/petit_utils.py,sha256=8oiFeO9uCAaHeV0QrKPs-GbmJok66L9jylexITD7Xpk,3967
|
|
821
|
+
vllm/model_executor/layers/quantization/utils/quant_utils.py,sha256=AdmOm_XyLwyr8I1WTbF3UbNH74ONgKi3P9IBJrH9lc4,21860
|
|
822
|
+
vllm/model_executor/layers/quantization/utils/w8a8_utils.py,sha256=aY42AALhUYziOh-7bpAqXCKFaPpUx6T-ylXDZhlrh0k,17175
|
|
823
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=10240,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=yi7jAKzpH-lsDg941APV4FXoYgssj7qBFhvbWl0iWXs,3270
|
|
824
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Szg1W2xH7h5U-UOH8vHbDV_xs1xO3AM_wITHbJtITgU,3264
|
|
825
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Ta8XgWb_aVhJwqJ59i1zzY45NhCGazJ75whDUmOfyVw,3259
|
|
826
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=t8TaODfMF2Nq0qg6KOc8NSTs7m90Jcu6Ih3BXUvFb04,3799
|
|
827
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=CNI-I9ncqHJ7ukpzgyxdJtz0bd29vsgC38tvMM6TV1U,3803
|
|
828
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=CNI-I9ncqHJ7ukpzgyxdJtz0bd29vsgC38tvMM6TV1U,3803
|
|
829
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=-j7Xyk4xFaiAD90FeH4AqRSnS82f4owKRGMHbObrrHQ,3250
|
|
830
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=sW_T-BdLbjJoFqlr-B5f9emF8E0IdKfy_1wUSIEi55g,3253
|
|
831
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=tkLjwLC_aVXhzuvo-2QHkojXZauPJsf3jNHFn1S7uRA,3244
|
|
832
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=akDNAjUZ3EXBznF9w6qUcpXxaLWq7oXnX5jy-R9cleI,3246
|
|
833
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=JAycl7EaUZtmCoXMjq4JwKXCeXxZ6S4Ts_DricRUw_o,549
|
|
834
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=q5KZyi9T-l07P3r1u9i6-Dpw89Upjw1gpTp3f1CluEo,3799
|
|
835
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RTnTPFQNg5JULbPLWJDTRNRZHI7FsrTxqSDkZfSbmzw,3806
|
|
836
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RTnTPFQNg5JULbPLWJDTRNRZHI7FsrTxqSDkZfSbmzw,3806
|
|
837
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=DLCfW5tQ9k74AGZ2yER1etP-HgUGglPp_woJiaPuxgQ,3249
|
|
838
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=8v9mdWPs1eXczo3iwFrNnRo2LF9wPU4Scm-r9bL7Fz8,3251
|
|
839
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Qoj9rLLRDbKM4IKBCXvN8RcxzSmNPd0TQUiM7CXDqHI,3241
|
|
840
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=7OFCbBqqEA7vQ1oiygfW-7Tqqx8OJATaLujtcQIgyTU,3247
|
|
841
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4D3Ku4y7BCVEJzueKvQC_KvOR026w3ONWsxfsA_YrEc,3249
|
|
842
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=iJZ_tAzoYGUmg9ltil4e8vzKlKi980yTmswEMWqV1Jw,546
|
|
843
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fDomA7uBQKX8kbO_4MFcoBwHhIR_7sOkngQPv6cQq4Y,548
|
|
844
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ucrZBIN_ivmmfMAvkT40xQpH87LdQK38lZbeLWMyV4M,3806
|
|
845
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zDnVqBqgT-nLkz_Cou-KTPsNIVh-YbTBno9L2MgdRTM,3803
|
|
846
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zDnVqBqgT-nLkz_Cou-KTPsNIVh-YbTBno9L2MgdRTM,3803
|
|
847
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=zd5cMYrxQ6PD0jKpd3YF6ThT9RGdqgEQnCW6F4W-r4E,3249
|
|
848
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=CjO6dh_qt1iTu5kYRs98tTLL-W6FOzLO4AESMUFHz5s,3254
|
|
849
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=7v4tp0RaT4vxF4urSBrkK5FR_5ikeFQ1htF3DwDl1lk,3249
|
|
850
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=M5F5wzSmFokEm0X8__ogLvdE1QVC6EW8atqq-kp3rVA,3253
|
|
851
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0J2MFgaLkv-mfVE5x363lgVKYU6miLG_xRO3tJUga_M,3249
|
|
852
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=983yfFeeo-BClL_H1g-owXwbA6t0l-kREiy7kLURUMw,550
|
|
853
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RzrnY_xKo39wZ4nO8zUorLp1ivTFabB8ZQOFRx5JcMc,3251
|
|
854
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=f7upf6kaHS5_3EqQYDxtSsbgb4D1iTvjCiC4auzbx3Q,3254
|
|
855
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=C2eM8RudmP-qXEf_Apg-qcB5n2Ugxf8-7uG8hQDSt1g,3801
|
|
856
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=llI6PWlSDgQf-ouTDXkFYOoSz9u3bzklwBtZYY_fWVM,3807
|
|
857
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=llI6PWlSDgQf-ouTDXkFYOoSz9u3bzklwBtZYY_fWVM,3807
|
|
858
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=q9HUcoL0cdZCOWZ8MKbcpR8NSy5iNEBq6NPTaHLgRB0,3242
|
|
859
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=uJu6Gv4e80vxVrDyBo8_y47tOV03RmWVsMIWQ-bbW6Q,3251
|
|
860
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4ubbhwSFX_XbefRLEkLoWxJkcetFWPzsszPu0X3_Wrw,3242
|
|
861
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=euiKvhb3DXkvPPQJLqNE_xN2evsTOoZnVIiquyN2Cm4,3246
|
|
862
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FhyniGTx5QeCuVrBSVTQys6q05Pr5lPEcPykpAX7Iyo,3247
|
|
863
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=pLQvMaVvlet_JenEz25mxxplAaHNisl6SFTSZ7lYP2w,548
|
|
864
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=irQUBLd3KHNd8JNX8eFe2fBB3ZZ3zMl3aAF22uxJ65Q,3266
|
|
865
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=gklD55iBvg488-PecvtcEypwCDZ2lCi8c5o9bqgEEeI,3266
|
|
866
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=uAa-ZQmASwlqZbr1l1CM6FyJI9irNdLBzc1U5Hdyw1E,3802
|
|
867
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RnN7lfu15CE-4ywMjAbEz8wWV743AP-1Fq5U_j8EQeI,3812
|
|
868
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RnN7lfu15CE-4ywMjAbEz8wWV743AP-1Fq5U_j8EQeI,3812
|
|
869
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=cE3BscS_zEtF_m_jr51IPfpaZZgIEojmhTHsrb9jABM,3260
|
|
870
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=SScyo-oYCBxJR9C7ZIKu_pJJNiXdpT13kYe26rddvPQ,3261
|
|
871
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0v17v78pETXv6S2ZoibekxOVhiTmCm807DYG4DONUck,3259
|
|
872
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AOuovUsPAHqZlbr4G3_CnCNE__fgxCz6RuOhOxCwWv4,3258
|
|
873
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ulvOEAFO8c-UOa34FEZrjOkCR6ovhJlfFFDhmaKIBiU,3245
|
|
874
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=BiZowqExbvXftuE37SYcheOdtYX7Z5BEXyykJ6GbYSk,3254
|
|
875
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=W-xd0c2ziC5YbC96TXlc0xkj2cmbfcdXclW453PsLpI,3258
|
|
876
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=7ok0uooTihvRSckZMNd6jInRvht_xkC5posHO66ejqc,552
|
|
877
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=h_Z6wBKdSGBEo5BfQKaxuFlxztrnbbZR0pkcYKv92sk,551
|
|
878
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=k63VgniyN3Rl_-h1hYmT_q9QZtSFqQmXBqhEXJQkxqE,3800
|
|
879
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=icswqRYUsUdoQMrv4YIqO46GG9BzepmBJmnTre9-VjU,3800
|
|
880
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=icswqRYUsUdoQMrv4YIqO46GG9BzepmBJmnTre9-VjU,3800
|
|
881
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=sL0E4zZzb01g6GHaTCXltg20uSbthXHSJFQ0SaxZ7PU,3245
|
|
882
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=MZcJz7BjwVOHHHxvYqGrWw77WnxslYhwW80bZw-jSKQ,3249
|
|
883
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=GsLoYkaZ2p4Qu0Coj-X90s7JWyfZBOloIHPlyNKSIes,3246
|
|
884
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4--7YWnJYUK4XmQ2zZ4M1ZYdKvUkET0VkNgIBn6xaOA,3247
|
|
885
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=NjEA2QjOVXyOaVSMPch5qa1Dq3igbW7MmE986-7taW0,547
|
|
886
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=21Buh2aiGTHjpW45Rm-TwZD8MSaAy8NMUrK5l_hGT5k,3803
|
|
887
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=P8p-dZZt_D61G6k3PgUetF01xzTRmCDJAnqCIsSDW8I,3805
|
|
888
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=P8p-dZZt_D61G6k3PgUetF01xzTRmCDJAnqCIsSDW8I,3805
|
|
889
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=8zuJhFdd6aXREpiqPFhIKEFWA5lgLVGrG0-a9UXcBqk,3262
|
|
890
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=_42bDZX4VODErI6OL-NrWja36iNHC4DzgF1l5Mk67-c,3248
|
|
891
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Zn1TvhAoPOv0zQBYHOZhwdDw3oqyxm0zIa7IJkTCHpo,3247
|
|
892
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=H9wONEU0XXSxOJfkx5UkS8Ss3A2QCp9G0XNoJEqE9nQ,548
|
|
893
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=2T2TYZhXgC97slH92HQ8GvZS3KuUt1ZiC3RtudPVEPA,3802
|
|
894
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=b6_bhUuQrI9HYvvwmAvUYh4v1GZ8w0sjApOmwuj_t8Y,3806
|
|
895
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=b6_bhUuQrI9HYvvwmAvUYh4v1GZ8w0sjApOmwuj_t8Y,3806
|
|
896
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=yqjO7zML7EseBJw6Bn5MTyHeAitkPsl1dndXeL6Rn6A,3257
|
|
897
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-nQIhKAOVCQrxLV6HDlcD0V8HMWvqrv-vyiORVU7qls,3244
|
|
898
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=KKmCvNh5T_qfD8v7JijMqXxQ5L6-gRX7oc6c5re6EF0,3248
|
|
899
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=M3nwpZd2-0w263ywZt9gaw53z7MN673T5tl4tc43Ntk,3249
|
|
900
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=H9wONEU0XXSxOJfkx5UkS8Ss3A2QCp9G0XNoJEqE9nQ,548
|
|
901
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=KmEgJ7zP2Sr_7GsAfL-12_g2S2a2wVpnxgCiF5dFiLI,3802
|
|
902
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=J4SXwpsioBRdTXOaj2OjrdNrEuW1NF43cLds65UWzCY,3808
|
|
903
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=J4SXwpsioBRdTXOaj2OjrdNrEuW1NF43cLds65UWzCY,3808
|
|
904
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=UjBOmVqYynBH3dJVuMJXjKnuZ6LssohzzEBpLBG4_G4,3256
|
|
905
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=8BJsjc2UUYdotrIqwyzisjrq0wcyW4jnTo_M8J3qYwA,3263
|
|
906
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=vLoV3JMtvHOKpR5D1BeCQPMuYlWUAlrXu54gByNkwKY,3266
|
|
907
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=BmXTZvWk7kphfBmGmuSIuolAK-3qCGdmcPhD4FcKd3g,3265
|
|
908
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=N0kCPHvybNK-HvMO2EqNDLkj7m7WrHTl-3AD32LBD4k,3248
|
|
909
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=mjh-AgJN_IoWAc1uwhUiB1lE3ufAPDf-KPP6vUTrDKw,3251
|
|
910
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=h0qz-pNlC9ZGNbyeFsESFdowFPfTTK3rh8SK4NH2Css,3259
|
|
911
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=mcF12eQTtGxocrVIA3I98NHd1NLd0-8EyfXtqDgv0PM,549
|
|
912
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AThoa7FUcGdNXYB_v9iMpBh2X8C0iLfc7y-C0xy2cRY,548
|
|
913
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=MJgIvZHf01ju8IWEVO6vyMedy5OTZxDpzv6A7_8W-Tg,3813
|
|
914
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AT2yrMoTvmoizi4sxwLtiULZ57P1CBhKGg9-6Gxnuc4,3819
|
|
915
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AT2yrMoTvmoizi4sxwLtiULZ57P1CBhKGg9-6Gxnuc4,3819
|
|
916
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=T60CKtM9YhIEZs8F9Lljrdqqc4ReloR7Xl9IYsfex-E,3261
|
|
917
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kk8WqNCGmjh8-tOMHBP8sv_5fW81Xkdzdf8-2WDm0RQ,3263
|
|
918
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=cPtr1UJq_B-dTqgMrVm8ptiYXA6qOy_F8rs2f7ljuEI,3811
|
|
919
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=cobt_ZhR3dt2CySr12bGPVwn1oS98YvGLdIh9H8BDQ0,3801
|
|
920
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=cobt_ZhR3dt2CySr12bGPVwn1oS98YvGLdIh9H8BDQ0,3801
|
|
921
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=6Z7kIa14RjVq3ek_C15q5mUu1IrY2r0OP8S-_pm-MYU,3252
|
|
922
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=r63SZkUJJV87B00hAX074_uaC7wwQXdurlJsB1jUA0I,3254
|
|
923
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=hL3doX7zzxld3UcS8p9ACSadDaE6t3xXlYwM7X3GOeI,3252
|
|
924
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xBhxdCFf3waTUsLxJxA54R90zODbC_DKI3XXBVKjKRw,3252
|
|
925
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=2ks7TQUULAD-Zn5i69YHo_2hpmsmxlocdYmJccSh2No,552
|
|
926
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zm2eqlVlPWlP-5o944QL40OCzMpUHGkPJwduy8HOV8A,3259
|
|
927
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Yfg4GDiXIYLyzL-334YirvDbcChz-Ep_atCghEZSntU,3257
|
|
928
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=eiI8X2fFNknJmiT0uHbzSaEKQwwZk5bxn676gNvcyg0,3802
|
|
929
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fQQDJMlLdYsY5Cosg5HkRzvrJ4asjQmc0WGgoD4bC20,3810
|
|
930
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fQQDJMlLdYsY5Cosg5HkRzvrJ4asjQmc0WGgoD4bC20,3810
|
|
931
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=O_SV2vo_oaABfT6Mxqcmo12pnhKtfX4TnXfe02OcHJk,3254
|
|
932
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=g12Xkurat7oUS7LdS9pHLKFlur4_FaMGiGBvdq-iBCs,3242
|
|
933
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=EWLxbWncwGJyL-dV6EO-s8kk25wfYrESa0STjCnzD64,3244
|
|
934
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=tFdrY5nADmXUlShdN8w8Jzkxuj_RPLXCRceX9FhQ35E,3251
|
|
935
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=M-ewEHbgHLBLYLi1Hgz5Pp4kypnUiCRo0ut2scNnvDw,550
|
|
936
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=zTzLbdff09HwMuWlWpoAIgQZ6NEjsFXSF0Y5z4Be7Ig,3802
|
|
937
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=dcPHbYEbz8T9SM5-a5sP_K_npDkhH7u0KM9aiLn9esE,3806
|
|
938
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=dcPHbYEbz8T9SM5-a5sP_K_npDkhH7u0KM9aiLn9esE,3806
|
|
939
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=TO2qRGmp37v53Zqu8Joeq_BSbtwM_mpVoozGyoNg0-o,3254
|
|
940
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=QqijmgLqIoBUxRPnuUQGsoQASRFRMsCVQKTjEjGecVo,3247
|
|
941
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=0xquf00fgfrDODpaxyre0VDcjqfzqExj939rzeJ8pMo,3244
|
|
942
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ipg8iK8w2ySRe1Z08YJUWAHX43rvkrXpR6svxRhSnFE,548
|
|
943
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=5120,K=25600,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RfKJ57-Tvq7WogfSRBPys53fLXfIr74m1YklXtzFgA8,3252
|
|
944
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=5120,K=8192,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=isRjD-twCTzTRlXloDHwMvjUZzTOhZL8-qnL4oqN-I0,3258
|
|
945
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=51200,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=pIFPPhTKBT7leK-TSMCmy1LWZiDc6_5r4zoP0i7bX98,3266
|
|
946
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-wuzdNXf3K0jfFQGB8nFSyoSZ4BfAvIkY10k6FdjnLY,3800
|
|
947
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-o9QqqQQ-9kRVCuDOUGBuKXHRTd0asGTzrDcHGGYJLQ,3799
|
|
948
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-o9QqqQQ-9kRVCuDOUGBuKXHRTd0asGTzrDcHGGYJLQ,3799
|
|
949
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=DbemSQdo2h5vGjSNB6Fovnn-aAGfjti04Bp-5KxLALk,3246
|
|
950
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=6glWpljtfiuspJv_Esg_LWCDDQ57d2HETsOIv0zr2Ec,3249
|
|
951
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qG6v3n3qF6LE2DdGT-mDIXecZ1a7vg7p3QqXYCMX85k,3254
|
|
952
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=l-9r2k1gcKB8UXlBXVuzkoa1JDLgJVTBQ_OaQK80z-k,3252
|
|
953
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4--7YWnJYUK4XmQ2zZ4M1ZYdKvUkET0VkNgIBn6xaOA,3247
|
|
954
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=ZfPPlx0qcuR4WjaFAE-W1QZgSPAMf3NyGcpvQIvyFMs,3245
|
|
955
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=9w-sicV97vSQxkRcEKnFKFjkzBOx-VOHlrh6b1hhQ1g,3254
|
|
956
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=QgSlDAhlB2W4bzTd2O98UL-C_IKfJm_cVmQz8FqsLF0,361
|
|
957
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=i3wy_CBO7BQQVhKReRC2F0PaRIQDdN9F5lJ7kD0xe1I,548
|
|
958
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=QpkqpJnyjuHH8Zo4U4QZgehUF2F2uQDZFb8fdhixXWI,3794
|
|
959
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=wv5GjGAA-NyJ41SYdYG3tPAgwf6JK7Zf6SaWALQ5c3Y,3806
|
|
960
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=wv5GjGAA-NyJ41SYdYG3tPAgwf6JK7Zf6SaWALQ5c3Y,3806
|
|
961
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=RRMNeM_qiHvlUTOAeqwgs7ukSoAZSlK8XN4z8hgWl0k,3258
|
|
962
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=brB0-FFr-Sv2bdrz4DQJ_NaFhETctf1g4Yzwj_Fcczc,3251
|
|
963
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bPQWtvaJrzOOIgI-R-MIxs_f4yC_FobkDydu3OkOFtg,3252
|
|
964
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RYLh-Uim9U2_djLkFwwpV0rNQHik0tZHzecuj1_hPLw,3248
|
|
965
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ZRgiuHZ2SFC6u-WV5DGwau4k1RiPLI67eENO0e-5Ylg,3253
|
|
966
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4EzbnLWHVwrjyKYPMcDxbxM2o-krjlT0YXvM8oPH5Cg,549
|
|
967
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OFgOtRkUHwyOT7Hk_BQft_WzuZOwbhMSLP65Fbr4goA,3799
|
|
968
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AOu05da2LZbCzD9SKsrgnzH-ih3CdXsRIdJc_4J1lps,3807
|
|
969
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=AOu05da2LZbCzD9SKsrgnzH-ih3CdXsRIdJc_4J1lps,3807
|
|
970
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=qzmFm2pqxphir1LBrycDZp5JA4It8OdQeQ5iTrTwLNE,3253
|
|
971
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=2UyOMRMdbvHt6WlZdOKALm3Or0eMCx7vvwgLiCYyoOs,3259
|
|
972
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-hP_P8NM0K04mGzTmpGBNibQ5xxh5gPz5WtoMXhoz1E,3253
|
|
973
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=vEU4_YOMnLdYFf1BkBEdFbGRMG8KLhsO_t0gv7vaO4Y,3244
|
|
974
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FB5Le4obvPoCgFSnC_3-Uh59n-Mt4Rol8saXVcK3RPw,3252
|
|
975
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=k1rzpgm9m19AHf_HPQcNCuSBtAwFgMePUYB1jZeFyYY,549
|
|
976
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=9IbzTwLRgTCfFLSvjEWKiajCjG81R-wTljIV2zUYUA8,3809
|
|
977
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=B4uEwuftvaj9gHGdoDBnVhxbNRmzUtzu4LH0u-O7voA,3804
|
|
978
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=B4uEwuftvaj9gHGdoDBnVhxbNRmzUtzu4LH0u-O7voA,3804
|
|
979
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=ZTPWtJA3JBL2jhy7C60RdsntKCN8oQ-DDIL17ok7OB4,3257
|
|
980
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=mokCWoXdKi8p4mLYqgljjwDRJWK5I2oF6_MJuObi5sU,3254
|
|
981
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kLviGvVngpgOuelfKtvv9Is7MWQ89rGxlomMRP6t0Ic,3250
|
|
982
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=bIVRtaaHThozH54VIte0Nk0sOGV67K4s2YZUE6QWx2s,3252
|
|
983
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_YXzQ6N3QpF3Ou1Fy-51YyL-J3i5gOBVCgSM42vOT9I,549
|
|
984
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=csaz7AaVDTvCuzaptN-e8K1PNuIwZm9OwnPSJydHI90,3803
|
|
985
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=scfO3_ncCtyrqcYSnIoAZTMfvBzjB4o_0_bdiiVSNh4,3803
|
|
986
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=scfO3_ncCtyrqcYSnIoAZTMfvBzjB4o_0_bdiiVSNh4,3803
|
|
987
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=CE1wRLyFONo4_icKO8fcTTX-5giKNJ9_1F-2mr-lGQU,3257
|
|
988
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=JdUaLiMmf8oEbwuhPHMIncvWzXS2SxOEgfM80ZjM7l0,3259
|
|
989
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=vlys0Zi_CaaU41OHGbWSBtbVglFi98bgqEySBMc9Sdg,3258
|
|
990
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-sqiMkGGMzhrs1WdhEfwiNZd2r-NmhEsfvJxczLZJ-g,3258
|
|
991
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=GY9VBPi21K6vJlF1NOEzCyqMS7LX3xq5dRxrK0jvIHk,3244
|
|
992
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=8LWF55ZPjrOY_sEdRGqf1eLcTNySgUiiWNWsN4EGxLY,3247
|
|
993
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xEN9qWPikXf4njuYyKQJVW0SM5cDReje-euoWbr64WE,3258
|
|
994
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_Cc0EqUzl6d93OxWJRWYbYpEaTIp0glJhdfV-GSAi5M,552
|
|
995
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=ZSHvdnC2vOXI2HPW1iNI9HdihoLcNYlRLMF85pqjWZE,551
|
|
996
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=SkyMLsoxGoHdO4kgTerihone7eEi0nmHlrvZUI1I_V4,3804
|
|
997
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=6Jo2hw2gQpyiNoCRZpGItu4MBkYytzdW-VggWUC4fPE,3804
|
|
998
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=6Jo2hw2gQpyiNoCRZpGItu4MBkYytzdW-VggWUC4fPE,3804
|
|
999
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=xbDfUYLphVtZWJojZWODlxGMCoiIgxn4LsnD9ge3r9A,3257
|
|
1000
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8,block_shape=[128,128].json",sha256=hqh8TQw3t5hPM9u7rmHPuaMjwgxmQ-Zt35fSTgOS0HQ,3261
|
|
1001
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Ggy4hejkcWjiw5Bi-wGzSP5JLVuvOjip_rbjXFBJZbs,3257
|
|
1002
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=RzkrUzR_nzxnD4L2jF0_8aDX-nidn6AjhVXlJK50VyY,3259
|
|
1003
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=qKG9hmaxN_7tCB_06L1dh0csxs3TGeya9B-X6W-tNhg,3245
|
|
1004
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=jb7vGi1RJefImkT3BZU_9iOkiCulcd5oDjxpVSt7big,3246
|
|
1005
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=at0_Rcc0-lSzI9MFj-TjnjyDt0HckCZYAZ19q-7p5zI,3257
|
|
1006
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_Cc0EqUzl6d93OxWJRWYbYpEaTIp0glJhdfV-GSAi5M,552
|
|
1007
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=TWpzs48j0QwApAsBWt3iIlu6cqR46Meslyp96MOANcc,551
|
|
1008
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=i5b52A1Oe8kCdPrPLBGud7OMHm8779JD0rBocYO_lo4,3797
|
|
1009
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=U20Q4JwG63kU-6cc241VHGdpettCWbBXRJ9EZ-fbkqA,3803
|
|
1010
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=U20Q4JwG63kU-6cc241VHGdpettCWbBXRJ9EZ-fbkqA,3803
|
|
1011
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4uWiQMh3cZY_EtLA0a3PU8Z1VCunF2PpolTPYeP9Rjo,3256
|
|
1012
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OgXOVvRKqsgzlJwjHNxNCsJ_o3POBFigwCqafbh_aKc,3258
|
|
1013
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=toHzCprq0KetQI0-9IrLYCIm1bQ0nSeP1gXArU0GogI,3245
|
|
1014
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=_0V6CEfYgBsaUnF5DwNWWseo8N1Ph_R0la_XN8HzcuM,3259
|
|
1015
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=pGZZj_gZms1T9Zgjs4tbIm90LhbEy1UUkkgrto9jPts,551
|
|
1016
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=fqnjZCn0gbY7fO9JwZOHMYJJHe8gceWhWCZOFPRUlYM,3802
|
|
1017
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OTZt3ell0OZ7Cg5L17K2NPU4UwayAkTihV5HjUmUiAw,3810
|
|
1018
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=OTZt3ell0OZ7Cg5L17K2NPU4UwayAkTihV5HjUmUiAw,3810
|
|
1019
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=LdtOyXsA9r18GiFkmDOkiRinsDSZBZ8NYapL59EZ4iM,3264
|
|
1020
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=07GarBHmiiYkyqn-qxEtrAcgCETuUbqm6HqlbH9yJi8,3252
|
|
1021
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=xMNxtLL_8tyg4TWSt_llz_IJ2qlxc2NEwhUzhV1VsG8,3252
|
|
1022
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=kEuvCsW3YNByF-DALYqPZpW3TL8ZbtQ5gUNq7-8YvZ4,3252
|
|
1023
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=4uNqB71a6ctZ-c4tF3r66vOsHFrqcR28g_UWy0N8iBo,550
|
|
1024
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=QkrfZ69jxW_mweigtHL5R0Sv_WcSBp7wjFX75G9kbHw,3805
|
|
1025
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xMGmoN2ZTjKQBZS-k75mFTPpAEbPR3kyMwqZVtgbEiM,3802
|
|
1026
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=xMGmoN2ZTjKQBZS-k75mFTPpAEbPR3kyMwqZVtgbEiM,3802
|
|
1027
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=PD4AJYCkHfy2ivv9baMouFXzBTy0eKMumbAfxfm91HI,3256
|
|
1028
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json",sha256=iu8M35YR-RDpKWbjXSRzk02sW9nr_dtbhalfLSNtxNs,3251
|
|
1029
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=FFBjSWlpKXMxfAUUYUqXbOK_Hd7qBeBsfbcaa9uB4qY,3249
|
|
1030
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=41m0bvskFUzVtlr_yppBr4PZ0cVkqHvy9Hrc5pUCUyY,552
|
|
1031
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=2VxMGfWtxTzXcF0bP3d5s7rc1cKb5TNBAn-WiCKAngw,3804
|
|
1032
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=VtQGO3fEiyhbKG4sl07cuVc6id2EtKeV05ozLmN_ENQ,3807
|
|
1033
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=VtQGO3fEiyhbKG4sl07cuVc6id2EtKeV05ozLmN_ENQ,3807
|
|
1034
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=W3cYFteFIZLu5c1K41cOh4_-WZzFU6-jGnZocDzmKaA,3796
|
|
1035
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HIoWSUgAOcNaK2kj2YwDjDa23PzQVTT2C2ePW985Ovw,3805
|
|
1036
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325_OAM,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=HIoWSUgAOcNaK2kj2YwDjDa23PzQVTT2C2ePW985Ovw,3805
|
|
1037
|
+
vllm/model_executor/layers/quantization/utils/configs/README.md,sha256=kfjjurECwd-xH4EDjuueS0Xezi86c_pYu2yELgiw8Ew,102
|
|
1038
|
+
vllm/model_executor/layers/rotary_embedding/__init__.py,sha256=ihg2q_ow0pPZ6CfRgKkZNLvsZLc6Fe4mWNDhljUBD0Q,10441
|
|
1039
|
+
vllm/model_executor/layers/rotary_embedding/base.py,sha256=TorlijaQEd5Q0ejItp_ixKkEfpUbWCPYpU5jt3Mvq6o,8480
|
|
1040
|
+
vllm/model_executor/layers/rotary_embedding/common.py,sha256=U_g7r0iUH6BaHTgBKDA5jC8BVVKU0S_JpFKz6LQEy4w,5367
|
|
1041
|
+
vllm/model_executor/layers/rotary_embedding/deepseek_scaling_rope.py,sha256=gz1nzkviimur19z78ehADynbP261_3ltjoFE7mHJ04o,5551
|
|
1042
|
+
vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py,sha256=BJc52pbq6NlkweRK7DEsyrJxIPhWzRKLfBIXXCQA4r0,8368
|
|
1043
|
+
vllm/model_executor/layers/rotary_embedding/dynamic_ntk_alpha_rope.py,sha256=gkD_OmIqduxIUvBgqEqFu22dVDm4zzOmtJ5SgRQJOAc,1289
|
|
1044
|
+
vllm/model_executor/layers/rotary_embedding/dynamic_ntk_scaling_rope.py,sha256=6lZQAj1v-nvRbZkLIR9_4a9nzAczr09YByOF7IXDr_U,2681
|
|
1045
|
+
vllm/model_executor/layers/rotary_embedding/ernie45_vl_rope.py,sha256=-kC66gUp0ONA7QbSBZtCvzImb3yBovIyPk8hcfCLKck,3029
|
|
1046
|
+
vllm/model_executor/layers/rotary_embedding/linear_scaling_rope.py,sha256=5a1OVeRvwUeU35x7xjUbhpc_UNtWd2MRWlZ1QftnxkI,4643
|
|
1047
|
+
vllm/model_executor/layers/rotary_embedding/llama3_rope.py,sha256=EMeHz5tB4hKDXr6ce4GFfFpt8x03HKYlmedwXUgDcHw,1785
|
|
1048
|
+
vllm/model_executor/layers/rotary_embedding/llama4_vision_rope.py,sha256=_f4tKV35lmZ4a3HvmTMzbqVNEGk6qwq4qoIugKubzhk,3197
|
|
1049
|
+
vllm/model_executor/layers/rotary_embedding/mrope.py,sha256=XEzGoRwsyDoHgpWNxCezfqMdcpJEQ1XlY2PUv2hKkDw,14180
|
|
1050
|
+
vllm/model_executor/layers/rotary_embedding/ntk_scaling_rope.py,sha256=KzRfhq8fROqVm5Eu6ETmQZyvc8LZjIKzde0ZGcr8Pkc,1462
|
|
1051
|
+
vllm/model_executor/layers/rotary_embedding/phi3_long_rope_scaled_rope.py,sha256=AT89hmBGCmGUtX1hoy4agKZfYdHd98eJnE1fGlzkQVA,5699
|
|
1052
|
+
vllm/model_executor/layers/rotary_embedding/xdrope.py,sha256=sZQ-_2BJ5KjgISB-OfI8tO-kctrSxkRXYkIr1yzd-2c,3317
|
|
1053
|
+
vllm/model_executor/layers/rotary_embedding/yarn_scaling_rope.py,sha256=rZENzx8gm_Ysbp_OzOn0qQB9v-D1faYWz5ZILHJBbrs,2863
|
|
1054
|
+
vllm/model_executor/model_loader/__init__.py,sha256=LHfIEpPjCh0nFjOPe4GS8kswwCr9bsvss8bumDhMHys,4901
|
|
1055
|
+
vllm/model_executor/model_loader/base_loader.py,sha256=BnF4wUJhm-eWW7tzYMO0UbE-Q9ORX90S2lVww7MNjcg,2075
|
|
1056
|
+
vllm/model_executor/model_loader/bitsandbytes_loader.py,sha256=O3PbLUnXn90YEzHKPMhs7tRFfkzM_xGS38ePV8gq3K0,34791
|
|
1057
|
+
vllm/model_executor/model_loader/default_loader.py,sha256=z4Z8WU7dAEYX6ixS84v-yIFEbnf8QxqbX9g8ZZT0xMc,12370
|
|
1058
|
+
vllm/model_executor/model_loader/dummy_loader.py,sha256=QStJ9SXJTYqzTWI6ytieoh0KNsQWlfL_sFz7bcHqtEY,1115
|
|
1059
|
+
vllm/model_executor/model_loader/gguf_loader.py,sha256=nxbEfSCYIXd_m9exjDTSh_yRzCxKuE2h0L9usI740CY,14910
|
|
1060
|
+
vllm/model_executor/model_loader/online_quantization.py,sha256=I92q7uvu1vyWcYUnFkQwRzghsb52R0IC8Qi-GShx9lQ,11543
|
|
1061
|
+
vllm/model_executor/model_loader/runai_streamer_loader.py,sha256=7YpbtdAaeMdq0wpI6GvkrvcUgt48EkxRRhgAYAqfdio,4394
|
|
1062
|
+
vllm/model_executor/model_loader/sharded_state_loader.py,sha256=ZiL0HOxm10eW2w6BDu8VGLOp5Vp4M3nL6vQWJspo0-k,8238
|
|
1063
|
+
vllm/model_executor/model_loader/tensorizer.py,sha256=dhi_PV99hi-gyEqEWtwVmH8EY5XbluVRLgcxRMrENOE,29807
|
|
1064
|
+
vllm/model_executor/model_loader/tensorizer_loader.py,sha256=brQv1ywScnNSpYMAt9l0zbLz1hUbEbStsEGhVcwpuJw,5826
|
|
1065
|
+
vllm/model_executor/model_loader/tpu.py,sha256=Yk2kqIhQxistx25MQriqsuUu8-PyFdu_lPpZCiOzOkU,4798
|
|
1066
|
+
vllm/model_executor/model_loader/utils.py,sha256=EHqw61I6yTRsf0vt3FzDYM3mg64k2FC5D782AE3KBWE,11395
|
|
1067
|
+
vllm/model_executor/model_loader/weight_utils.py,sha256=ZSvE_s1-uz45EMGRmBiV4PIKit--5fFQlJsLyrF-IL4,42666
|
|
1068
|
+
vllm/model_executor/models/__init__.py,sha256=JC8KFZavvBlB4woyRgOBd_vcuoiA31nmBOR5dGcJSjo,997
|
|
1069
|
+
vllm/model_executor/models/adapters.py,sha256=Hxn0atnBM0CXWlIVxkGfCAchrWdYr7hcXKkTxSB-BrY,19353
|
|
1070
|
+
vllm/model_executor/models/afmoe.py,sha256=boh7wMGgADGrAUw7fnoD2FETdb-OOXZTP42u9Xmf2TE,26196
|
|
1071
|
+
vllm/model_executor/models/aimv2.py,sha256=78Agfjp4a5Hu_uWSOKdfTVkPyx-0Q9KD5ObyNeahlKI,8300
|
|
1072
|
+
vllm/model_executor/models/apertus.py,sha256=ZGAZr8XUgqhzB9Vx49By4w3m2_mwLUUw5DWgKmmSQVs,21029
|
|
1073
|
+
vllm/model_executor/models/arcee.py,sha256=-UFp6gIs8sqbk26I2gVKv0gq78Qb5h3CoKDQac6XXc4,16084
|
|
1074
|
+
vllm/model_executor/models/arctic.py,sha256=szBc8b-bWdTfPtJVeQ2vVEO_Pz30jj0R8kFC3tusXxM,23805
|
|
1075
|
+
vllm/model_executor/models/aria.py,sha256=93GaVD47WLug13-5fNJYoYLzq_KK9U6Pcf6c41W4jXs,23523
|
|
1076
|
+
vllm/model_executor/models/aya_vision.py,sha256=eTnjMz3pZUYvH54zG04-eMpQhruR2ZnuawyIauv1l8w,16568
|
|
1077
|
+
vllm/model_executor/models/baichuan.py,sha256=-xsiS4QgP_uJvoMtE_YxkstJoafn5KlRQX9cmpHNi_k,17853
|
|
1078
|
+
vllm/model_executor/models/bailing_moe.py,sha256=ysB4AUeTjsf5TG8o5GEBOMNBLBLE7OnRFQyuUPQIuBs,23158
|
|
1079
|
+
vllm/model_executor/models/bamba.py,sha256=5EeeYUJrAc6jJgGnZqy5781zIiHx0IM3uURbNSOJP_s,17839
|
|
1080
|
+
vllm/model_executor/models/bee.py,sha256=BXEICXixtwrG50Roqwk1cujdmQ4pljJGfxQgUt7ZqtA,5450
|
|
1081
|
+
vllm/model_executor/models/bert.py,sha256=ZxM79Yrcx5sVi7vAo_4B4bTGc5mm7VTwltBwnPwPRiY,31354
|
|
1082
|
+
vllm/model_executor/models/bert_with_rope.py,sha256=CbohS09BZMV8Y7WHVbMGvsz5-KT6M_Zo0LwAplbuGs4,25587
|
|
1083
|
+
vllm/model_executor/models/blip.py,sha256=9H3pzmrtN_9OV3BLO1Dsk54bptwoJKnU0qVxLNIH-V0,11910
|
|
1084
|
+
vllm/model_executor/models/blip2.py,sha256=xfWKeShF_mWqqTaT3hmbS1G62No4jUJrmn0S3o6XNzI,23302
|
|
1085
|
+
vllm/model_executor/models/bloom.py,sha256=9Y1UAwmAaiZt4fI4kfOfF68liZxOy4RiFLwl0eyiXxI,13967
|
|
1086
|
+
vllm/model_executor/models/chameleon.py,sha256=CavUi3IKSann0m16NvVmmjJW5UlUbgc2L8AMcKcqMPU,40509
|
|
1087
|
+
vllm/model_executor/models/chatglm.py,sha256=xljxbjDR4U3Hof0pyVXtUJZezbvMpRdgAZfhb658f4k,17562
|
|
1088
|
+
vllm/model_executor/models/clip.py,sha256=Cymzkka7EmRVKcTDQFT4yZ0n5Bquiyk_8jWX_H6Riyc,33366
|
|
1089
|
+
vllm/model_executor/models/cohere2_vision.py,sha256=5SxbFLm4Kda3rdaeXVjDcySAp59aEImLgrP71pGQTO0,17069
|
|
1090
|
+
vllm/model_executor/models/commandr.py,sha256=Y4rZP60QRQYRoW_Bm91CQYmVa71TsPYvVCljLRVqPjo,17434
|
|
1091
|
+
vllm/model_executor/models/config.py,sha256=kIwJZshtWIYyVGS7bcu4giAqRubTlomjYPyTj6urzx4,21431
|
|
1092
|
+
vllm/model_executor/models/dbrx.py,sha256=wWJ2aboeUh5YnTDJzqaoayockcUn_RrtyuNBptSqFNo,17467
|
|
1093
|
+
vllm/model_executor/models/deepencoder.py,sha256=xX4tgjD7akJrsdHKsWOJacDfZ8iWsBlD4mmCepqO_Sg,23774
|
|
1094
|
+
vllm/model_executor/models/deepseek_eagle.py,sha256=GJdG-Ii1vSTtsJy-jB3zzMHB2iWHsgjCOrak3hqecnk,9329
|
|
1095
|
+
vllm/model_executor/models/deepseek_mtp.py,sha256=DCOhilLz0IzEcLtYobgoBSwTK6rtfn7gB8rkSxsIrq4,18016
|
|
1096
|
+
vllm/model_executor/models/deepseek_ocr.py,sha256=kT_yC0IE-VaLyBoDoplSxqOVCjFfFK1T6VGN2hRbeUA,20395
|
|
1097
|
+
vllm/model_executor/models/deepseek_v2.py,sha256=IwOTNRfO8CHxeT5eB7rIAjqgyJo-lAzCEwdYFwZBf6w,65596
|
|
1098
|
+
vllm/model_executor/models/deepseek_vl2.py,sha256=JRbjqvd2SY7LFXGvrvEK8sDR90DKybAAqLDLddpQmF8,22925
|
|
1099
|
+
vllm/model_executor/models/dots1.py,sha256=a0aiL8OoDRctm9vlFKYOWfbA30h75jr8ryYgyRombSM,20855
|
|
1100
|
+
vllm/model_executor/models/dots_ocr.py,sha256=g0Xey_lisMAq39z_4kHrrycTlZDo-WO9Gqmgt6KAFeI,30121
|
|
1101
|
+
vllm/model_executor/models/ernie45.py,sha256=gxkle1tmFbYsDkQx8AjoYZ-2_e93ALUtHMMdVnPA_fY,2244
|
|
1102
|
+
vllm/model_executor/models/ernie45_moe.py,sha256=V7qqhVhCUfF71a79mWamwX42dEwm3kVVW5q9Y79a2Ik,28130
|
|
1103
|
+
vllm/model_executor/models/ernie45_vl.py,sha256=QppequTQ9ElmIN5NhM7-Fduw7xltYal9S_hv-uQTIF0,60973
|
|
1104
|
+
vllm/model_executor/models/ernie45_vl_moe.py,sha256=Thp8AmJbpuMzZcxzmQ4-Sa8uFsfvPOXw_qp83FCV1iw,30396
|
|
1105
|
+
vllm/model_executor/models/ernie_mtp.py,sha256=2Lh7jpKYkisUeuVVc4spslBo_eYCYWEhHlO32pHddZA,10568
|
|
1106
|
+
vllm/model_executor/models/exaone.py,sha256=9bo_xMS78CFUgR-q1Q1cK979MhO5m13xUELzeWKABww,18847
|
|
1107
|
+
vllm/model_executor/models/exaone4.py,sha256=2KRfKlo0dsdOKrn0jZx71Uw6I2G8jnSp0x4xiFChVbM,18688
|
|
1108
|
+
vllm/model_executor/models/fairseq2_llama.py,sha256=dIadCgG1u8yASjN4qmOTvkli4xxu-Ygl3t0iL2Czsik,6375
|
|
1109
|
+
vllm/model_executor/models/falcon.py,sha256=l5YUKHQeOmQn2kqz4jEBsuuduoLm6h8Z4XgUXsGvwrI,20509
|
|
1110
|
+
vllm/model_executor/models/falcon_h1.py,sha256=jR_sXTTSqs6dcd6_qrvB_qxRjV5qIbDb0Vgh7eNEkKY,24320
|
|
1111
|
+
vllm/model_executor/models/flex_olmo.py,sha256=eWFSijc0m35t7xMZKdsb0cXZv1OdI3vbAw8nAujahMI,5624
|
|
1112
|
+
vllm/model_executor/models/fuyu.py,sha256=9Dfy6RAbw7BgHkx91KV89SUFnUTdTS-DpRFXf7t65nQ,12952
|
|
1113
|
+
vllm/model_executor/models/gemma.py,sha256=SayMwJLUBh4BGWUQpdu0-VyyQPlVVAxfdsT7CvSEiD8,15572
|
|
1114
|
+
vllm/model_executor/models/gemma2.py,sha256=3kyhHaTuRQsKZCmmi01Rc4JkH26IiBaSm-wC5Z2cU1I,16400
|
|
1115
|
+
vllm/model_executor/models/gemma3.py,sha256=UBpTHaXx2VgPb6TvIos7djo7mnjO3WyRRpZ9lSkDpAU,22287
|
|
1116
|
+
vllm/model_executor/models/gemma3_mm.py,sha256=QYrPlJBIh6bIynNtdu6O9j44VSv5nH9hQ-WvHIP7LIw,21891
|
|
1117
|
+
vllm/model_executor/models/gemma3n.py,sha256=HYJQTFgqRMqXUQYjJa1JFD5ZNz-tIjd64hfcxtWbCIk,44207
|
|
1118
|
+
vllm/model_executor/models/gemma3n_mm.py,sha256=B2apzMJ_dWnEwMlw12y942qkHeyipjdNu6zEixvpfBY,29732
|
|
1119
|
+
vllm/model_executor/models/glm.py,sha256=FhBl3j5GNEFJFqiPe76ccfMH2BW8z7FzaQ6Rs-0rB9c,1059
|
|
1120
|
+
vllm/model_executor/models/glm4.py,sha256=fgm4vbqBTUhgrULMPm1Dl8wyF1GUzVhoV_Obt9X5udo,10722
|
|
1121
|
+
vllm/model_executor/models/glm4_1v.py,sha256=rh_EDGz2MYJljKSbJOhsrB1-abdfFA4MPnrLlRD8Z1s,67823
|
|
1122
|
+
vllm/model_executor/models/glm4_moe.py,sha256=0Jqc924jGTB-LPqIuth8LY5HW9DGfA6gDoE5O4baXFQ,28166
|
|
1123
|
+
vllm/model_executor/models/glm4_moe_mtp.py,sha256=ILXawxkleeK_jaTrKBIhSGnMSPnCX6h-YbNGWqyBdXU,14106
|
|
1124
|
+
vllm/model_executor/models/glm4v.py,sha256=wVFMea6b_GZxUojVPqpauL8tnk81kIE6EftqSPbKDIw,25780
|
|
1125
|
+
vllm/model_executor/models/gpt2.py,sha256=ZyPRJybDLhq5LoZbMIH3S6V_kmFXTyvflebsXD19BGk,14316
|
|
1126
|
+
vllm/model_executor/models/gpt_bigcode.py,sha256=nN3bU32akyp24tLWpc5Puzfka96VlfUdcLObR6YC7EA,12135
|
|
1127
|
+
vllm/model_executor/models/gpt_j.py,sha256=6ten1P7alJPbYLJ9t4R4sv7Z-2HAP36_McdlNW3Q97M,12674
|
|
1128
|
+
vllm/model_executor/models/gpt_neox.py,sha256=Nh0a6ytB2E39etLR25XVGX2tYh2G6IBq5KaqZBWcfBM,12810
|
|
1129
|
+
vllm/model_executor/models/gpt_oss.py,sha256=RXUux8PjalTkYIcNU5-NUcoYOodGiYhr7-Q4SIqJbDM,28892
|
|
1130
|
+
vllm/model_executor/models/granite.py,sha256=gIDjMCWHAuCc_vOEpEO4s9YSqpjrUNkTTwKPUdPVlws,17407
|
|
1131
|
+
vllm/model_executor/models/granite_speech.py,sha256=iORwgyGlDxPF3gu9X-LfCP4n-jv3_Opwn177YJz6PaU,34657
|
|
1132
|
+
vllm/model_executor/models/granitemoe.py,sha256=7LWb_2LAGaralusAas0RjxlbiZyEvMPpUKEezPu9D1Y,21138
|
|
1133
|
+
vllm/model_executor/models/granitemoehybrid.py,sha256=SXvjeCb7s1zcK2T61XEzxSd78jhUB_ejwb2fFr4XZJA,25791
|
|
1134
|
+
vllm/model_executor/models/granitemoeshared.py,sha256=mOXadUhv4xcOoQhff4qB_cwgT5yIolVss8Do0Ds1wY0,12029
|
|
1135
|
+
vllm/model_executor/models/gritlm.py,sha256=iIEUG6CjqX43f4vwmyDIvaWlrzQc5rAIrMGkea3kUGw,8266
|
|
1136
|
+
vllm/model_executor/models/grok1.py,sha256=Rle122M9C663y1Pn24LD7WOK5GXAgXsQJsFlm4K0id0,20662
|
|
1137
|
+
vllm/model_executor/models/h2ovl.py,sha256=esbz1E_zaZK6p0YBB5QqcbZaU3eq-3kXZEqLSYsydJs,17830
|
|
1138
|
+
vllm/model_executor/models/hunyuan_v1.py,sha256=hIKCy0R8ihK58a4yadosODCWpEIr1mDy3B4sjUb1al8,39494
|
|
1139
|
+
vllm/model_executor/models/hunyuan_vision.py,sha256=u1dwOGEZClPthUHU4WGuizL_1V_Xq7rCk9YfC-g9thQ,34869
|
|
1140
|
+
vllm/model_executor/models/hyperclovax_vision.py,sha256=4gkUTlc-VUM_eIODLuW7VGvSOu3wER6HwztLNATezjU,40447
|
|
1141
|
+
vllm/model_executor/models/idefics2_vision_model.py,sha256=LUVcrbE87rLldyd0fB3Px96AI0CM_6Qyiq5MNjKgHIg,15539
|
|
1142
|
+
vllm/model_executor/models/idefics3.py,sha256=SC4wtk9q3t1qlJDWz2-yh30ZrJ9gK66HDrVHMPucEeU,24684
|
|
1143
|
+
vllm/model_executor/models/interfaces.py,sha256=exXDqHVeRbA2B-Gwi_Tnzg2JPtyLaMs_erncvVkU7Qk,35173
|
|
1144
|
+
vllm/model_executor/models/interfaces_base.py,sha256=0H5cyoVPXp3vZzUblm6ifQNYTT59uoYd43EIEMb6_zw,7068
|
|
1145
|
+
vllm/model_executor/models/intern_vit.py,sha256=GekvyrlCVDNxHqGhiUza214e-KBymnR1z7cAlTWgMAQ,15099
|
|
1146
|
+
vllm/model_executor/models/internlm2.py,sha256=bKTkIGOCUnndt9FC7rvtOpXp85BwBPUeAUv6XWJhd9s,16155
|
|
1147
|
+
vllm/model_executor/models/internlm2_ve.py,sha256=hDhlTCpPsJ50_mnB7XqLnMT6waw_E99gSM7n2tr93mw,5350
|
|
1148
|
+
vllm/model_executor/models/interns1.py,sha256=Udo0PZf1Wq6jZYzYefkXION0e6dcofdi7eINBJ5gMfE,30635
|
|
1149
|
+
vllm/model_executor/models/interns1_vit.py,sha256=Zz53jQ6eqM46oIWEavlA5uLz_pKLldax_RcQCl62VQo,14909
|
|
1150
|
+
vllm/model_executor/models/internvl.py,sha256=Fo20gSzVGO_TIctUKE9smVmp3o5mpGAvO3223VSL8lY,49898
|
|
1151
|
+
vllm/model_executor/models/jais.py,sha256=iDGCyrKYbJMfa1TYl0oyJz5S3ZRJqmR7YXJ92wEJnUc,14198
|
|
1152
|
+
vllm/model_executor/models/jamba.py,sha256=q2EQ4q6o3W6hwW9NrKanXyweLGxvGj7gbOiO_xvhv-Q,21600
|
|
1153
|
+
vllm/model_executor/models/jina_vl.py,sha256=oGnJwu1_XSi6AnB4rA3C_sec8YAxZjAh3kz2jsO5JyE,5262
|
|
1154
|
+
vllm/model_executor/models/keye.py,sha256=bsvSztW0ih-xz88C1KC3duDtKA6bgKLxTbr1R9I1CYw,61659
|
|
1155
|
+
vllm/model_executor/models/keye_vl1_5.py,sha256=KJEMR34TguKFFGuC1tnTf-T4akAiKDP6XGsMblIZWO4,24902
|
|
1156
|
+
vllm/model_executor/models/kimi_linear.py,sha256=CoLW8JssLyB86xB8RPCj34tuV3YrFNtTdOCARW-fpt4,23810
|
|
1157
|
+
vllm/model_executor/models/kimi_vl.py,sha256=qt3VKGQKcFL-44Vew2_Mx5ByexP0WLiSGmOCqPoNghA,22169
|
|
1158
|
+
vllm/model_executor/models/lfm2.py,sha256=50BNxxnnC4-nCj-YTaWudTJQnvPxIro3tVvAjr-73w8,18260
|
|
1159
|
+
vllm/model_executor/models/lfm2_moe.py,sha256=UDfeVmw3CK7ORqI_X5FK8dhF_2V27G4b8FqWfqqaa68,26808
|
|
1160
|
+
vllm/model_executor/models/lightonocr.py,sha256=8WKI50EwvphQp4rn2NKKWYW94NhgdVlflL1Wl6aK4rs,7062
|
|
1161
|
+
vllm/model_executor/models/llama.py,sha256=IEDpS71GbSc95J6X9yjYQceEV5W8Tfdzu_gtGtwR8hU,26417
|
|
1162
|
+
vllm/model_executor/models/llama4.py,sha256=fqRTIkgdPcz7tSAqkSsqPo3BljQRinPViyf1Xk9f5nU,35172
|
|
1163
|
+
vllm/model_executor/models/llama4_eagle.py,sha256=IAOsVe4NKEm4RxWr8q9FYMVd2xd9ZMRhP0zIvr4mGEA,8746
|
|
1164
|
+
vllm/model_executor/models/llama_eagle.py,sha256=y8zOZL1d5-E-OAqNpX98DydzaXa8_2P42Yu3QvrSZLw,7937
|
|
1165
|
+
vllm/model_executor/models/llama_eagle3.py,sha256=2bGYKrlU4mHFDu8KXIbeKhCsLVeCbXOgAA1qcYAvvM8,13899
|
|
1166
|
+
vllm/model_executor/models/llava.py,sha256=s71aQeButQnRZwRE6s2w7a1O84lje-v5MBUm7ncjI_Q,29040
|
|
1167
|
+
vllm/model_executor/models/llava_next.py,sha256=WdPffJIMbUPBNejOXwX9owu6Tr7KKWs_HA6ceS24QCc,22040
|
|
1168
|
+
vllm/model_executor/models/llava_next_video.py,sha256=_uMNJ5LfCwqOwZhXbVU5UWHsfpLJmsnyqGJOAR-UlTo,16144
|
|
1169
|
+
vllm/model_executor/models/llava_onevision.py,sha256=4a0c7Pc7S-eWv-u5FeSM6LRrXtwScXh31HGundfJffA,32817
|
|
1170
|
+
vllm/model_executor/models/longcat_flash.py,sha256=8UXvzfcUY22FgZu5sbiJzDTkrS8LA5jwQP1czMBFflQ,27764
|
|
1171
|
+
vllm/model_executor/models/longcat_flash_mtp.py,sha256=tN7zbhFVQj7XvokoXYjXezg6LQhmVILKigcm2FknOLY,15551
|
|
1172
|
+
vllm/model_executor/models/mamba.py,sha256=su7lsV3dqkgTgsc4TTBca8QVuhg2hl4e5OXvqFMNW7w,9787
|
|
1173
|
+
vllm/model_executor/models/mamba2.py,sha256=_3ljnMFLPp_-8VM1h34_0uUFD96bDQZaQVjaM5oUZSE,10000
|
|
1174
|
+
vllm/model_executor/models/medusa.py,sha256=ljZQYNwpS3jkemq1r2ghTc2Z1LW8ncpdfh6qzY20TKg,6738
|
|
1175
|
+
vllm/model_executor/models/midashenglm.py,sha256=RGp4Eqto1KZQ53SvphSpQhYHZwEToNMwOnrKz1OmTHI,27817
|
|
1176
|
+
vllm/model_executor/models/mimo.py,sha256=4b4Ezgz1uHqVOyhjxm8_FOd8IthV0WXoGSqTs_zq2Qs,7332
|
|
1177
|
+
vllm/model_executor/models/mimo_mtp.py,sha256=LZGDXqszX94QsLS32RRGuC8d-cFlM2O02mjwgC9oRc4,11061
|
|
1178
|
+
vllm/model_executor/models/minicpm.py,sha256=jEFV1CA5r3hTVHy7k5-kRNw-2TtIoyWUUIEsVNx3k-Y,23759
|
|
1179
|
+
vllm/model_executor/models/minicpm3.py,sha256=0fjdXUNgHd9tyzSe8McRORymkAwPEYwZELdAtyDYSog,8615
|
|
1180
|
+
vllm/model_executor/models/minicpm_eagle.py,sha256=JLUHeZKf75a748ygxV1LEqvWBDKhxPvyxf5wBUUIe_Q,14390
|
|
1181
|
+
vllm/model_executor/models/minicpmo.py,sha256=mD4uCUlkpmdeW7kPJoU-BITGtex3uuvvH2RZN22Iy9g,26859
|
|
1182
|
+
vllm/model_executor/models/minicpmv.py,sha256=b36yYU5K6U8QF5q6j1Yn1TQDhNE5Jpe2f5nOXIgAIOo,59107
|
|
1183
|
+
vllm/model_executor/models/minimax_m2.py,sha256=vZFHk8ZQkeTNWItOJTGx52n3WI0cyxh7F5z4pTn-Qw8,20485
|
|
1184
|
+
vllm/model_executor/models/minimax_text_01.py,sha256=iwcEy4YC_fqk8zewozlypbck5TAQuXp2rbgrrHOqvF4,38042
|
|
1185
|
+
vllm/model_executor/models/minimax_vl_01.py,sha256=O_vkO-GV_dZ0xt4kr-XuU8IXCqOdq7rtdtR9VL7lGY8,14493
|
|
1186
|
+
vllm/model_executor/models/mistral3.py,sha256=YKm4atzzYypLrmPQVGvTBYpyERkxME6utu7bwLgkXl0,22082
|
|
1187
|
+
vllm/model_executor/models/mistral_large_3.py,sha256=iS7LwF8g1RaDqEC6XPNY65zDVoN8atVksWnAvF7WXDM,3671
|
|
1188
|
+
vllm/model_executor/models/mistral_large_3_eagle.py,sha256=NIZBYwTwWOu89K_0fug--X171K1FVWjEWRjGXt7y4Yo,5906
|
|
1189
|
+
vllm/model_executor/models/mixtral.py,sha256=kZIh-_iF08_zYeA55KDxrM776VXXUKOY5pnbmk7_pxY,22495
|
|
1190
|
+
vllm/model_executor/models/mllama4.py,sha256=S2paGP0zvIQO4XNLyhZtjOYAHpiz57LpdXyHw6uwxJ4,41955
|
|
1191
|
+
vllm/model_executor/models/mlp_speculator.py,sha256=HDvlP-QB88Z6facl3fDKmIck7dtSWjpifteV4i1E23c,8457
|
|
1192
|
+
vllm/model_executor/models/modernbert.py,sha256=W_CFDhHzKVZXOtp_IPahlfHU9xJqzAsL_GLiQ_Pb2Uo,16260
|
|
1193
|
+
vllm/model_executor/models/module_mapping.py,sha256=YdEB0K1EaW-BbLfkr-IvlO-E9pv7G5qrYUn_vQwnLis,1688
|
|
1194
|
+
vllm/model_executor/models/molmo.py,sha256=Ee1F0meGvvNRcfwz1SCqdsGhPi-hHcwM68LWpe3JaPo,51929
|
|
1195
|
+
vllm/model_executor/models/moonvit.py,sha256=1vxAYPsjBS7fw3d-ur-OIYXDAbZmItAthyiunF5IRuc,25390
|
|
1196
|
+
vllm/model_executor/models/mpt.py,sha256=HLqYAFNUcxNdSRShcP-mgY41dLkb6xDMazq_pvp8JU8,12119
|
|
1197
|
+
vllm/model_executor/models/nano_nemotron_vl.py,sha256=587GcbUZcLXEDgMxpW9hPiY3UOlM8l2Gec91S2U9CCo,64592
|
|
1198
|
+
vllm/model_executor/models/nemotron.py,sha256=PT8ZBik7ZsBj79iYWCbbgwq4BIGsTAImi4pvCQILDEc,18095
|
|
1199
|
+
vllm/model_executor/models/nemotron_h.py,sha256=xwKtt-L0-gGvNlSDIk7Un4FrisvQUL0y6HbbZJfDU5U,30444
|
|
1200
|
+
vllm/model_executor/models/nemotron_nas.py,sha256=teReeeWrCRkCF1e0tAA1Y5RM1AzljOYgIFFc2PEPSes,16893
|
|
1201
|
+
vllm/model_executor/models/nemotron_vl.py,sha256=FlVhqFpGZxHAnc1m2Ohwfj-B8OV3UJpba2Njj7NHYmI,22506
|
|
1202
|
+
vllm/model_executor/models/nvlm_d.py,sha256=MqXkN1AQ-SJv9UCAbpdTvOe4-R1yVcG3wEOv94z45nY,7636
|
|
1203
|
+
vllm/model_executor/models/olmo.py,sha256=Ln0MBCfKX1JuumcRUMbmtdTVlYZ2kXVQPjv4AoWW8ig,14365
|
|
1204
|
+
vllm/model_executor/models/olmo2.py,sha256=T0VaM3KJFTVXG0BVaNWorQN9J0lj5phQCKHV6FjGA2Q,16626
|
|
1205
|
+
vllm/model_executor/models/olmoe.py,sha256=zGYp8hrW8QI_fCAT88IWVL_HAh04IlZvhal7R73sPxc,18407
|
|
1206
|
+
vllm/model_executor/models/opencua.py,sha256=cSL_hDAeS-gUdSOdGjTy77UgqJpC1XpIUpOIElb092c,8809
|
|
1207
|
+
vllm/model_executor/models/openpangu.py,sha256=Eagzz6BV2BuBhlrTf7mxgCGcFTtZ3vyIAQTvlIY-Msg,39336
|
|
1208
|
+
vllm/model_executor/models/openpangu_mtp.py,sha256=1MEp3hje6mdaayhvzH7AeSVxkF29eEpch16tVM6rJow,10369
|
|
1209
|
+
vllm/model_executor/models/opt.py,sha256=xd_6gvFtiwdJe9am899LwXsalxBVx2TbYNpxiVB-lJ4,15681
|
|
1210
|
+
vllm/model_executor/models/orion.py,sha256=e8Nvk2ETJj1ZxLGFmCg_k6FB-nxP6QQYoy0dCQfpImI,13250
|
|
1211
|
+
vllm/model_executor/models/ouro.py,sha256=FwakxiWqVgOKqCA98O_tJPvzKtvNs_KCOu-jbPHys_Q,18821
|
|
1212
|
+
vllm/model_executor/models/ovis.py,sha256=4m2NXluwFSlLrJS72Un_6avItp1YYiNirf-mYVcLzgk,20342
|
|
1213
|
+
vllm/model_executor/models/ovis2_5.py,sha256=mnDNcLHbd1MoZYT2IwW99vwkZDdZJSRC-GmcJG83bzk,25087
|
|
1214
|
+
vllm/model_executor/models/paddleocr_vl.py,sha256=hGWS1PQ_A-A3TEBv1vMiTLFYq9W2_5CjdaREP3mU0BE,48940
|
|
1215
|
+
vllm/model_executor/models/paligemma.py,sha256=g3C3aG3yKSAaVAdrgw7chWdWA_Y7gqWtOqcWJGQGtCI,13595
|
|
1216
|
+
vllm/model_executor/models/persimmon.py,sha256=QczsO5yZdLsRQcKIQRawFBxB9iJhb79BJATQT_-J_iI,13756
|
|
1217
|
+
vllm/model_executor/models/phi.py,sha256=UVqni6zt0W9cm0a5SXl4J5479v31Iu1OgFvXyvnjpZg,13203
|
|
1218
|
+
vllm/model_executor/models/phi3.py,sha256=N380ApMP7_3VL-rlWeVD27SUjC-kLXbldzYNWgG8ApM,456
|
|
1219
|
+
vllm/model_executor/models/phi3v.py,sha256=OYg-00ZSvzanq1eq24Yj7vCkATEITb15HNiOVvcNnhQ,26075
|
|
1220
|
+
vllm/model_executor/models/phi4_multimodal.py,sha256=DrtKdfv1axdlEHcb5AfCryb64DO5x6lkPGTtKThx4xI,52221
|
|
1221
|
+
vllm/model_executor/models/phi4mm.py,sha256=d_yQk1aIZcHNmmCvMy63s5shz5fqOcsc-1tCectHI-A,45294
|
|
1222
|
+
vllm/model_executor/models/phi4mm_audio.py,sha256=EML6r9O_PY-LQZQwCbC45nvf0QY2j0pevPYKPuZNsE0,50483
|
|
1223
|
+
vllm/model_executor/models/phi4mm_utils.py,sha256=un2oSpNyKdnDN9wLMnBn2CzxWO1xNeRwAPyV4pI6Gj0,67179
|
|
1224
|
+
vllm/model_executor/models/phimoe.py,sha256=l1Cj2MQ44AOsHrF-6RUsXeJi3bc4r2IyAgHQZEqQp_4,23483
|
|
1225
|
+
vllm/model_executor/models/pixtral.py,sha256=RMCheZJN7WPD2GaPItSsnE84qy-fa9nyOrWzaBI-S3Q,48467
|
|
1226
|
+
vllm/model_executor/models/plamo2.py,sha256=-orwY811XvsQ3YCMHB5awtA1eVemSAllSY50Ao6UHbA,36934
|
|
1227
|
+
vllm/model_executor/models/plamo3.py,sha256=4nWWXpOe9Q5OTdvb44kvjvLnJBKyLseMBLJd_JLtv7s,15900
|
|
1228
|
+
vllm/model_executor/models/qwen.py,sha256=LY7KmPyR9CrVNEFTDfKggbk7_HkOwyaZB-prs1bk970,12917
|
|
1229
|
+
vllm/model_executor/models/qwen2.py,sha256=tlQZDYT6Zxws_M-KL3hWjq4him7eTES08FvoYfbPeHw,21196
|
|
1230
|
+
vllm/model_executor/models/qwen2_5_omni_thinker.py,sha256=luZ65KhsydPMqWvkytRYttEvhKbsk-CkYAdSXqIYRKo,47045
|
|
1231
|
+
vllm/model_executor/models/qwen2_5_vl.py,sha256=EYDKo30z-CDK-w_EVjjqiRs9Gn_weLnS6Rp0q31UtTw,57184
|
|
1232
|
+
vllm/model_executor/models/qwen2_audio.py,sha256=otDiUl9mrisB1AFvbi_fOpiYEHp0vPW7Qz2Ql0roaP8,16912
|
|
1233
|
+
vllm/model_executor/models/qwen2_moe.py,sha256=Ty9AyIj4PG7jmK76s3N2d1KzrDDIXQaW1CPH9WND8R8,22733
|
|
1234
|
+
vllm/model_executor/models/qwen2_rm.py,sha256=K3lpU9hDakDURPIClLkzT81ZwOAUAsBPtvRpevJbsB0,4131
|
|
1235
|
+
vllm/model_executor/models/qwen2_vl.py,sha256=QoACK-MJs-kKlyyaOZqAyIHPV2cI0qE3_YrJ02WHlzs,55157
|
|
1236
|
+
vllm/model_executor/models/qwen3.py,sha256=zbjGSEjkdVo88omKAf5ZZiTKJr4Z_z5kuSZfG1oZ2X8,12394
|
|
1237
|
+
vllm/model_executor/models/qwen3_moe.py,sha256=ZURMT0kL_WDT-ql3UUDUyMbgmuCXDHxvJjx2nZgGdf8,29027
|
|
1238
|
+
vllm/model_executor/models/qwen3_next.py,sha256=sOENVHHa5QqGRNeFsqwI5KhwkLhkDqbtgWTyztQ_KI4,50926
|
|
1239
|
+
vllm/model_executor/models/qwen3_next_mtp.py,sha256=beovwMRrBMh5AIqjwydzTVLbR9XJ2TsIylrfA8HxL-M,10691
|
|
1240
|
+
vllm/model_executor/models/qwen3_omni_moe_thinker.py,sha256=ejgoc57f7DtfhXLkkPq8saEVkqLXFMzTLck3Px4xe3w,69516
|
|
1241
|
+
vllm/model_executor/models/qwen3_vl.py,sha256=2fsJYZOhjj6AfK6GvcetQRkgKQUuKFsQpqFffTPjx2M,64356
|
|
1242
|
+
vllm/model_executor/models/qwen3_vl_moe.py,sha256=ug70tYiQ3mYQ6k_qXomFPCVSYrC8-LrxhvgSajxE3uM,19402
|
|
1243
|
+
vllm/model_executor/models/qwen_vl.py,sha256=AN_A9G_i7vh5NsSSG4LjUNIvLVEsvMNzMaY_5xgyyjc,25246
|
|
1244
|
+
vllm/model_executor/models/radio.py,sha256=wZd79PQaK33rgnguwVacOop8-ab7zn4vSbeKFcAacAM,18240
|
|
1245
|
+
vllm/model_executor/models/registry.py,sha256=7D1mUzUlbmW-enalw3IJvruz6h47qhW8slcrSIljoc4,46487
|
|
1246
|
+
vllm/model_executor/models/roberta.py,sha256=k9DeYeEXRgMRUjWM5YpZvXlRRGFFiWi64UhEIgzUiOk,9630
|
|
1247
|
+
vllm/model_executor/models/rvl.py,sha256=-XiyV1RZrjlWPfJhnL0K8ulP02dHOLbt0DiLuWdvhLk,3567
|
|
1248
|
+
vllm/model_executor/models/seed_oss.py,sha256=sLh2-qIKSt_VovsjaspHfJ1q69RewuwFRovO-BIP_dM,17916
|
|
1249
|
+
vllm/model_executor/models/siglip.py,sha256=YA13K-KfHOGBdPMY16IQCM9MMnEcNtFn4YXLvEntxeg,42927
|
|
1250
|
+
vllm/model_executor/models/siglip2navit.py,sha256=ehHfo-2qhmN1x5tfi_thHPvvHDie4M9RrCqnEzcvJDc,27107
|
|
1251
|
+
vllm/model_executor/models/skyworkr1v.py,sha256=oX6dtUPwPZgSgISg0nSn6alL8_Q9Odh511cEddc4ab4,31823
|
|
1252
|
+
vllm/model_executor/models/smolvlm.py,sha256=ZsY0x3CaHHUuTBggSWCwGv-HfUAiwks8jZRNoMd7hXs,1450
|
|
1253
|
+
vllm/model_executor/models/solar.py,sha256=03h_QMmsF4WSb6tnrAmuuhsMDG-Y8ETftZOnGTpt9eI,17801
|
|
1254
|
+
vllm/model_executor/models/stablelm.py,sha256=qj0jZk_8v8J3NnP9hhPof4Yhta4obedaJjrH5Il_BAM,13797
|
|
1255
|
+
vllm/model_executor/models/starcoder2.py,sha256=gkURROdNzRjcPH7LFpUp58iIsx6FwFd5yiejLNIJ5Hk,13409
|
|
1256
|
+
vllm/model_executor/models/step3_text.py,sha256=g5ID7ZdojtaFUnVEQueRZSSYrnS27i3L1RML3iRI1NE,19902
|
|
1257
|
+
vllm/model_executor/models/step3_vl.py,sha256=e2lHASiWwmLImhHcva1zcbwZCs5F87h0LoHSYWZW2tk,40360
|
|
1258
|
+
vllm/model_executor/models/swin.py,sha256=6HMXPVyWBQm59cAC4lunRkzSFCcHk28pi_eCKQkNWpI,16978
|
|
1259
|
+
vllm/model_executor/models/tarsier.py,sha256=EylnPwlRQkKEZgC_nhqQUewRe3-WaMiCL3SJwxHihgM,22850
|
|
1260
|
+
vllm/model_executor/models/telechat2.py,sha256=wOEquSezPeLg2qqUNZ7ncsIzpfxHxRCrFoproADyARE,6245
|
|
1261
|
+
vllm/model_executor/models/teleflm.py,sha256=vlTObvAPJAJhkhy-8Snyx_7R1jGqAbYU8OYbWAPgvh4,3030
|
|
1262
|
+
vllm/model_executor/models/terratorch.py,sha256=cgMC4sd93oI-T-EHlz93_-0rXuLPkN3bBA0jYXnxRLU,11246
|
|
1263
|
+
vllm/model_executor/models/ultravox.py,sha256=Q-53JH3Z3feqoj2CiLabK5B5CW9PU6pfxZoaRDpmIXc,25732
|
|
1264
|
+
vllm/model_executor/models/utils.py,sha256=Jtw-OwjPC8aXYtpF9ICfMurukCzLqLs6tv9-GafKGXg,27418
|
|
1265
|
+
vllm/model_executor/models/vision.py,sha256=5E7o7uN5yOb8tR4kdl_v7cByz5AUMOaLu5Pc_D-bcNo,19421
|
|
1266
|
+
vllm/model_executor/models/voxtral.py,sha256=b1c2xws6S_iUR6Xr6TA77UfGuP7nhnzCgzXg1Eirzkg,30696
|
|
1267
|
+
vllm/model_executor/models/whisper.py,sha256=JZcJtZwcl8w-Ko0VcSemIj7WzRusFvXkcuphS2QCZfA,33163
|
|
1268
|
+
vllm/model_executor/models/zamba2.py,sha256=a83oBP9sa4Sz3_qxVelP-saJIU8hnbImbgMcibJFKqc,35356
|
|
1269
|
+
vllm/model_executor/models/transformers/__init__.py,sha256=KR0hAoCBU4oqFfOpZ1kT9u80zQ_s-Z6HWpTfkvra-iM,4264
|
|
1270
|
+
vllm/model_executor/models/transformers/base.py,sha256=KNxZA6pnYE4KJGk5vsH00eu_q8wsoJ3EHHs7-GBK7lM,18559
|
|
1271
|
+
vllm/model_executor/models/transformers/causal.py,sha256=WkomK1hlsPamiJU7wi-Y-kXtPKo9j8e5mEb7rUn2_hM,2609
|
|
1272
|
+
vllm/model_executor/models/transformers/legacy.py,sha256=NY96kEaStY66o4Sa3tOFCqLhhwgiIf3eO2dnViXowIQ,3229
|
|
1273
|
+
vllm/model_executor/models/transformers/moe.py,sha256=6jieJQSeR2bQtcTL9xAzzagqo3cSxJWQbBmGsVwqqiE,14217
|
|
1274
|
+
vllm/model_executor/models/transformers/multimodal.py,sha256=TiuayxGZs0CRu2ULpfV0Ug81nl9SvIvr8NLV1X1NSwk,16398
|
|
1275
|
+
vllm/model_executor/models/transformers/pooling.py,sha256=b7wvQD_BcNhKrRTfatvYapeHZq4TbP7gnaB5SiGcjbU,4606
|
|
1276
|
+
vllm/model_executor/models/transformers/utils.py,sha256=Sj2gn7zVB6EwmmjbXNxLaK-sLlec_Xgy6xz8RA7A8S0,7690
|
|
1277
|
+
vllm/model_executor/warmup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1278
|
+
vllm/model_executor/warmup/deep_gemm_warmup.py,sha256=HP_WkAMOTu9t2viVV7jtK9xA4Cb_ueNUpWZ_pRZ-QZs,10885
|
|
1279
|
+
vllm/model_executor/warmup/kernel_warmup.py,sha256=mPsA-O_KblSFAvqMfIiYfz5lO2d4k4qTnuvvs1Hf00k,3574
|
|
1280
|
+
vllm/multimodal/__init__.py,sha256=12IM-iHLb9Uko5kVWANuRPcW6-fxcPP7VjJ7yoQSjpY,1031
|
|
1281
|
+
vllm/multimodal/audio.py,sha256=3ZseJ7JU3f93ropWeQIDiEc3H60x_EtUJ9fjP-j-7D4,4164
|
|
1282
|
+
vllm/multimodal/base.py,sha256=lfe3t_e1h6x7kjZQkuwsdOWNbzb2ulAOSW7qvM_lfjo,701
|
|
1283
|
+
vllm/multimodal/cache.py,sha256=ygMqbrWjiuv5E5fdwpbVtuXYzv-KOGPWl25-rfXlFzE,25498
|
|
1284
|
+
vllm/multimodal/evs.py,sha256=fRGDSsF8VNjS6c665IH4SgKZd__RKIll-sEeDZP3Kyg,10886
|
|
1285
|
+
vllm/multimodal/hasher.py,sha256=27tiR_7YEdENFbYhjCK-wUF3ezT43AaAOBuBzRlq7Jc,3710
|
|
1286
|
+
vllm/multimodal/image.py,sha256=FglAc-z9-wLqIEVEDBjDDCkDoIOsRDvZnqXRAKV4jnE,4375
|
|
1287
|
+
vllm/multimodal/inputs.py,sha256=qT1h8tur8xNndVed_PbV4dpW6iIaFNGcP83yRIT4voI,31896
|
|
1288
|
+
vllm/multimodal/parse.py,sha256=SzDRitBZ6P9QNTOoOocy9nQ8GTw71Llf6VdkZ7_7P2M,16362
|
|
1289
|
+
vllm/multimodal/processing.py,sha256=4zswSQg7YQO4r9sRePsvqc9AJnkr-5vORIZ1eCqtQWE,73263
|
|
1290
|
+
vllm/multimodal/profiling.py,sha256=_Aj_-CR_4Apta8G14vZ8UQpHQ6SjqYFDMlAeFZfXcyw,12156
|
|
1291
|
+
vllm/multimodal/registry.py,sha256=Jas3v8YMysghFZWQyHZsEaqhNjGlyznaFGOjL_c6BsU,12172
|
|
1292
|
+
vllm/multimodal/utils.py,sha256=j4cItofNy8Nt4SJk5yzNxUuqmQdxbNCYzpcVcyaURpg,16805
|
|
1293
|
+
vllm/multimodal/video.py,sha256=RNPBFCn4bpb_n0dZbJpruU2bvUv3B_P1X7vKAJK0Yu0,11322
|
|
1294
|
+
vllm/platforms/__init__.py,sha256=9MJt87rVxIFAeoDiKAQWoMsJOhD8noEyUZ1SUakJWvo,9896
|
|
1295
|
+
vllm/platforms/cpu.py,sha256=CfdfHAIBrNLo7RascFGkOlsjG9yte710eFTTrNg5VyE,15190
|
|
1296
|
+
vllm/platforms/cuda.py,sha256=_KL0XqWZthY71RgYV2T3ECENWFJ-em6-tM4QvnkSZxA,23002
|
|
1297
|
+
vllm/platforms/interface.py,sha256=sbUkpx_leRpLXR2ZikDXpWVqBeSCzmZ9lgmfDr7ZI_4,20865
|
|
1298
|
+
vllm/platforms/rocm.py,sha256=vksXXOFtzOky0A1pF-vDXYfAEofebidQBafV5MtlnTM,18800
|
|
1299
|
+
vllm/platforms/tpu.py,sha256=R4PKfGKRYCTG6oX-F5MdC1qMvGQ5_ngcmZIMvnLzajU,9095
|
|
1300
|
+
vllm/platforms/xpu.py,sha256=1DMo5rNptFN4tW-Eq6iSwB70DfQ_b6i0xGV3cppX-_w,9259
|
|
1301
|
+
vllm/plugins/__init__.py,sha256=Nsw0J9H4aw1c1Re9Lq57fapbZooXT5itsF6kG3GJPwo,2833
|
|
1302
|
+
vllm/plugins/io_processors/__init__.py,sha256=UhJEF--e0B816MCdrtyBxon4RQgsuM6vxLTBu6V6Y4A,2517
|
|
1303
|
+
vllm/plugins/io_processors/interface.py,sha256=6ZIp0yXv07pH3gynuueyYb0QcHk9YbTKyoLqzU3If_k,2583
|
|
1304
|
+
vllm/plugins/lora_resolvers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1305
|
+
vllm/plugins/lora_resolvers/filesystem_resolver.py,sha256=Frj6--zxNA52jqW6UhIEjH5P9DoTaup3N2WeMHyF4V0,1957
|
|
1306
|
+
vllm/profiler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1307
|
+
vllm/profiler/gpu_profiler.py,sha256=_sxi5rH6LLqdfK9det26AsLyrU2ClG5tNwRWyPoytaA,7109
|
|
1308
|
+
vllm/profiler/layerwise_profile.py,sha256=p_EhWfWFVE-Nkhiz6VlwR5S5Y7OUEx12mvJp3TE7lsQ,13424
|
|
1309
|
+
vllm/profiler/utils.py,sha256=0rGR3LYSg6uZitAxN0bKgruTtVwtvytsNfbFZz4QLjk,4659
|
|
1310
|
+
vllm/ray/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1311
|
+
vllm/ray/lazy_utils.py,sha256=0QXF-uTIUdzl992ugkYgkvHbWUG-85yjuIDNSLVu2gQ,651
|
|
1312
|
+
vllm/ray/ray_env.py,sha256=hi3BEix6Bwyaaunm-2KvvhCuqV4AD3ooK6SQQDowizA,2562
|
|
1313
|
+
vllm/reasoning/__init__.py,sha256=iE1WyvEZBZhFeW8kNREYw_aiMwvs98Irr9obyTbvBXw,2346
|
|
1314
|
+
vllm/reasoning/abs_reasoning_parsers.py,sha256=jXTQ6vKiCyz7XEh_qcuMhKQtBNF6iEMuQaFud7HBvjk,9563
|
|
1315
|
+
vllm/reasoning/basic_parsers.py,sha256=ApQFNyszpSBV27mJ7aaOjn513mHTkcEMsdWL6G1CNWs,6450
|
|
1316
|
+
vllm/reasoning/deepseek_r1_reasoning_parser.py,sha256=aCkmFQVv4d-4EqYMbNtdHnozRs_5tLrOJWfXXHT6U-E,2351
|
|
1317
|
+
vllm/reasoning/deepseek_v3_reasoning_parser.py,sha256=xoymChTclMZWe1MLIysKFen4NrRwoUGmWr1Gd1MaL_0,2176
|
|
1318
|
+
vllm/reasoning/ernie45_reasoning_parser.py,sha256=FWSQqSHiUxh9VeR0jP7fMbWVjeiwnKs8iqy9Eudy-oI,6828
|
|
1319
|
+
vllm/reasoning/glm4_moe_reasoning_parser.py,sha256=9iogIA3Ss8_GgqAScUZnbpGygakEf1OBqMWJ5ERc5_s,6893
|
|
1320
|
+
vllm/reasoning/gptoss_reasoning_parser.py,sha256=e1_-mx24_2pLk0OWu9AjF3x-jzArD_G0YCvF8l5mR_4,6796
|
|
1321
|
+
vllm/reasoning/granite_reasoning_parser.py,sha256=d6BikPcKaIBd5WkZaIm2dG1H8HUrCcjPR4gEePz15js,15196
|
|
1322
|
+
vllm/reasoning/hunyuan_a13b_reasoning_parser.py,sha256=sTm9xUNnoJ73zevO_Z0hkx_O4SriOKNe6e7THs_NCYU,9571
|
|
1323
|
+
vllm/reasoning/identity_reasoning_parser.py,sha256=o1Wt5C74ROikHK-IiAoSPR7Jwq78IIH--D3VS9ZrFgA,1983
|
|
1324
|
+
vllm/reasoning/minimax_m2_reasoning_parser.py,sha256=lTqiCvzd_vPsQvTvX6NMCT0z1MSP5rTs6K9kgYlVVXg,2082
|
|
1325
|
+
vllm/reasoning/mistral_reasoning_parser.py,sha256=sZXKFKkgS72PNjIZQz6mABnQOyA2S5SL3GsSD_medrw,1993
|
|
1326
|
+
vllm/reasoning/olmo3_reasoning_parser.py,sha256=-RtXQ-UF091RzUMjMGEfCSzBLQm-2BQl_0AKPU5rPl4,10991
|
|
1327
|
+
vllm/reasoning/qwen3_reasoning_parser.py,sha256=6yJYZVXxa-QL3I2ZHqmFdhZOpmoJh4pWex-6YWegSrU,2487
|
|
1328
|
+
vllm/reasoning/seedoss_reasoning_parser.py,sha256=Oz4zSgr6seYtssSyDKsFi7J-b9kTy-IcuC01HNJkv_c,832
|
|
1329
|
+
vllm/reasoning/step3_reasoning_parser.py,sha256=gl1-8lvpbv2H4rXscf-bVRFZUgJYbX2GbmhOueuWo0U,4023
|
|
1330
|
+
vllm/third_party/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1331
|
+
vllm/third_party/pynvml.py,sha256=HRQEbE5ZB-AgMIySG4j24hjlEgSGLrNvHJUq7UawCfA,234653
|
|
1332
|
+
vllm/tokenizers/__init__.py,sha256=MWevZ-kDUWl4JdBE1jc8oaAytjkCDzAbem8PmHfg1oU,593
|
|
1333
|
+
vllm/tokenizers/detokenizer_utils.py,sha256=pn4BAMQzAWeDC-rgBUVyJjhKMFvuVbkbP8Szqr3ihkQ,7601
|
|
1334
|
+
vllm/tokenizers/hf.py,sha256=yvkBwhXBMKPurXhe2j2hhDXMSqiVxj-m_PTSYNtaQW8,4433
|
|
1335
|
+
vllm/tokenizers/mistral.py,sha256=JCwwj4jkdVf0ddAo3x5ONq2-muMFZFR7sezDeNA2H88,21905
|
|
1336
|
+
vllm/tokenizers/protocol.py,sha256=Z_2rivdKBkmiieeQqEDIwkp70pX7cEz3WjNMBJUaO9Q,2821
|
|
1337
|
+
vllm/tokenizers/registry.py,sha256=c7kaZrEnwCVrcTOK4OYT317-C7nUx1kigtjPaUBiOx8,7961
|
|
1338
|
+
vllm/transformers_utils/__init__.py,sha256=BTdT_ym1ftRVhgxBUkdJQqmO2LiKDX2MZZEEG8U_05E,932
|
|
1339
|
+
vllm/transformers_utils/config.py,sha256=jW8R06TLSxaTRzVhzh13ve8C6gUF9agn_0IWSseCH88,38842
|
|
1340
|
+
vllm/transformers_utils/config_parser_base.py,sha256=qSyL1AYBvvnQTII-lS9_N602OJ_Huf5BkUZYBhQEFtU,523
|
|
1341
|
+
vllm/transformers_utils/dynamic_module.py,sha256=K1nKutDfT9VCxbU58gw_o3H49BBM7pu-1jFh2UmIsXU,1781
|
|
1342
|
+
vllm/transformers_utils/gguf_utils.py,sha256=zCcDoPeofgzHHsvE2BfTnM-7b4SglZpG2CdSGjq1DSk,7492
|
|
1343
|
+
vllm/transformers_utils/processor.py,sha256=PUxtVteTOQITih5o5paRn58gW6KeVpg_icyhhp_dL6o,15019
|
|
1344
|
+
vllm/transformers_utils/repo_utils.py,sha256=iFkVvdV7Hjyo4isZozMjoMwxCQxbsWpFAELcZAd9XDU,8467
|
|
1345
|
+
vllm/transformers_utils/runai_utils.py,sha256=xJ0HgkaBGZrOZ5G6RaYBbBgyAI4lhgEdLEN8j0XfrqA,3337
|
|
1346
|
+
vllm/transformers_utils/s3_utils.py,sha256=S8pMrLcoUOXiexsioyzBjuYz4wst_YZC-yqTpC0QCsI,2783
|
|
1347
|
+
vllm/transformers_utils/tokenizer.py,sha256=TkrRmYY00MvKxJyKxP3Ms1ws0GgIMIJsCo27K0Mrxq4,3844
|
|
1348
|
+
vllm/transformers_utils/tokenizer_base.py,sha256=N997UqbMcc0NNBssPQLQbYKG9qAUvqit4QNAVHPIKEM,1038
|
|
1349
|
+
vllm/transformers_utils/utils.py,sha256=1CZeYL3mp0JOYWpJ1tRKxpbXSWBmUOf4q_4G_jiMtZI,5076
|
|
1350
|
+
vllm/transformers_utils/chat_templates/__init__.py,sha256=U1sUyX9swSjxaULlg0B6rSroU5H8upeyInuHsF74SEE,208
|
|
1351
|
+
vllm/transformers_utils/chat_templates/registry.py,sha256=f5ULuuY1mJUrpwFwJXY_QqDskleozjJKMomEhr-jUBc,2563
|
|
1352
|
+
vllm/transformers_utils/chat_templates/template_basic.jinja,sha256=DMH0156UMA7eoJelXKUMEDzB-SigjbyCOBxIu9OyFJE,78
|
|
1353
|
+
vllm/transformers_utils/chat_templates/template_blip2.jinja,sha256=ltMbjFdK7T4HUcN_OQaX4hj2r0PGlS1EJ9zhSlnTz1c,332
|
|
1354
|
+
vllm/transformers_utils/chat_templates/template_chatml.jinja,sha256=CKxCWf_KemM_DntV70Hf03WNkDvxznolyW-03SJJw54,370
|
|
1355
|
+
vllm/transformers_utils/chat_templates/template_deepseek_ocr.jinja,sha256=sN0qqjXqEmWsTBafWtrvXbYnSaeCOTgfDjzmwvk4Njk,499
|
|
1356
|
+
vllm/transformers_utils/chat_templates/template_deepseek_vl2.jinja,sha256=WX32uOZ7h8_xqrWvmsI5R-6Ns8ZcXVn74CKB7FJOifA,785
|
|
1357
|
+
vllm/transformers_utils/chat_templates/template_fuyu.jinja,sha256=hzdsPgeUMaZnd5L23QPiz2oC6_wMBy5WgZkXMVs3Dgo,85
|
|
1358
|
+
vllm/transformers_utils/chat_templates/template_minicpmv45.jinja,sha256=tNvJgf7S0je1GqFxPUQ-q5nSGwXoINdqW3-VOFNekh8,4231
|
|
1359
|
+
vllm/transformers_utils/configs/__init__.py,sha256=xmAc_gm8evia3XyX59CMESP6YfQo31OfrNUKNLvRqQE,3244
|
|
1360
|
+
vllm/transformers_utils/configs/afmoe.py,sha256=aQB0DRO3xFbPr3HhYN8Qu_n-D65SpjJcdcdBVRzaXts,3212
|
|
1361
|
+
vllm/transformers_utils/configs/arctic.py,sha256=jy-9t3V9xqxrPtwgTDq3HmB0W1tzo1ehxgbUbQQ_szc,9790
|
|
1362
|
+
vllm/transformers_utils/configs/chatglm.py,sha256=0Lw_vCbBpbsWOSiLQG6q9LpgeWmgbTAIJJwlHYbMWPk,2731
|
|
1363
|
+
vllm/transformers_utils/configs/deepseek_vl2.py,sha256=0X1rctqdTJmbNu1uFybVeYSpDxAr299Ly0qZjl0SQLU,3881
|
|
1364
|
+
vllm/transformers_utils/configs/dotsocr.py,sha256=_mxuA6xDpO6N2-FD4R5XVqLDP79D8i0OAZcPvqUCSdU,2445
|
|
1365
|
+
vllm/transformers_utils/configs/eagle.py,sha256=R8LT924n_tTE8LkfYcENCv_UVvLmsIWKl6th6okyOWg,3012
|
|
1366
|
+
vllm/transformers_utils/configs/falcon.py,sha256=XNrg2x08UDZngZqtv5T0CiEFZq7qhoJPWdEYnI64e_Q,2937
|
|
1367
|
+
vllm/transformers_utils/configs/flex_olmo.py,sha256=NInzKT7pO5w6CKxxaaEAXW_YnN6f1Sv3hDWQYhPL7ko,3157
|
|
1368
|
+
vllm/transformers_utils/configs/hunyuan_vl.py,sha256=ErUQbR08co_u4Mt4l1uyCI386fTVK2IjwDE7EapVmRw,14493
|
|
1369
|
+
vllm/transformers_utils/configs/jais.py,sha256=0mHMFC7GztEyIRf8IJGF6ELhzyVlCqPnJpOEFBUpIRY,10441
|
|
1370
|
+
vllm/transformers_utils/configs/kimi_linear.py,sha256=NQpLdbqUEQYGOsaUrvqMbPFgUv8C3uDBCv5X8dPZ3lE,5377
|
|
1371
|
+
vllm/transformers_utils/configs/kimi_vl.py,sha256=wGV24Na51emzxtMP6EbQ2pereXMCjkIQPo1A2pgcSZs,1362
|
|
1372
|
+
vllm/transformers_utils/configs/lfm2_moe.py,sha256=WUTK1E6qOA8ROk3kCzaP1fxJLjZchXyvd3nD3nZk4G8,7514
|
|
1373
|
+
vllm/transformers_utils/configs/medusa.py,sha256=ECZ7guyPJJob-viGpZh1LZSdi0VPQg1w84pym4C6Q3o,1930
|
|
1374
|
+
vllm/transformers_utils/configs/midashenglm.py,sha256=FG_hFNjxJaAmXV5LIePEXWcYZqs6IRlSle-9awAeU_c,3631
|
|
1375
|
+
vllm/transformers_utils/configs/mistral.py,sha256=8oH2nEQfv5oGnjN_EZu3Ax6kC6fS48j2gJKNwuCgZTs,8367
|
|
1376
|
+
vllm/transformers_utils/configs/mlp_speculator.py,sha256=aTNL7dpJxF6piYE6EysUiB11sBAOFw_xlmlDOFEoEa8,2403
|
|
1377
|
+
vllm/transformers_utils/configs/moonvit.py,sha256=wENIYbaocro7cWlpcc2yrIaWSyzkLpABVTEJ-JQ7Aak,1232
|
|
1378
|
+
vllm/transformers_utils/configs/nemotron.py,sha256=JarNWrI2AeYsXtQ8J_2HBBOdhESLF4mIeAK-5CVP_T4,9311
|
|
1379
|
+
vllm/transformers_utils/configs/nemotron_h.py,sha256=eFZ7oDbzNKQI2KmyNyu8QILtVrq8VYBegKFQEXecmDk,13099
|
|
1380
|
+
vllm/transformers_utils/configs/olmo3.py,sha256=pnjjin2JhHw7lA0JzpsVaRiF4l3-jDwj5_DrroEEVTU,3026
|
|
1381
|
+
vllm/transformers_utils/configs/ovis.py,sha256=zjfzz8-btPauEhKwQm9dRqmsZ8jakSaVCqqZ2rJZv2g,7535
|
|
1382
|
+
vllm/transformers_utils/configs/qwen3_next.py,sha256=YUPodFZU88nQUTCi25d8haSxjHsIjCvOlSDoRGjtcCY,14807
|
|
1383
|
+
vllm/transformers_utils/configs/radio.py,sha256=bde0vTUtEfMNZEAefJoyMFC7uDFR35zOPeAiwl9vP2I,3575
|
|
1384
|
+
vllm/transformers_utils/configs/step3_vl.py,sha256=4qeCToaFjy95XRlvAN1UHyYQpz89VVd33iVOEdOB8x4,5238
|
|
1385
|
+
vllm/transformers_utils/configs/ultravox.py,sha256=i6GhU7jGY8e5g89o9CB4L758FF4qERwEQ0w_teYmw2U,4848
|
|
1386
|
+
vllm/transformers_utils/configs/speculators/__init__.py,sha256=48Vcuw16i9R99vM3iDVkRkX107yJtFeTtdWgLQE-XFg,107
|
|
1387
|
+
vllm/transformers_utils/configs/speculators/algos.py,sha256=ZUKraC3NROj6rIWXDUqWJBELGFbNI3P0-4Or4W39enQ,1538
|
|
1388
|
+
vllm/transformers_utils/configs/speculators/base.py,sha256=6ltGW5jguo0u1Sznw2I1pXfIAe0ojteBKsm9DhaMOsQ,4382
|
|
1389
|
+
vllm/transformers_utils/processors/__init__.py,sha256=GAtWQ7zZvab4DdngNVZowoD_2K66OQ_JARUxu-18Y-Q,874
|
|
1390
|
+
vllm/transformers_utils/processors/deepseek_ocr.py,sha256=qhDq_pr2PZjisj5Mj0SBY6mjX0ivSSGmp3z_V0i8K3U,15088
|
|
1391
|
+
vllm/transformers_utils/processors/deepseek_vl2.py,sha256=YWmA16RtLAOE_eMHTJwHJSFoRFlBU3wD7cR3ZXP9JyQ,15121
|
|
1392
|
+
vllm/transformers_utils/processors/hunyuan_vl.py,sha256=ggX18hq8h7eR1GZokvu8GV-dYPrGZ--R-kJU--MKg3A,9485
|
|
1393
|
+
vllm/transformers_utils/processors/hunyuan_vl_image.py,sha256=KeauATCER1RdedquOh8bvXPKk9GT6eQAG8avSRqSdz8,22292
|
|
1394
|
+
vllm/transformers_utils/processors/ovis.py,sha256=wzvMI1WEBK408Yb4PxgepUwJ96-LQV2n-lxyUI9mcjM,19426
|
|
1395
|
+
vllm/transformers_utils/processors/ovis2_5.py,sha256=AGj8iHo5IrDmPlRmljIYnh9T2DED9Ior1HFSJWwXsGo,19505
|
|
1396
|
+
vllm/triton_utils/__init__.py,sha256=FY20qv1flNw_TDjM9j544voqnflClkYGSOEF5lPwv0M,567
|
|
1397
|
+
vllm/triton_utils/importing.py,sha256=CcaJ7kpP7bKP3yfuR_1w_vNRBxiZk8qNdcatjsvoAYI,3589
|
|
1398
|
+
vllm/usage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1399
|
+
vllm/usage/usage_lib.py,sha256=zNXchtEzMFhPnwC5Iu5Y0dCaYTrLzXfqme2Gig2qK94,9594
|
|
1400
|
+
vllm/utils/__init__.py,sha256=iIOUf3TBSGVGWEHoNqe_qLalOulKKBLA1NH6yZMQYnA,2270
|
|
1401
|
+
vllm/utils/argparse_utils.py,sha256=kLdxb-qB6bldsiKfAhi-v8Y0vkqvggHmblAMtxbKR0Q,19748
|
|
1402
|
+
vllm/utils/async_utils.py,sha256=nwAA8cr1EgJb7rAAwifFWXHAQbTZvhRqH9KRdKPHNdk,11193
|
|
1403
|
+
vllm/utils/cache.py,sha256=p6Cvrul9e1fOuw4h9-n74qmY_lHMQyS0BqhHXQqN-_Y,6206
|
|
1404
|
+
vllm/utils/collection_utils.py,sha256=OevIR00n3MlaZIvf4q39a0fXkqek0bR7WXi57WHxBdk,3070
|
|
1405
|
+
vllm/utils/counter.py,sha256=6Xa0WjHey2LwyPJkGfYa37mgOsQfcHJF9kRypIcaHDQ,1165
|
|
1406
|
+
vllm/utils/deep_gemm.py,sha256=EtV4DqSlYVH5cUI5U7oszjRerWCH1yrp1Bj2VgzbZkc,13638
|
|
1407
|
+
vllm/utils/flashinfer.py,sha256=zHrerg-3Z65YxKxB0urgWdauhBwEh7OCk17Z0oUATLE,17084
|
|
1408
|
+
vllm/utils/func_utils.py,sha256=pLXKoub-DlGrxZRwliCGmuMy2eiEHrglZPEQSbvPjKg,7706
|
|
1409
|
+
vllm/utils/gc_utils.py,sha256=zMuLZmEcjECblk30kHjKGwLdOHANND5vopi17x_IRjI,4970
|
|
1410
|
+
vllm/utils/hashing.py,sha256=1M7eC_F4CmAx31II5hKmdOJEwdHyVrUKd1nUNcGgjGw,2445
|
|
1411
|
+
vllm/utils/import_utils.py,sha256=T2ba3mHBFihEDRo7VlMtcOPoyyAX1-NZp_wuP_M4Eeg,13882
|
|
1412
|
+
vllm/utils/jsontree.py,sha256=lktXNEOq0w1qqAGTPgpJ5eDogjetHDC15Hq___2OLmg,3755
|
|
1413
|
+
vllm/utils/math_utils.py,sha256=MskLJpEF6qy1In1mRyRLzmuyDRBlJgtZHfyu2Okq1c4,774
|
|
1414
|
+
vllm/utils/mem_constants.py,sha256=DerNf9-iEKE2kx8c6ufmLY23mn7vV3K1vskiAw3SWJU,390
|
|
1415
|
+
vllm/utils/mem_utils.py,sha256=MDTjSENzVUjIdZjiEQXhreF6R6nUIPwHMN9jLt97juk,8850
|
|
1416
|
+
vllm/utils/nccl.py,sha256=V0yVYxhEKRi2hSWBqK_7OaFwvVR_RAJBNQ-a3wgCDXA,1915
|
|
1417
|
+
vllm/utils/network_utils.py,sha256=J3SsZGRhg_47sujXrpKD88HdirxxRrkSow9dQTZxmsI,10076
|
|
1418
|
+
vllm/utils/platform_utils.py,sha256=V5bnsv9S_IGUJtlyqhIG0Nn-BldsEwrqDAvRTgSp_QY,1873
|
|
1419
|
+
vllm/utils/profiling.py,sha256=UWku3rWFiMP4UclIokbOxF1fh5xVuwiOc4vjsq2Fdo4,1469
|
|
1420
|
+
vllm/utils/registry.py,sha256=gWRZ2XRwU-YapctL5A05O1bG2Vgm-QBcPrxjUPRugFU,1555
|
|
1421
|
+
vllm/utils/serial_utils.py,sha256=HDxai84PXIsCfL_8GD3BsUNHsFC6zFZdLoPhEtaGUms,4874
|
|
1422
|
+
vllm/utils/system_utils.py,sha256=LG-rnlYLIQp8-zZL0YaUqP0fMfYeVDF0NA-lc2Qfpik,7797
|
|
1423
|
+
vllm/utils/tensor_schema.py,sha256=Q2GzQ-CzlvQjA9qvZBcP8f3layD454s7c5nRt_FeZWU,9140
|
|
1424
|
+
vllm/utils/torch_utils.py,sha256=CJDJesZ9e91d7PQPzGZcAca20oL2Y9oZV9pz06e1cMg,21217
|
|
1425
|
+
vllm/v1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1426
|
+
vllm/v1/cudagraph_dispatcher.py,sha256=2UWfKWADMdhq90Hg2yKKUaOKV9GTzrsWot_4CU0JU6M,7774
|
|
1427
|
+
vllm/v1/kv_cache_interface.py,sha256=ZX9oDY86vgviQNVEhcnfI4XeRnSjzPN7wXpVLJIAsHQ,14494
|
|
1428
|
+
vllm/v1/outputs.py,sha256=JW1uQExAIEGxB7SKSvn7fxVbkmz3Cp2p_lH5mzCKbi8,7876
|
|
1429
|
+
vllm/v1/request.py,sha256=0gRGiGKLzGwiIEk8dw3w7iwQTIbec3nwAPOFrDBTKNI,10131
|
|
1430
|
+
vllm/v1/serial_utils.py,sha256=NUgH_AOsd8Tidf-DSJf7FiDpVp6GN_V3MnThwXhyNfI,20445
|
|
1431
|
+
vllm/v1/utils.py,sha256=bN8fkzu6oInYP_vOjUMxjmKiuSZLLXVfml6Cl3XdIBk,13923
|
|
1432
|
+
vllm/v1/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1433
|
+
vllm/v1/attention/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1434
|
+
vllm/v1/attention/backends/cpu_attn.py,sha256=cnobLCXhbLhW6PXVf_M8TpaJ5g4Qiz-U0TCNhIQXxa4,18013
|
|
1435
|
+
vllm/v1/attention/backends/flash_attn.py,sha256=nV_rhpzntUeSMRvFv_rs8uzdmRJ4iGBKDlQ-LQPl3K8,41453
|
|
1436
|
+
vllm/v1/attention/backends/flashinfer.py,sha256=Sk2Js74OAOMc5tACcP2_MGCX16ffRZXSOzK2yYBjQpU,63198
|
|
1437
|
+
vllm/v1/attention/backends/flex_attention.py,sha256=Wb2OrGMXClNgEcXmMmv9lIDefv9cXXWpE45hYdwmv8Q,36093
|
|
1438
|
+
vllm/v1/attention/backends/gdn_attn.py,sha256=GcXAzEytL7-5lx8oF5p4hcxgqoyklFjcahxzUeg3Cl0,15593
|
|
1439
|
+
vllm/v1/attention/backends/linear_attn.py,sha256=Rtv3Ar38CJaIFLQ8gTZEbiTQaiuuYvOMWd-FBRZx41I,2423
|
|
1440
|
+
vllm/v1/attention/backends/mamba1_attn.py,sha256=P_gggtrN3dCOKIpu8tfaPA0OxHMillVnw7-Fq15SrlE,6566
|
|
1441
|
+
vllm/v1/attention/backends/mamba2_attn.py,sha256=I-QqkgHIi16wTrbmRdaOYYbXGjdERvJeMsp_tVP4e4Y,14536
|
|
1442
|
+
vllm/v1/attention/backends/mamba_attn.py,sha256=Ju98CzwIx5NZdnrihqLKfiZ7aUA12Mos6jVerifXcoo,4155
|
|
1443
|
+
vllm/v1/attention/backends/pallas.py,sha256=vPmofZaWK01Ofrrefk-j80q-Zb5Y0iIgVLsnCwWwkwg,15525
|
|
1444
|
+
vllm/v1/attention/backends/rocm_aiter_fa.py,sha256=x9BynteXttHruzgFzoFhygOan82fy774TutWYZyNKjI,38645
|
|
1445
|
+
vllm/v1/attention/backends/rocm_aiter_unified_attn.py,sha256=iUE5HookrAG-bwCByxAU0_xxi8oxGXZ7xNIY7sTHaG4,7062
|
|
1446
|
+
vllm/v1/attention/backends/rocm_attn.py,sha256=tGbnNFszyIC2snWIUWyPLqbIZhTvNHBDp8kJQaD4XO0,13167
|
|
1447
|
+
vllm/v1/attention/backends/short_conv_attn.py,sha256=4H_h50v2RK1zT6ty_hUw0D2oscm91Y0qeE8R7VYUm0k,3642
|
|
1448
|
+
vllm/v1/attention/backends/tree_attn.py,sha256=imbuCXjvLcOFDdMDP4sUNs-z042hO94mNAArqidYh2s,15689
|
|
1449
|
+
vllm/v1/attention/backends/triton_attn.py,sha256=So7JSJ5XONAmp6DSDFjgd7-gvxBK8AU56uv_7hHBC60,13390
|
|
1450
|
+
vllm/v1/attention/backends/utils.py,sha256=gX5ITCIhLaDlGUZI6CydJBTusYd3TMTdcpV8SW-KU-4,43660
|
|
1451
|
+
vllm/v1/attention/backends/mla/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1452
|
+
vllm/v1/attention/backends/mla/aiter_triton_mla.py,sha256=Laa8x_OwO3kNf4nd2WstB54C59SnBw9iAPn6f73X7S4,2183
|
|
1453
|
+
vllm/v1/attention/backends/mla/common.py,sha256=40HGDvzt6q8IFi1deGKmsMMRxRD-_i0VWI08Z8X28rs,81745
|
|
1454
|
+
vllm/v1/attention/backends/mla/cutlass_mla.py,sha256=sR4Os01cT3N0Hz94qlM8N1b3gytiqg99e52AGoRvN-A,8851
|
|
1455
|
+
vllm/v1/attention/backends/mla/flashattn_mla.py,sha256=1S7rvpgXY48setyQWwyB789P3uTYPpduOI11kf-wrU0,11986
|
|
1456
|
+
vllm/v1/attention/backends/mla/flashinfer_mla.py,sha256=LSU2gm1Y2L10jcIrIFSZg3DyBbnfONJJEcoG5OcvUd0,5646
|
|
1457
|
+
vllm/v1/attention/backends/mla/flashmla.py,sha256=2uujtSg-e-mhbt-g1YXwsaANIa6tKk9aYhloJGCzPSE,11289
|
|
1458
|
+
vllm/v1/attention/backends/mla/flashmla_sparse.py,sha256=ArZ2Fs3vL4bar_2ejwEnKnG9VeuCTAhMnn-_brmIY5g,19516
|
|
1459
|
+
vllm/v1/attention/backends/mla/indexer.py,sha256=XtjOa0dn0_hQDybsGbk3TCFWr1-hDGSRZ6zi-OrR8Xg,13246
|
|
1460
|
+
vllm/v1/attention/backends/mla/rocm_aiter_mla.py,sha256=EYgB67QCne1KAau-2McYbdzbYKW9SwiJLXlnVABL2Xg,9293
|
|
1461
|
+
vllm/v1/attention/backends/mla/rocm_aiter_mla_sparse.py,sha256=6J5gbviNQLiO0mcq7BLns1UsRpcop_zN2obKFvxkLw8,11177
|
|
1462
|
+
vllm/v1/attention/backends/mla/triton_mla.py,sha256=ahsT84ViQyAuFsP38zMfrEkG5mxUtt_Lpz_k-8ZFhk4,5135
|
|
1463
|
+
vllm/v1/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1464
|
+
vllm/v1/core/block_pool.py,sha256=CIsoUlXTBtT4ekidjCpaJfSHY7P-BQzLKu_-js_lbao,18014
|
|
1465
|
+
vllm/v1/core/encoder_cache_manager.py,sha256=IMT_S9-qVSz_BpWp5Ln98BCdKFgbAxczEb2kvsXY2Bs,13588
|
|
1466
|
+
vllm/v1/core/kv_cache_coordinator.py,sha256=sps9Z_hSQ2sqzmIF7rNrzNFArMbXMt78-l1wJV0uzME,22110
|
|
1467
|
+
vllm/v1/core/kv_cache_manager.py,sha256=6as6do-sznpTnl-Wcw1fo5-5_Pi952WhKXPGPiiOzBU,16750
|
|
1468
|
+
vllm/v1/core/kv_cache_metrics.py,sha256=7-3sBP7_XwSm1RxsRkKQtSq4wknWUSGpq58TcNa2f0c,3138
|
|
1469
|
+
vllm/v1/core/kv_cache_utils.py,sha256=DEiVPQyPzLkPPEtpZb9TUNMnm0VTFOpTCzF461nfJeI,57675
|
|
1470
|
+
vllm/v1/core/single_type_kv_cache_manager.py,sha256=L8-Jx1L_lFumX4eP1-TlkCqV3Ve_oj3OurotqfzgtJw,32757
|
|
1471
|
+
vllm/v1/core/sched/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1472
|
+
vllm/v1/core/sched/async_scheduler.py,sha256=MParbZ37oAwGSgF6a_OXh_np5_cmKOHo90mIy6nd5jk,2770
|
|
1473
|
+
vllm/v1/core/sched/interface.py,sha256=GI30-XxeczCYaXd6cS23nbbOwg-uBizVstZMNwS92xw,7218
|
|
1474
|
+
vllm/v1/core/sched/output.py,sha256=JHg1X4kiyynP9DkFfgTAnCUg6vcs1aPoFhu4dQI0sBE,8524
|
|
1475
|
+
vllm/v1/core/sched/request_queue.py,sha256=q1dc1b7gvxh2El2jwyDyAfB3ceLWI4warqy5StqeFXQ,7305
|
|
1476
|
+
vllm/v1/core/sched/scheduler.py,sha256=vZGmw1N3v6XsA3nOceIVCPVGPABbsty5wOlpFGSTvCg,79064
|
|
1477
|
+
vllm/v1/core/sched/utils.py,sha256=1QRUNDCcMmg1VWbm07iYgkrSETwWGyM2uSn6gpnMneY,2374
|
|
1478
|
+
vllm/v1/engine/__init__.py,sha256=xPmZ3l4_IJK28hs8NQSlZYfqGynPrgro1FsrO3VbH2E,6240
|
|
1479
|
+
vllm/v1/engine/async_llm.py,sha256=gZcutGBtapbSLpgksH5wFbqFxuJc8RNb3Wcr7tb1_T4,34138
|
|
1480
|
+
vllm/v1/engine/coordinator.py,sha256=U1oOQQmip60PDIPfSibkkiKtXb-3ZLU1T_ehwQBrpqM,16464
|
|
1481
|
+
vllm/v1/engine/core.py,sha256=u1HIcR-B9tgT5h72hL3DI8EHrUIUMh5WJuTUqqkB3ik,56933
|
|
1482
|
+
vllm/v1/engine/core_client.py,sha256=vNorxQf8w3yU6jI78dBWlpyfqvNVbInaoo9uqddyRHw,53826
|
|
1483
|
+
vllm/v1/engine/detokenizer.py,sha256=bqjCl_-KZ5OYiKC9CN-dy4kXm5liJAFNqFyyDFIreC8,13188
|
|
1484
|
+
vllm/v1/engine/exceptions.py,sha256=Uqu6bUKEvMYpeVJYxlqYeveRcd9WnsFUENKt0JLMins,732
|
|
1485
|
+
vllm/v1/engine/input_processor.py,sha256=ja8_41TyrPeS-GD1x5-UxTDF3u3E2TZ3kN3Fuvh4hWg,26924
|
|
1486
|
+
vllm/v1/engine/llm_engine.py,sha256=rDnyh6Xmn0JsOSzMiH83NKPbnQexDnrSMK6Ye3RrL5s,15860
|
|
1487
|
+
vllm/v1/engine/logprobs.py,sha256=fr2NyUcLSNVy6r_waE4SvyuXt3lk-g_PnsmxIXSNt2U,6272
|
|
1488
|
+
vllm/v1/engine/output_processor.py,sha256=SQfNyaQKajJUxIUrSjPEcGijJBmVbvQM-ZYo77vXUbE,25150
|
|
1489
|
+
vllm/v1/engine/parallel_sampling.py,sha256=cWNTjIH6qXgQ0lzN6Jbe-dGCR5p0iruyaHNd2qitQqA,5313
|
|
1490
|
+
vllm/v1/engine/processor.py,sha256=IFvjvs7Ra48m9isjZziA9vficQnK46wpvji99-s03Co,620
|
|
1491
|
+
vllm/v1/engine/utils.py,sha256=vKj9fxFwYelmowoL7zCfC-TEA7V_CyzbM1JACKo7w9k,41498
|
|
1492
|
+
vllm/v1/executor/__init__.py,sha256=VwU0pRwKjvcCcXII_7N2FIYT2oNj1fquLjvUS-qqE2U,227
|
|
1493
|
+
vllm/v1/executor/abstract.py,sha256=DtnQ83Vk3xlVD9zUaHka42L_xj9D-MuM5s54Sdq2VDs,13247
|
|
1494
|
+
vllm/v1/executor/multiproc_executor.py,sha256=8x7HeWKqmkWhq-ULIA_6zp-T-jIS07uDUZ-Benkdtco,34778
|
|
1495
|
+
vllm/v1/executor/ray_distributed_executor.py,sha256=tl8FrTK1jqQk2SKF-Rt6RtXacGD6ND-hXIjTrquAbkc,289
|
|
1496
|
+
vllm/v1/executor/ray_executor.py,sha256=Jx658pDLy-P0GqWtBHXv2RJXynr2ujaTqFUqPB5UVB4,25084
|
|
1497
|
+
vllm/v1/executor/ray_utils.py,sha256=MzthlsqlXOeYkeYrkKmLNYC5HcNgezzTgLTjfvZXVEI,19165
|
|
1498
|
+
vllm/v1/executor/uniproc_executor.py,sha256=jBmZS7HLUnjmFwxobfLfgPCw7KkHixZNpGiCL4ZI4hs,7254
|
|
1499
|
+
vllm/v1/kv_offload/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1500
|
+
vllm/v1/kv_offload/abstract.py,sha256=rEo4jQBZZ3AuYMDWNprePENX8wDFc086h40wFj4gmyg,5262
|
|
1501
|
+
vllm/v1/kv_offload/arc_manager.py,sha256=vUgKdsb11DwRqCcMkzW-lTf2zlMvGN2AaEHGy24G4LU,9545
|
|
1502
|
+
vllm/v1/kv_offload/backend.py,sha256=2ewriYjByJ2UwiWX-YJYhGkriJB0lChRnAbgtN0_8rY,2898
|
|
1503
|
+
vllm/v1/kv_offload/cpu.py,sha256=nTVHPag7alEuLarA734gjnL8fhWtVa76IHlZTzkoY2Y,3389
|
|
1504
|
+
vllm/v1/kv_offload/factory.py,sha256=iHoQ7Nz6tsCfg1UrrC0Ik9oI6APUQp_2y-oeGtSZ8Fk,1995
|
|
1505
|
+
vllm/v1/kv_offload/lru_manager.py,sha256=QO85HtD0uV-Et_UkhZdtgXk38-SZqHQtIi0M-qnWULY,4964
|
|
1506
|
+
vllm/v1/kv_offload/mediums.py,sha256=8i5qik1oKldR3Gyf7S5veHM5h1prPZVR4xN05HSOUKQ,880
|
|
1507
|
+
vllm/v1/kv_offload/spec.py,sha256=kEGVZYid5oV6sYlzW0b5tMO4RCLzzH-6aWdbbbsChhQ,2201
|
|
1508
|
+
vllm/v1/kv_offload/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1509
|
+
vllm/v1/kv_offload/backends/cpu.py,sha256=McAbCUX_6yYAipJ8bd418EOKxT_I4eIbzr0fiqeR46Y,2228
|
|
1510
|
+
vllm/v1/kv_offload/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1511
|
+
vllm/v1/kv_offload/worker/cpu_gpu.py,sha256=TYKlEfYqMyMb99R_waqmhUK2c6QuQ299IByt3sGc1sI,7173
|
|
1512
|
+
vllm/v1/kv_offload/worker/worker.py,sha256=Dl9fhiT_ARmjZ_e_NLGYtu1jx9uHZ7IaiGbYy8AI6Gs,4662
|
|
1513
|
+
vllm/v1/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1514
|
+
vllm/v1/metrics/loggers.py,sha256=ScdOJveLgIUSrMD5v0JTXHqSzH7rV5AdqtZDvo78EbA,46894
|
|
1515
|
+
vllm/v1/metrics/prometheus.py,sha256=dhI7DQbT7X3gFlcQOXmoa7PY5JPyw3fvFm0azVEP-ok,2777
|
|
1516
|
+
vllm/v1/metrics/ray_wrappers.py,sha256=aKg4C1sdyPhVyS41Cw48c-CSBFRCFaIUhi7FC7yIknk,6268
|
|
1517
|
+
vllm/v1/metrics/reader.py,sha256=drwtEKJn4gOnaCFvlaYEjibmQx7cQHIsDiQii4B9Uk4,8694
|
|
1518
|
+
vllm/v1/metrics/stats.py,sha256=WPfO1QTTTQoAUyuf4fuHAiQMK6JhqY1XAtExPnigFgk,14631
|
|
1519
|
+
vllm/v1/pool/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1520
|
+
vllm/v1/pool/metadata.py,sha256=CQBh5F6yDEgQabhEBLsffSuDrGOkrvEb6NlimowbTrw,2747
|
|
1521
|
+
vllm/v1/sample/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1522
|
+
vllm/v1/sample/metadata.py,sha256=jLeOuEJuWBJhgcy9TBL2gfjFj2DaJLWk-zPXARUEbsI,1142
|
|
1523
|
+
vllm/v1/sample/rejection_sampler.py,sha256=mbR3YCcdSLir36nPID6JakVx1kYdm8IEcnkxIVFsEhE,30049
|
|
1524
|
+
vllm/v1/sample/sampler.py,sha256=H0SOGJZvXIcnoSR7npHY6-j_tjvTiR2uXA5reu8cAVs,12583
|
|
1525
|
+
vllm/v1/sample/logits_processor/__init__.py,sha256=Hs6S01p-p_Xo-LcG5ihCwwGjqypt_8d_TEFnNLNfbIU,12047
|
|
1526
|
+
vllm/v1/sample/logits_processor/builtin.py,sha256=ejN7QaSXMarG07G5rVPwCZ-MbYua3ji6JbnjErnz1x8,10323
|
|
1527
|
+
vllm/v1/sample/logits_processor/interface.py,sha256=p6dGdoKdK94lIUv6RktdOjSHP8adIPNbL4lHxXDfC14,3218
|
|
1528
|
+
vllm/v1/sample/logits_processor/state.py,sha256=Fk_xGySqz7y2MiAi8hL0Q95DNXWelyu5E4XB-pD0d4E,5666
|
|
1529
|
+
vllm/v1/sample/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1530
|
+
vllm/v1/sample/ops/bad_words.py,sha256=z573nbjiCHu1wCQvnUSFaHS7pvgjnc5xnzDJpzNv3xU,1659
|
|
1531
|
+
vllm/v1/sample/ops/logprobs.py,sha256=krdqPu-zZQChtxbssdvIQtm49l4EckUTljJNVSxZfjk,942
|
|
1532
|
+
vllm/v1/sample/ops/penalties.py,sha256=OOrkMB8o3sFEbYjnCq8fvTbT0EEdL7Zn2U1Euf44CjM,1929
|
|
1533
|
+
vllm/v1/sample/ops/topk_topp_sampler.py,sha256=Um-MHs__yixtZ0BMOsbygkoC_-H3Cear_VEJvLFotPw,14599
|
|
1534
|
+
vllm/v1/sample/tpu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1535
|
+
vllm/v1/sample/tpu/metadata.py,sha256=-bfn1jLwhVOguzItVzMr44WzBKIvbhozwBZOLTKK8gQ,4624
|
|
1536
|
+
vllm/v1/sample/tpu/sampler.py,sha256=cLhsAU4ZFBJIgpP4915fqr4Cj3IBNVRPgCLrJsJCe6M,7723
|
|
1537
|
+
vllm/v1/spec_decode/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1538
|
+
vllm/v1/spec_decode/eagle.py,sha256=767s5v6P_ILhoBxOvFcCakngak7kYhkVOxWvHoo8EBs,57771
|
|
1539
|
+
vllm/v1/spec_decode/medusa.py,sha256=feMJOjJZaFvLQj_YYEvn_8iOvjfDSPpA8NES4BP1oPA,2510
|
|
1540
|
+
vllm/v1/spec_decode/metadata.py,sha256=pmlkh7PIgjwRn2Ad6BUENBve_v6Vuv5nPB9XCrICjag,2353
|
|
1541
|
+
vllm/v1/spec_decode/metrics.py,sha256=KZ4k_OZ5hyJFc9EciPxjEXJCTDWG6BuT9369H0VANxI,7867
|
|
1542
|
+
vllm/v1/spec_decode/ngram_proposer.py,sha256=vImwASeHuZsFweJkAc10V3HUKTmoEQcIDO0D7SXQjlo,11155
|
|
1543
|
+
vllm/v1/spec_decode/suffix_decoding.py,sha256=cqxL4Z8ugdjOrVDbPp33nn-UrLLdKXqF83p1rs9fP6s,4501
|
|
1544
|
+
vllm/v1/spec_decode/utils.py,sha256=ORHGXcR1Ifyk2YhhdkPBtvjOW9VNn-wPQLRWGUKXSBQ,5096
|
|
1545
|
+
vllm/v1/structured_output/__init__.py,sha256=0i1UTCzJmID3ebSTh92Hts49UA19VAp_MXOMe2rZxtA,14126
|
|
1546
|
+
vllm/v1/structured_output/backend_guidance.py,sha256=oMIwUIobGba_daERjvGua059g-ouDPv-2oa8m4fP3ZY,9000
|
|
1547
|
+
vllm/v1/structured_output/backend_lm_format_enforcer.py,sha256=Srnwxs9RmrtdxO2JL1PkwDOAczjrfZsA5eHh-uuAEH4,6307
|
|
1548
|
+
vllm/v1/structured_output/backend_outlines.py,sha256=e4MIkyIQk6oiKL5cdCJQsK7ZmM0QzKWgp31qLM5W8aA,11748
|
|
1549
|
+
vllm/v1/structured_output/backend_types.py,sha256=71Pfd9VOLNCoM8oyRiG2AFBNbIGrGuRwbo6sC0XqrRQ,3809
|
|
1550
|
+
vllm/v1/structured_output/backend_xgrammar.py,sha256=qMHw4Ek9Ut8Q9i9agj9qFI8MRecrJuAhNzR_IPlDl1E,12642
|
|
1551
|
+
vllm/v1/structured_output/request.py,sha256=PeAz0cG86T-VwR4y1p75TIM9aSKD09Ey7luq0g4h990,3313
|
|
1552
|
+
vllm/v1/structured_output/utils.py,sha256=2cGKjVj4NT1PsgbtJnvY22nuzyUOzmj2m835c90VdaE,16884
|
|
1553
|
+
vllm/v1/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1554
|
+
vllm/v1/worker/block_table.py,sha256=-OQlfV1ziXOrxorxyrRA5nngHhZALaOq7LN2jscDJRE,13178
|
|
1555
|
+
vllm/v1/worker/cpu_model_runner.py,sha256=Z4ltdu0avYcshrT5RecZn_fGm0aeQA9zvF2his8jQfA,4195
|
|
1556
|
+
vllm/v1/worker/cpu_worker.py,sha256=peU67Da6S9lnNuCMtwbbJaLphqdSV5FD5pUF8z6fl9A,8381
|
|
1557
|
+
vllm/v1/worker/dp_utils.py,sha256=tGmtzHB67A_-jFxGU-tfbDO71ybeo2LnGYpapacUS2k,9144
|
|
1558
|
+
vllm/v1/worker/ec_connector_model_runner_mixin.py,sha256=Wb5sV4xvjww7jijlgfnEOgOoswwyOKBuOJTG782b_b4,2967
|
|
1559
|
+
vllm/v1/worker/gpu_input_batch.py,sha256=BGN85GWlsnZqKMWtc8e04IoKkLz_KJFLWa7Ki0fZGTM,40542
|
|
1560
|
+
vllm/v1/worker/gpu_model_runner.py,sha256=Yj0pL7jF155BUSYv_jeni-vjVnbSpa56B1Pwoquf0cA,236465
|
|
1561
|
+
vllm/v1/worker/gpu_ubatch_wrapper.py,sha256=-c7NHDh-BX6mXy0HO3g6MQCh-I0izkfTIztmraDTn54,18195
|
|
1562
|
+
vllm/v1/worker/gpu_worker.py,sha256=JM8P272vhmCphHktrffftfX0RbiNIjUfg2WTuBbm-VE,38136
|
|
1563
|
+
vllm/v1/worker/kv_connector_model_runner_mixin.py,sha256=DVL1RiRnSU7rCHqQDp0d7WUXWZaMhrbGCFDC1CobWAU,12004
|
|
1564
|
+
vllm/v1/worker/lora_model_runner_mixin.py,sha256=Pif_hHUHu49LuXjvBLjJqYt4Hn1PISsYDnJR8A5Qxak,7447
|
|
1565
|
+
vllm/v1/worker/tpu_input_batch.py,sha256=V3GYLnwVuQNhCdE4V3Au2hmU3TNsBbfoQXTFrm6g8gU,24582
|
|
1566
|
+
vllm/v1/worker/tpu_model_runner.py,sha256=B0eWpBOcp98QfmoNeDw0ROx156DJrc1yBINzXY_gyWs,94508
|
|
1567
|
+
vllm/v1/worker/tpu_worker.py,sha256=0Jun0h6hv-7cI_0wjU6rAAa6Ikq5oYLlECSAgUPmaW0,14579
|
|
1568
|
+
vllm/v1/worker/ubatch_utils.py,sha256=1_zwPq9ZjBDEv671mvjmlVxMT7KmG41Zr99J-MYL0gY,2416
|
|
1569
|
+
vllm/v1/worker/ubatching.py,sha256=Ijg4yg_o596_fklK1ea-NXrtz8fKy-QN81hkqgJ5LhA,7974
|
|
1570
|
+
vllm/v1/worker/utils.py,sha256=cRz33hIo0TVRr_JPb3LA-2GMvsx1D9KPm4G9Of_QP8o,13446
|
|
1571
|
+
vllm/v1/worker/worker_base.py,sha256=DtUHbzHPsdb8TRVazhfyi7-gIIiWLGEAoxP_rcv-X_c,14535
|
|
1572
|
+
vllm/v1/worker/xpu_model_runner.py,sha256=2U3jepUQpj99KvOkLQf6ok0je8_veXET6ntuUS8gNHk,1251
|
|
1573
|
+
vllm/v1/worker/xpu_worker.py,sha256=z7ezF1JcglK59lFpWbm4h6E-rneAsv7YK9LyBptKQ-Q,8219
|
|
1574
|
+
vllm/v1/worker/gpu/README.md,sha256=1H_fnHpMus5c95vNXWX5-Ryx3UkQiRwY_b5WDd0D8Ww,181
|
|
1575
|
+
vllm/v1/worker/gpu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1576
|
+
vllm/v1/worker/gpu/async_utils.py,sha256=m-ujqv2PudqbFaBaeA-vvwfLqChOpM_IigM8vYOPnvg,4080
|
|
1577
|
+
vllm/v1/worker/gpu/attn_utils.py,sha256=LvL9Y9C-LyWq7TW7GARW1qKLvqh6GdUQiWx30oUrke8,7257
|
|
1578
|
+
vllm/v1/worker/gpu/block_table.py,sha256=nRKidgmffNrUNaOIHWkLu9nECLyhQB-UCvxOeu8xBZo,12049
|
|
1579
|
+
vllm/v1/worker/gpu/cudagraph_utils.py,sha256=UwaTuZV4TP4HcfJo63Pq1xwSh4f39b19m_3tM0YrPtA,8998
|
|
1580
|
+
vllm/v1/worker/gpu/dp_utils.py,sha256=tFuN8YrGpMRaX6wrsJ4j1trxM8dE9Fek2G60a8ovheY,920
|
|
1581
|
+
vllm/v1/worker/gpu/input_batch.py,sha256=Nvq22oSSJBt0vJmQu6y1sw_GaZhktSzr9SHg_tUbLT0,13753
|
|
1582
|
+
vllm/v1/worker/gpu/model_runner.py,sha256=gFNbKlYoI_nOgYjM9dCkSgyf4ve2Zsols-Gjk_hbrYs,41074
|
|
1583
|
+
vllm/v1/worker/gpu/states.py,sha256=ICVeT1UeZfR8e-62UnWuErGVqGu422qVYmtm-xNDWBQ,11533
|
|
1584
|
+
vllm/v1/worker/gpu/structured_outputs.py,sha256=gN73Jdtmx_E4qO1q15qoQCyzuFvylEe2epGoozlYcOQ,2515
|
|
1585
|
+
vllm/v1/worker/gpu/sample/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1586
|
+
vllm/v1/worker/gpu/sample/gumbel.py,sha256=pvYIkkNPjYc6jHGzR5R8hmU7aUMoIobjXBnn6qXGbhI,3033
|
|
1587
|
+
vllm/v1/worker/gpu/sample/logprob.py,sha256=32kWDLJyz3ct_mHKyp6vhzeuICtXmqs7E2deqJZhGkg,5227
|
|
1588
|
+
vllm/v1/worker/gpu/sample/metadata.py,sha256=W3_aa_p7c4tZc7UoAk5KFajFQkEqtbwNiWYkjSYZdTA,6647
|
|
1589
|
+
vllm/v1/worker/gpu/sample/penalties.py,sha256=_2sN8lRHTt3DYc2yXbGnJhg9ZsLb0AqutiKG4cMJYbQ,5343
|
|
1590
|
+
vllm/v1/worker/gpu/sample/sampler.py,sha256=9k0FdeimDAvG8unFWMqjDvox7GDOlC9gQ2CBp05NIKM,2641
|
|
1591
|
+
vllm/v1/worker/gpu/spec_decode/__init__.py,sha256=Ca2Xgzk8ZBRa5sae1pFSzBJR9DBk7vWIPgUWsFgILUI,584
|
|
1592
|
+
vllm/v1/worker/gpu/spec_decode/eagle.py,sha256=xzZkOV89uBcUkTpKgQuqfE-WmkKtoQ2nTZXbgEhdyEs,20644
|
|
1593
|
+
vllm/v1/worker/gpu/spec_decode/eagle_cudagraph.py,sha256=J-m9JoDhouw0AwTafwEC8aI0NnXfqLBXu2hMU2Pl2Y4,4044
|
|
1594
|
+
vllm/v1/worker/gpu/spec_decode/rejection_sample.py,sha256=p3H2FfFh4dBDnCYL0CR_hRNkj9ki1Srh5zVJn7Q9B9c,2563
|
|
1595
|
+
vllm/vllm_flash_attn/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1596
|
+
vllm_cpu-0.12.0.dist-info/METADATA,sha256=0iwm0ai_mDSedff41jgnq-U38P7_AgJTTrBqo4A1l6A,14259
|
|
1597
|
+
vllm_cpu-0.12.0.dist-info/WHEEL,sha256=xQyHjUA2gxo8wIrD8CY4L9aFQLreRF9cXdK-zQkv0Y8,114
|
|
1598
|
+
vllm_cpu-0.12.0.dist-info/entry_points.txt,sha256=ErfiCUEEMrGDD3jBwf8c54AolBCFv7qrc8Ix9iqzzfs,184
|
|
1599
|
+
vllm_cpu-0.12.0.dist-info/top_level.txt,sha256=fAgb8Pt4zQoKTUA3ZnKEIgcjh0L97_dwEjYDTL5MEEo,5
|
|
1600
|
+
vllm_cpu-0.12.0.dist-info/RECORD,,
|