vllm-cpu 0.11.0.post2__cp312-cp312-manylinux_2_17_x86_64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- vllm/_C.abi3.so +0 -0
- vllm/__init__.py +220 -0
- vllm/_bc_linter.py +59 -0
- vllm/_custom_ops.py +2044 -0
- vllm/_ipex_ops.py +393 -0
- vllm/_version.py +34 -0
- vllm/assets/__init__.py +0 -0
- vllm/assets/audio.py +45 -0
- vllm/assets/base.py +41 -0
- vllm/assets/image.py +50 -0
- vllm/assets/video.py +145 -0
- vllm/attention/__init__.py +15 -0
- vllm/attention/backends/__init__.py +0 -0
- vllm/attention/backends/abstract.py +204 -0
- vllm/attention/backends/utils.py +33 -0
- vllm/attention/layer.py +645 -0
- vllm/attention/layers/__init__.py +0 -0
- vllm/attention/layers/chunked_local_attention.py +93 -0
- vllm/attention/layers/cross_attention.py +162 -0
- vllm/attention/layers/encoder_only_attention.py +86 -0
- vllm/attention/ops/__init__.py +0 -0
- vllm/attention/ops/chunked_prefill_paged_decode.py +405 -0
- vllm/attention/ops/common.py +345 -0
- vllm/attention/ops/flashmla.py +192 -0
- vllm/attention/ops/merge_attn_states.py +43 -0
- vllm/attention/ops/paged_attn.py +262 -0
- vllm/attention/ops/pallas_kv_cache_update.py +124 -0
- vllm/attention/ops/prefix_prefill.py +928 -0
- vllm/attention/ops/rocm_aiter_mla.py +104 -0
- vllm/attention/ops/rocm_aiter_paged_attn.py +102 -0
- vllm/attention/ops/triton_decode_attention.py +691 -0
- vllm/attention/ops/triton_flash_attention.py +984 -0
- vllm/attention/ops/triton_merge_attn_states.py +97 -0
- vllm/attention/ops/triton_reshape_and_cache_flash.py +175 -0
- vllm/attention/ops/triton_unified_attention.py +894 -0
- vllm/attention/selector.py +245 -0
- vllm/attention/utils/__init__.py +0 -0
- vllm/attention/utils/fa_utils.py +85 -0
- vllm/attention/utils/kv_sharing_utils.py +33 -0
- vllm/beam_search.py +87 -0
- vllm/benchmarks/__init__.py +0 -0
- vllm/benchmarks/datasets.py +2723 -0
- vllm/benchmarks/latency.py +170 -0
- vllm/benchmarks/lib/__init__.py +3 -0
- vllm/benchmarks/lib/endpoint_request_func.py +533 -0
- vllm/benchmarks/lib/ready_checker.py +73 -0
- vllm/benchmarks/lib/utils.py +80 -0
- vllm/benchmarks/serve.py +1358 -0
- vllm/benchmarks/throughput.py +696 -0
- vllm/collect_env.py +823 -0
- vllm/compilation/__init__.py +0 -0
- vllm/compilation/activation_quant_fusion.py +189 -0
- vllm/compilation/backends.py +650 -0
- vllm/compilation/base_static_graph.py +56 -0
- vllm/compilation/collective_fusion.py +1188 -0
- vllm/compilation/compiler_interface.py +573 -0
- vllm/compilation/counter.py +47 -0
- vllm/compilation/cuda_graph.py +199 -0
- vllm/compilation/cuda_piecewise_backend.py +117 -0
- vllm/compilation/decorators.py +400 -0
- vllm/compilation/fix_functionalization.py +205 -0
- vllm/compilation/fusion.py +383 -0
- vllm/compilation/fusion_attn.py +295 -0
- vllm/compilation/fx_utils.py +84 -0
- vllm/compilation/inductor_pass.py +136 -0
- vllm/compilation/monitor.py +57 -0
- vllm/compilation/noop_elimination.py +158 -0
- vllm/compilation/pass_manager.py +125 -0
- vllm/compilation/post_cleanup.py +20 -0
- vllm/compilation/sequence_parallelism.py +478 -0
- vllm/compilation/torch25_custom_graph_pass.py +42 -0
- vllm/compilation/vllm_inductor_pass.py +156 -0
- vllm/compilation/wrapper.py +136 -0
- vllm/config/__init__.py +814 -0
- vllm/config/cache.py +220 -0
- vllm/config/compilation.py +673 -0
- vllm/config/device.py +74 -0
- vllm/config/kv_events.py +50 -0
- vllm/config/kv_transfer.py +111 -0
- vllm/config/load.py +113 -0
- vllm/config/lora.py +132 -0
- vllm/config/model.py +1912 -0
- vllm/config/multimodal.py +129 -0
- vllm/config/observability.py +99 -0
- vllm/config/parallel.py +524 -0
- vllm/config/pooler.py +97 -0
- vllm/config/scheduler.py +287 -0
- vllm/config/speculative.py +568 -0
- vllm/config/speech_to_text.py +39 -0
- vllm/config/structured_outputs.py +64 -0
- vllm/config/utils.py +145 -0
- vllm/connections.py +186 -0
- vllm/device_allocator/__init__.py +0 -0
- vllm/device_allocator/cumem.py +311 -0
- vllm/distributed/__init__.py +6 -0
- vllm/distributed/communication_op.py +41 -0
- vllm/distributed/device_communicators/__init__.py +0 -0
- vllm/distributed/device_communicators/all2all.py +440 -0
- vllm/distributed/device_communicators/all_reduce_utils.py +317 -0
- vllm/distributed/device_communicators/base_device_communicator.py +295 -0
- vllm/distributed/device_communicators/cpu_communicator.py +201 -0
- vllm/distributed/device_communicators/cuda_communicator.py +323 -0
- vllm/distributed/device_communicators/cuda_wrapper.py +180 -0
- vllm/distributed/device_communicators/custom_all_reduce.py +311 -0
- vllm/distributed/device_communicators/mnnvl_compat.py +28 -0
- vllm/distributed/device_communicators/pynccl.py +340 -0
- vllm/distributed/device_communicators/pynccl_allocator.py +186 -0
- vllm/distributed/device_communicators/pynccl_wrapper.py +416 -0
- vllm/distributed/device_communicators/quick_all_reduce.py +278 -0
- vllm/distributed/device_communicators/ray_communicator.py +258 -0
- vllm/distributed/device_communicators/shm_broadcast.py +589 -0
- vllm/distributed/device_communicators/shm_object_storage.py +635 -0
- vllm/distributed/device_communicators/symm_mem.py +136 -0
- vllm/distributed/device_communicators/tpu_communicator.py +102 -0
- vllm/distributed/device_communicators/xpu_communicator.py +94 -0
- vllm/distributed/eplb/__init__.py +8 -0
- vllm/distributed/eplb/eplb_state.py +620 -0
- vllm/distributed/eplb/rebalance_algo.py +239 -0
- vllm/distributed/eplb/rebalance_execute.py +424 -0
- vllm/distributed/kv_events.py +362 -0
- vllm/distributed/kv_transfer/README.md +29 -0
- vllm/distributed/kv_transfer/__init__.py +13 -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 +113 -0
- vllm/distributed/kv_transfer/kv_connector/utils.py +261 -0
- vllm/distributed/kv_transfer/kv_connector/v1/__init__.py +6 -0
- vllm/distributed/kv_transfer/kv_connector/v1/base.py +388 -0
- vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py +168 -0
- vllm/distributed/kv_transfer/kv_connector/v1/metrics.py +100 -0
- vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py +328 -0
- vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py +1473 -0
- vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py +485 -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 +488 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py +550 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py +267 -0
- vllm/distributed/kv_transfer/kv_connector/v1/shared_storage_connector.py +418 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/__init__.py +0 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/base.py +175 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/mooncake_store.py +161 -0
- vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py +237 -0
- vllm/distributed/kv_transfer/kv_pipe/__init__.py +0 -0
- vllm/distributed/kv_transfer/kv_pipe/base.py +67 -0
- vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py +290 -0
- vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py +280 -0
- vllm/distributed/kv_transfer/kv_transfer_state.py +73 -0
- vllm/distributed/parallel_state.py +1532 -0
- vllm/distributed/tpu_distributed_utils.py +178 -0
- vllm/distributed/utils.py +536 -0
- vllm/engine/__init__.py +0 -0
- vllm/engine/arg_utils.py +1778 -0
- vllm/engine/async_llm_engine.py +6 -0
- vllm/engine/llm_engine.py +6 -0
- vllm/engine/metrics.py +577 -0
- vllm/engine/metrics_types.py +84 -0
- vllm/engine/protocol.py +333 -0
- vllm/entrypoints/__init__.py +0 -0
- vllm/entrypoints/api_server.py +178 -0
- vllm/entrypoints/chat_utils.py +1705 -0
- vllm/entrypoints/cli/__init__.py +12 -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 +55 -0
- vllm/entrypoints/cli/benchmark/serve.py +21 -0
- vllm/entrypoints/cli/benchmark/throughput.py +21 -0
- vllm/entrypoints/cli/collect_env.py +36 -0
- vllm/entrypoints/cli/main.py +60 -0
- vllm/entrypoints/cli/openai.py +233 -0
- vllm/entrypoints/cli/run_batch.py +67 -0
- vllm/entrypoints/cli/serve.py +232 -0
- vllm/entrypoints/cli/types.py +29 -0
- vllm/entrypoints/constants.py +10 -0
- vllm/entrypoints/context.py +481 -0
- vllm/entrypoints/harmony_utils.py +436 -0
- vllm/entrypoints/launcher.py +164 -0
- vllm/entrypoints/llm.py +1629 -0
- vllm/entrypoints/logger.py +79 -0
- vllm/entrypoints/openai/__init__.py +0 -0
- vllm/entrypoints/openai/api_server.py +1953 -0
- vllm/entrypoints/openai/cli_args.py +288 -0
- vllm/entrypoints/openai/logits_processors.py +90 -0
- vllm/entrypoints/openai/protocol.py +2757 -0
- vllm/entrypoints/openai/run_batch.py +491 -0
- vllm/entrypoints/openai/serving_chat.py +1597 -0
- vllm/entrypoints/openai/serving_classification.py +173 -0
- vllm/entrypoints/openai/serving_completion.py +692 -0
- vllm/entrypoints/openai/serving_embedding.py +631 -0
- vllm/entrypoints/openai/serving_engine.py +992 -0
- vllm/entrypoints/openai/serving_models.py +288 -0
- vllm/entrypoints/openai/serving_pooling.py +276 -0
- vllm/entrypoints/openai/serving_responses.py +1709 -0
- vllm/entrypoints/openai/serving_score.py +479 -0
- vllm/entrypoints/openai/serving_tokenization.py +196 -0
- vllm/entrypoints/openai/serving_transcription.py +136 -0
- vllm/entrypoints/openai/speech_to_text.py +388 -0
- vllm/entrypoints/openai/tool_parsers/__init__.py +55 -0
- vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py +164 -0
- vllm/entrypoints/openai/tool_parsers/deepseekv31_tool_parser.py +367 -0
- vllm/entrypoints/openai/tool_parsers/deepseekv3_tool_parser.py +370 -0
- vllm/entrypoints/openai/tool_parsers/glm4_moe_tool_parser.py +185 -0
- vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py +259 -0
- vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py +237 -0
- vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py +455 -0
- vllm/entrypoints/openai/tool_parsers/hunyuan_a13b_tool_parser.py +372 -0
- vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py +216 -0
- vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py +308 -0
- vllm/entrypoints/openai/tool_parsers/kimi_k2_tool_parser.py +377 -0
- vllm/entrypoints/openai/tool_parsers/llama4_pythonic_tool_parser.py +316 -0
- vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py +269 -0
- vllm/entrypoints/openai/tool_parsers/longcat_tool_parser.py +39 -0
- vllm/entrypoints/openai/tool_parsers/minimax_tool_parser.py +816 -0
- vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py +369 -0
- vllm/entrypoints/openai/tool_parsers/openai_tool_parser.py +93 -0
- vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py +112 -0
- vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py +308 -0
- vllm/entrypoints/openai/tool_parsers/qwen3coder_tool_parser.py +707 -0
- vllm/entrypoints/openai/tool_parsers/qwen3xml_tool_parser.py +1137 -0
- vllm/entrypoints/openai/tool_parsers/seed_oss_tool_parser.py +679 -0
- vllm/entrypoints/openai/tool_parsers/step3_tool_parser.py +296 -0
- vllm/entrypoints/openai/tool_parsers/utils.py +124 -0
- vllm/entrypoints/openai/tool_parsers/xlam_tool_parser.py +524 -0
- vllm/entrypoints/renderer.py +395 -0
- vllm/entrypoints/score_utils.py +232 -0
- vllm/entrypoints/ssl.py +75 -0
- vllm/entrypoints/tool.py +139 -0
- vllm/entrypoints/tool_server.py +206 -0
- vllm/entrypoints/utils.py +233 -0
- vllm/env_override.py +23 -0
- vllm/envs.py +1590 -0
- vllm/executor/__init__.py +0 -0
- vllm/executor/executor_base.py +381 -0
- vllm/executor/msgspec_utils.py +35 -0
- vllm/executor/ray_distributed_executor.py +699 -0
- vllm/executor/ray_utils.py +410 -0
- vllm/executor/uniproc_executor.py +176 -0
- vllm/forward_context.py +402 -0
- vllm/inputs/__init__.py +30 -0
- vllm/inputs/data.py +356 -0
- vllm/inputs/parse.py +151 -0
- vllm/inputs/preprocess.py +664 -0
- vllm/logger.py +229 -0
- vllm/logging_utils/__init__.py +10 -0
- vllm/logging_utils/dump_input.py +81 -0
- vllm/logging_utils/formatter.py +79 -0
- vllm/logging_utils/log_time.py +32 -0
- vllm/logits_process.py +119 -0
- vllm/logprobs.py +28 -0
- vllm/lora/__init__.py +0 -0
- vllm/lora/layers/__init__.py +34 -0
- vllm/lora/layers/base.py +69 -0
- vllm/lora/layers/base_linear.py +185 -0
- vllm/lora/layers/column_parallel_linear.py +609 -0
- vllm/lora/layers/logits_processor.py +247 -0
- vllm/lora/layers/qkv_x_parallel_linear.py +8 -0
- vllm/lora/layers/replicated_linear.py +60 -0
- vllm/lora/layers/row_parallel_linear.py +196 -0
- vllm/lora/layers/utils.py +65 -0
- vllm/lora/layers/vocal_parallel_embedding.py +174 -0
- vllm/lora/lora_weights.py +199 -0
- vllm/lora/models.py +816 -0
- vllm/lora/ops/__init__.py +0 -0
- vllm/lora/ops/ipex_ops/__init__.py +7 -0
- vllm/lora/ops/ipex_ops/lora_ops.py +44 -0
- vllm/lora/ops/torch_ops/__init__.py +16 -0
- vllm/lora/ops/torch_ops/lora_ops.py +119 -0
- vllm/lora/ops/triton_ops/__init__.py +12 -0
- vllm/lora/ops/triton_ops/kernel_utils.py +243 -0
- vllm/lora/ops/triton_ops/lora_expand_op.py +289 -0
- vllm/lora/ops/triton_ops/lora_kernel_metadata.py +148 -0
- vllm/lora/ops/triton_ops/lora_shrink_op.py +243 -0
- vllm/lora/ops/triton_ops/utils.py +126 -0
- vllm/lora/ops/xla_ops/__init__.py +7 -0
- vllm/lora/ops/xla_ops/lora_ops.py +144 -0
- vllm/lora/peft_helper.py +127 -0
- vllm/lora/punica_wrapper/__init__.py +10 -0
- vllm/lora/punica_wrapper/punica_base.py +458 -0
- vllm/lora/punica_wrapper/punica_cpu.py +349 -0
- vllm/lora/punica_wrapper/punica_gpu.py +272 -0
- vllm/lora/punica_wrapper/punica_selector.py +20 -0
- vllm/lora/punica_wrapper/punica_tpu.py +391 -0
- vllm/lora/punica_wrapper/punica_xpu.py +276 -0
- vllm/lora/punica_wrapper/utils.py +136 -0
- vllm/lora/request.py +97 -0
- vllm/lora/resolver.py +85 -0
- vllm/lora/utils.py +246 -0
- vllm/lora/worker_manager.py +267 -0
- vllm/model_executor/__init__.py +12 -0
- vllm/model_executor/custom_op.py +194 -0
- vllm/model_executor/layers/__init__.py +0 -0
- vllm/model_executor/layers/activation.py +575 -0
- vllm/model_executor/layers/attention_layer_base.py +23 -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 +225 -0
- vllm/model_executor/layers/fla/ops/chunk_delta_h.py +290 -0
- vllm/model_executor/layers/fla/ops/chunk_o.py +177 -0
- vllm/model_executor/layers/fla/ops/chunk_scaled_dot_kkt.py +140 -0
- vllm/model_executor/layers/fla/ops/cumsum.py +226 -0
- vllm/model_executor/layers/fla/ops/fused_recurrent.py +366 -0
- vllm/model_executor/layers/fla/ops/index.py +39 -0
- vllm/model_executor/layers/fla/ops/l2norm.py +143 -0
- vllm/model_executor/layers/fla/ops/layernorm_guard.py +337 -0
- vllm/model_executor/layers/fla/ops/op.py +39 -0
- vllm/model_executor/layers/fla/ops/solve_tril.py +365 -0
- vllm/model_executor/layers/fla/ops/utils.py +180 -0
- vllm/model_executor/layers/fla/ops/wy_fast.py +114 -0
- vllm/model_executor/layers/fused_moe/__init__.py +89 -0
- vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py +322 -0
- vllm/model_executor/layers/fused_moe/batched_triton_or_deep_gemm_moe.py +141 -0
- vllm/model_executor/layers/fused_moe/config.py +804 -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=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 +218 -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=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=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=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=NVIDIA_H100,dtype=fp8_w8a8.json +123 -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=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=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=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=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=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=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=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=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=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=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=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=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=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=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=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=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_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.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_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=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_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=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 +300 -0
- vllm/model_executor/layers/fused_moe/cutlass_moe.py +957 -0
- vllm/model_executor/layers/fused_moe/deep_gemm_moe.py +362 -0
- vllm/model_executor/layers/fused_moe/deep_gemm_utils.py +413 -0
- vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py +361 -0
- vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py +274 -0
- vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py +268 -0
- vllm/model_executor/layers/fused_moe/flashinfer_cutlass_prepare_finalize.py +300 -0
- vllm/model_executor/layers/fused_moe/flashinfer_trtllm_moe.py +184 -0
- vllm/model_executor/layers/fused_moe/fused_batched_moe.py +993 -0
- vllm/model_executor/layers/fused_moe/fused_marlin_moe.py +239 -0
- vllm/model_executor/layers/fused_moe/fused_moe.py +1890 -0
- vllm/model_executor/layers/fused_moe/gpt_oss_triton_kernels_moe.py +307 -0
- vllm/model_executor/layers/fused_moe/layer.py +2195 -0
- vllm/model_executor/layers/fused_moe/modular_kernel.py +1038 -0
- vllm/model_executor/layers/fused_moe/moe_align_block_size.py +87 -0
- vllm/model_executor/layers/fused_moe/moe_pallas.py +80 -0
- vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py +205 -0
- vllm/model_executor/layers/fused_moe/moe_torch_iterative.py +60 -0
- vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py +341 -0
- vllm/model_executor/layers/fused_moe/prepare_finalize.py +70 -0
- vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py +424 -0
- vllm/model_executor/layers/fused_moe/routing_simulator.py +291 -0
- vllm/model_executor/layers/fused_moe/topk_weight_and_reduce.py +146 -0
- vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py +143 -0
- vllm/model_executor/layers/fused_moe/trtllm_moe.py +191 -0
- vllm/model_executor/layers/fused_moe/utils.py +274 -0
- vllm/model_executor/layers/layernorm.py +395 -0
- vllm/model_executor/layers/lightning_attn.py +661 -0
- vllm/model_executor/layers/linear.py +1603 -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 +42 -0
- vllm/model_executor/layers/mamba/linear_attn.py +403 -0
- vllm/model_executor/layers/mamba/mamba_mixer.py +466 -0
- vllm/model_executor/layers/mamba/mamba_mixer2.py +764 -0
- vllm/model_executor/layers/mamba/mamba_utils.py +186 -0
- vllm/model_executor/layers/mamba/ops/__init__.py +0 -0
- vllm/model_executor/layers/mamba/ops/causal_conv1d.py +1092 -0
- vllm/model_executor/layers/mamba/ops/layernorm_gated.py +168 -0
- vllm/model_executor/layers/mamba/ops/mamba_ssm.py +414 -0
- vllm/model_executor/layers/mamba/ops/ssd_bmm.py +242 -0
- vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py +527 -0
- vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py +724 -0
- vllm/model_executor/layers/mamba/ops/ssd_combined.py +238 -0
- vllm/model_executor/layers/mamba/ops/ssd_state_passing.py +200 -0
- vllm/model_executor/layers/mamba/short_conv.py +253 -0
- vllm/model_executor/layers/mla.py +173 -0
- vllm/model_executor/layers/pooler.py +719 -0
- vllm/model_executor/layers/quantization/__init__.py +157 -0
- vllm/model_executor/layers/quantization/auto_round.py +388 -0
- vllm/model_executor/layers/quantization/awq.py +228 -0
- vllm/model_executor/layers/quantization/awq_marlin.py +554 -0
- vllm/model_executor/layers/quantization/awq_triton.py +320 -0
- vllm/model_executor/layers/quantization/base_config.py +170 -0
- vllm/model_executor/layers/quantization/bitblas.py +464 -0
- vllm/model_executor/layers/quantization/bitsandbytes.py +627 -0
- vllm/model_executor/layers/quantization/compressed_tensors/__init__.py +0 -0
- vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py +797 -0
- vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py +2074 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py +27 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py +366 -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 +160 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py +105 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py +185 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_fp8.py +169 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_int.py +135 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py +121 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py +157 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py +111 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py +201 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/__init__.py +0 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/linear.py +238 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/module.py +153 -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 +46 -0
- vllm/model_executor/layers/quantization/compressed_tensors/transform/utils.py +13 -0
- vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py +206 -0
- vllm/model_executor/layers/quantization/compressed_tensors/utils.py +216 -0
- vllm/model_executor/layers/quantization/deepspeedfp.py +196 -0
- vllm/model_executor/layers/quantization/experts_int8.py +223 -0
- vllm/model_executor/layers/quantization/fbgemm_fp8.py +172 -0
- vllm/model_executor/layers/quantization/fp8.py +1098 -0
- vllm/model_executor/layers/quantization/gguf.py +599 -0
- vllm/model_executor/layers/quantization/gptq.py +340 -0
- vllm/model_executor/layers/quantization/gptq_bitblas.py +448 -0
- vllm/model_executor/layers/quantization/gptq_marlin.py +751 -0
- vllm/model_executor/layers/quantization/gptq_marlin_24.py +297 -0
- vllm/model_executor/layers/quantization/hqq_marlin.py +333 -0
- vllm/model_executor/layers/quantization/inc.py +61 -0
- vllm/model_executor/layers/quantization/input_quant_fp8.py +156 -0
- vllm/model_executor/layers/quantization/ipex_quant.py +415 -0
- vllm/model_executor/layers/quantization/kernels/__init__.py +0 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py +91 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py +93 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py +116 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py +302 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/conch.py +92 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/cutlass.py +117 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/dynamic_4bit.py +92 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py +143 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py +144 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py +139 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py +67 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py +89 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py +161 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/cpu.py +206 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py +137 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py +41 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py +104 -0
- vllm/model_executor/layers/quantization/kv_cache.py +143 -0
- vllm/model_executor/layers/quantization/modelopt.py +1596 -0
- vllm/model_executor/layers/quantization/moe_wna16.py +484 -0
- vllm/model_executor/layers/quantization/mxfp4.py +988 -0
- vllm/model_executor/layers/quantization/petit.py +306 -0
- vllm/model_executor/layers/quantization/ptpc_fp8.py +129 -0
- vllm/model_executor/layers/quantization/quark/__init__.py +0 -0
- vllm/model_executor/layers/quantization/quark/quark.py +432 -0
- vllm/model_executor/layers/quantization/quark/quark_moe.py +561 -0
- vllm/model_executor/layers/quantization/quark/schemes/__init__.py +9 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py +55 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py +239 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py +163 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py +122 -0
- vllm/model_executor/layers/quantization/quark/utils.py +105 -0
- vllm/model_executor/layers/quantization/rtn.py +466 -0
- vllm/model_executor/layers/quantization/schema.py +86 -0
- vllm/model_executor/layers/quantization/torchao.py +214 -0
- vllm/model_executor/layers/quantization/tpu_int8.py +125 -0
- vllm/model_executor/layers/quantization/utils/__init__.py +6 -0
- vllm/model_executor/layers/quantization/utils/allspark_utils.py +52 -0
- vllm/model_executor/layers/quantization/utils/bitblas_utils.py +210 -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=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 +79 -0
- vllm/model_executor/layers/quantization/utils/flashinfer_utils.py +248 -0
- vllm/model_executor/layers/quantization/utils/fp8_utils.py +949 -0
- vllm/model_executor/layers/quantization/utils/gptq_utils.py +146 -0
- vllm/model_executor/layers/quantization/utils/int8_utils.py +492 -0
- vllm/model_executor/layers/quantization/utils/layer_utils.py +40 -0
- vllm/model_executor/layers/quantization/utils/machete_utils.py +50 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils.py +479 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py +396 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py +345 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_test.py +165 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py +464 -0
- vllm/model_executor/layers/quantization/utils/mxfp4_utils.py +141 -0
- vllm/model_executor/layers/quantization/utils/mxfp8_utils.py +20 -0
- vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py +137 -0
- vllm/model_executor/layers/quantization/utils/nvfp4_moe_support.py +59 -0
- vllm/model_executor/layers/quantization/utils/petit_utils.py +122 -0
- vllm/model_executor/layers/quantization/utils/quant_utils.py +641 -0
- vllm/model_executor/layers/quantization/utils/w8a8_utils.py +458 -0
- vllm/model_executor/layers/resampler.py +270 -0
- vllm/model_executor/layers/rotary_embedding/__init__.py +204 -0
- vllm/model_executor/layers/rotary_embedding/base.py +177 -0
- vllm/model_executor/layers/rotary_embedding/common.py +150 -0
- vllm/model_executor/layers/rotary_embedding/deepseek_scaling_rope.py +138 -0
- vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py +197 -0
- vllm/model_executor/layers/rotary_embedding/dynamic_ntk_alpha_rope.py +41 -0
- vllm/model_executor/layers/rotary_embedding/dynamic_ntk_scaling_rope.py +67 -0
- vllm/model_executor/layers/rotary_embedding/ernie45_vl_rope.py +80 -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 +81 -0
- vllm/model_executor/layers/rotary_embedding/mrope.py +1321 -0
- vllm/model_executor/layers/rotary_embedding/ntk_scaling_rope.py +42 -0
- vllm/model_executor/layers/rotary_embedding/phi3_long_rope_scaled_rope.py +129 -0
- vllm/model_executor/layers/rotary_embedding/rocm_aiter_rope_ops.py +86 -0
- vllm/model_executor/layers/rotary_embedding/yarn_scaling_rope.py +68 -0
- vllm/model_executor/layers/shared_fused_moe/__init__.py +6 -0
- vllm/model_executor/layers/shared_fused_moe/shared_fused_moe.py +56 -0
- vllm/model_executor/layers/utils.py +195 -0
- vllm/model_executor/layers/vocab_parallel_embedding.py +487 -0
- vllm/model_executor/model_loader/__init__.py +138 -0
- vllm/model_executor/model_loader/base_loader.py +52 -0
- vllm/model_executor/model_loader/bitsandbytes_loader.py +788 -0
- vllm/model_executor/model_loader/default_loader.py +277 -0
- vllm/model_executor/model_loader/dummy_loader.py +28 -0
- vllm/model_executor/model_loader/gguf_loader.py +155 -0
- vllm/model_executor/model_loader/runai_streamer_loader.py +104 -0
- vllm/model_executor/model_loader/sharded_state_loader.py +199 -0
- vllm/model_executor/model_loader/tensorizer.py +738 -0
- vllm/model_executor/model_loader/tensorizer_loader.py +143 -0
- vllm/model_executor/model_loader/tpu.py +114 -0
- vllm/model_executor/model_loader/utils.py +292 -0
- vllm/model_executor/model_loader/weight_utils.py +990 -0
- vllm/model_executor/models/__init__.py +33 -0
- vllm/model_executor/models/adapters.py +542 -0
- vllm/model_executor/models/aimv2.py +246 -0
- vllm/model_executor/models/apertus.py +579 -0
- vllm/model_executor/models/arcee.py +422 -0
- vllm/model_executor/models/arctic.py +558 -0
- vllm/model_executor/models/aria.py +650 -0
- vllm/model_executor/models/aya_vision.py +468 -0
- vllm/model_executor/models/baichuan.py +474 -0
- vllm/model_executor/models/bailing_moe.py +642 -0
- vllm/model_executor/models/bamba.py +514 -0
- vllm/model_executor/models/bert.py +665 -0
- vllm/model_executor/models/bert_with_rope.py +687 -0
- vllm/model_executor/models/blip.py +339 -0
- vllm/model_executor/models/blip2.py +712 -0
- vllm/model_executor/models/bloom.py +374 -0
- vllm/model_executor/models/chameleon.py +1139 -0
- vllm/model_executor/models/chatglm.py +476 -0
- vllm/model_executor/models/clip.py +407 -0
- vllm/model_executor/models/cohere2_vision.py +481 -0
- vllm/model_executor/models/commandr.py +465 -0
- vllm/model_executor/models/config.py +445 -0
- vllm/model_executor/models/dbrx.py +471 -0
- vllm/model_executor/models/deepseek.py +497 -0
- vllm/model_executor/models/deepseek_eagle.py +240 -0
- vllm/model_executor/models/deepseek_mtp.py +289 -0
- vllm/model_executor/models/deepseek_v2.py +1444 -0
- vllm/model_executor/models/deepseek_vl2.py +658 -0
- vllm/model_executor/models/dots1.py +546 -0
- vllm/model_executor/models/dots_ocr.py +873 -0
- vllm/model_executor/models/ernie45.py +43 -0
- vllm/model_executor/models/ernie45_moe.py +607 -0
- vllm/model_executor/models/ernie45_vl.py +1527 -0
- vllm/model_executor/models/ernie45_vl_moe.py +727 -0
- vllm/model_executor/models/ernie_mtp.py +268 -0
- vllm/model_executor/models/exaone.py +550 -0
- vllm/model_executor/models/exaone4.py +533 -0
- vllm/model_executor/models/fairseq2_llama.py +154 -0
- vllm/model_executor/models/falcon.py +509 -0
- vllm/model_executor/models/falcon_h1.py +674 -0
- vllm/model_executor/models/fuyu.py +399 -0
- vllm/model_executor/models/gemma.py +425 -0
- vllm/model_executor/models/gemma2.py +422 -0
- vllm/model_executor/models/gemma3.py +555 -0
- vllm/model_executor/models/gemma3_mm.py +721 -0
- vllm/model_executor/models/gemma3n.py +1113 -0
- vllm/model_executor/models/gemma3n_mm.py +761 -0
- vllm/model_executor/models/glm.py +23 -0
- vllm/model_executor/models/glm4.py +304 -0
- vllm/model_executor/models/glm4_1v.py +1690 -0
- vllm/model_executor/models/glm4_moe.py +727 -0
- vllm/model_executor/models/glm4_moe_mtp.py +301 -0
- vllm/model_executor/models/glm4v.py +654 -0
- vllm/model_executor/models/gpt2.py +380 -0
- vllm/model_executor/models/gpt_bigcode.py +344 -0
- vllm/model_executor/models/gpt_j.py +339 -0
- vllm/model_executor/models/gpt_neox.py +330 -0
- vllm/model_executor/models/gpt_oss.py +712 -0
- vllm/model_executor/models/granite.py +489 -0
- vllm/model_executor/models/granite_speech.py +794 -0
- vllm/model_executor/models/granitemoe.py +550 -0
- vllm/model_executor/models/granitemoehybrid.py +614 -0
- vllm/model_executor/models/granitemoeshared.py +332 -0
- vllm/model_executor/models/gritlm.py +262 -0
- vllm/model_executor/models/grok1.py +547 -0
- vllm/model_executor/models/h2ovl.py +536 -0
- vllm/model_executor/models/hunyuan_v1.py +1042 -0
- vllm/model_executor/models/hyperclovax_vision.py +1192 -0
- vllm/model_executor/models/idefics2_vision_model.py +417 -0
- vllm/model_executor/models/idefics3.py +756 -0
- vllm/model_executor/models/interfaces.py +959 -0
- vllm/model_executor/models/interfaces_base.py +192 -0
- vllm/model_executor/models/intern_vit.py +441 -0
- vllm/model_executor/models/internlm2.py +450 -0
- vllm/model_executor/models/internlm2_ve.py +148 -0
- vllm/model_executor/models/interns1.py +838 -0
- vllm/model_executor/models/interns1_vit.py +418 -0
- vllm/model_executor/models/internvl.py +1423 -0
- vllm/model_executor/models/jais.py +373 -0
- vllm/model_executor/models/jamba.py +591 -0
- vllm/model_executor/models/jina_vl.py +144 -0
- vllm/model_executor/models/keye.py +1680 -0
- vllm/model_executor/models/keye_vl1_5.py +602 -0
- vllm/model_executor/models/kimi_vl.py +618 -0
- vllm/model_executor/models/lfm2.py +548 -0
- vllm/model_executor/models/llama.py +669 -0
- vllm/model_executor/models/llama4.py +746 -0
- vllm/model_executor/models/llama4_eagle.py +239 -0
- vllm/model_executor/models/llama_eagle.py +179 -0
- vllm/model_executor/models/llama_eagle3.py +296 -0
- vllm/model_executor/models/llava.py +870 -0
- vllm/model_executor/models/llava_next.py +571 -0
- vllm/model_executor/models/llava_next_video.py +476 -0
- vllm/model_executor/models/llava_onevision.py +942 -0
- vllm/model_executor/models/longcat_flash.py +715 -0
- vllm/model_executor/models/longcat_flash_mtp.py +352 -0
- vllm/model_executor/models/mamba.py +275 -0
- vllm/model_executor/models/mamba2.py +291 -0
- vllm/model_executor/models/medusa.py +169 -0
- vllm/model_executor/models/midashenglm.py +792 -0
- vllm/model_executor/models/mimo.py +188 -0
- vllm/model_executor/models/mimo_mtp.py +280 -0
- vllm/model_executor/models/minicpm.py +631 -0
- vllm/model_executor/models/minicpm3.py +230 -0
- vllm/model_executor/models/minicpm_eagle.py +389 -0
- vllm/model_executor/models/minicpmo.py +770 -0
- vllm/model_executor/models/minicpmv.py +1784 -0
- vllm/model_executor/models/minimax_text_01.py +986 -0
- vllm/model_executor/models/minimax_vl_01.py +426 -0
- vllm/model_executor/models/mistral3.py +628 -0
- vllm/model_executor/models/mixtral.py +606 -0
- vllm/model_executor/models/mllama4.py +1076 -0
- vllm/model_executor/models/mlp_speculator.py +206 -0
- vllm/model_executor/models/modernbert.py +374 -0
- vllm/model_executor/models/module_mapping.py +72 -0
- vllm/model_executor/models/molmo.py +1567 -0
- vllm/model_executor/models/moonvit.py +673 -0
- vllm/model_executor/models/motif.py +345 -0
- vllm/model_executor/models/mpt.py +329 -0
- vllm/model_executor/models/nano_nemotron_vl.py +1394 -0
- vllm/model_executor/models/nemotron.py +507 -0
- vllm/model_executor/models/nemotron_h.py +565 -0
- vllm/model_executor/models/nemotron_nas.py +481 -0
- vllm/model_executor/models/nemotron_vl.py +652 -0
- vllm/model_executor/models/nvlm_d.py +203 -0
- vllm/model_executor/models/olmo.py +404 -0
- vllm/model_executor/models/olmo2.py +439 -0
- vllm/model_executor/models/olmoe.py +483 -0
- vllm/model_executor/models/opt.py +412 -0
- vllm/model_executor/models/orion.py +348 -0
- vllm/model_executor/models/ovis.py +559 -0
- vllm/model_executor/models/ovis2_5.py +642 -0
- vllm/model_executor/models/paligemma.py +411 -0
- vllm/model_executor/models/persimmon.py +343 -0
- vllm/model_executor/models/phi.py +356 -0
- vllm/model_executor/models/phi3.py +19 -0
- vllm/model_executor/models/phi3v.py +698 -0
- vllm/model_executor/models/phi4_multimodal.py +1475 -0
- vllm/model_executor/models/phi4mm.py +1279 -0
- vllm/model_executor/models/phi4mm_audio.py +1254 -0
- vllm/model_executor/models/phi4mm_utils.py +1875 -0
- vllm/model_executor/models/phimoe.py +679 -0
- vllm/model_executor/models/pixtral.py +1345 -0
- vllm/model_executor/models/plamo2.py +978 -0
- vllm/model_executor/models/qwen.py +361 -0
- vllm/model_executor/models/qwen2.py +523 -0
- vllm/model_executor/models/qwen2_5_omni_thinker.py +984 -0
- vllm/model_executor/models/qwen2_5_vl.py +1481 -0
- vllm/model_executor/models/qwen2_audio.py +489 -0
- vllm/model_executor/models/qwen2_moe.py +558 -0
- vllm/model_executor/models/qwen2_rm.py +122 -0
- vllm/model_executor/models/qwen2_vl.py +1670 -0
- vllm/model_executor/models/qwen3.py +341 -0
- vllm/model_executor/models/qwen3_moe.py +692 -0
- vllm/model_executor/models/qwen3_next.py +1266 -0
- vllm/model_executor/models/qwen3_next_mtp.py +281 -0
- vllm/model_executor/models/qwen3_vl.py +1613 -0
- vllm/model_executor/models/qwen3_vl_moe.py +358 -0
- vllm/model_executor/models/qwen_vl.py +795 -0
- vllm/model_executor/models/radio.py +576 -0
- vllm/model_executor/models/registry.py +990 -0
- vllm/model_executor/models/roberta.py +252 -0
- vllm/model_executor/models/rvl.py +103 -0
- vllm/model_executor/models/seed_oss.py +485 -0
- vllm/model_executor/models/siglip.py +540 -0
- vllm/model_executor/models/siglip2navit.py +689 -0
- vllm/model_executor/models/skyworkr1v.py +911 -0
- vllm/model_executor/models/smolvlm.py +44 -0
- vllm/model_executor/models/solar.py +504 -0
- vllm/model_executor/models/stablelm.py +341 -0
- vllm/model_executor/models/starcoder2.py +354 -0
- vllm/model_executor/models/step3_text.py +510 -0
- vllm/model_executor/models/step3_vl.py +1072 -0
- vllm/model_executor/models/swin.py +475 -0
- vllm/model_executor/models/tarsier.py +639 -0
- vllm/model_executor/models/telechat2.py +151 -0
- vllm/model_executor/models/teleflm.py +79 -0
- vllm/model_executor/models/terratorch.py +294 -0
- vllm/model_executor/models/transformers.py +948 -0
- vllm/model_executor/models/ultravox.py +654 -0
- vllm/model_executor/models/utils.py +808 -0
- vllm/model_executor/models/vision.py +404 -0
- vllm/model_executor/models/voxtral.py +786 -0
- vllm/model_executor/models/whisper.py +963 -0
- vllm/model_executor/models/zamba2.py +960 -0
- vllm/model_executor/parameter.py +620 -0
- vllm/model_executor/utils.py +86 -0
- vllm/model_executor/warmup/__init__.py +0 -0
- vllm/model_executor/warmup/deep_gemm_warmup.py +230 -0
- vllm/model_executor/warmup/kernel_warmup.py +83 -0
- vllm/multimodal/__init__.py +33 -0
- vllm/multimodal/audio.py +116 -0
- vllm/multimodal/base.py +27 -0
- vllm/multimodal/cache.py +697 -0
- vllm/multimodal/evs.py +273 -0
- vllm/multimodal/hasher.py +102 -0
- vllm/multimodal/image.py +130 -0
- vllm/multimodal/inputs.py +987 -0
- vllm/multimodal/parse.py +511 -0
- vllm/multimodal/processing.py +2148 -0
- vllm/multimodal/profiling.py +284 -0
- vllm/multimodal/registry.py +345 -0
- vllm/multimodal/utils.py +503 -0
- vllm/multimodal/video.py +319 -0
- vllm/outputs.py +324 -0
- vllm/platforms/__init__.py +263 -0
- vllm/platforms/cpu.py +340 -0
- vllm/platforms/cuda.py +668 -0
- vllm/platforms/interface.py +620 -0
- vllm/platforms/rocm.py +497 -0
- vllm/platforms/tpu.py +233 -0
- vllm/platforms/xpu.py +243 -0
- vllm/plugins/__init__.py +72 -0
- vllm/plugins/io_processors/__init__.py +68 -0
- vllm/plugins/io_processors/interface.py +67 -0
- vllm/plugins/lora_resolvers/README.md +16 -0
- vllm/plugins/lora_resolvers/__init__.py +0 -0
- vllm/plugins/lora_resolvers/filesystem_resolver.py +50 -0
- vllm/pooling_params.py +191 -0
- vllm/profiler/__init__.py +0 -0
- vllm/profiler/layerwise_profile.py +375 -0
- vllm/profiler/utils.py +148 -0
- vllm/py.typed +2 -0
- vllm/ray/__init__.py +0 -0
- vllm/ray/lazy_utils.py +22 -0
- vllm/ray/ray_env.py +72 -0
- vllm/reasoning/__init__.py +29 -0
- vllm/reasoning/abs_reasoning_parsers.py +202 -0
- vllm/reasoning/basic_parsers.py +156 -0
- vllm/reasoning/deepseek_r1_reasoning_parser.py +67 -0
- vllm/reasoning/glm4_moe_reasoning_parser.py +151 -0
- vllm/reasoning/gptoss_reasoning_parser.py +87 -0
- vllm/reasoning/granite_reasoning_parser.py +363 -0
- vllm/reasoning/hunyuan_a13b_reasoning_parser.py +245 -0
- vllm/reasoning/mistral_reasoning_parser.py +56 -0
- vllm/reasoning/qwen3_reasoning_parser.py +72 -0
- vllm/reasoning/seedoss_reasoning_parser.py +28 -0
- vllm/reasoning/step3_reasoning_parser.py +109 -0
- vllm/sampling_params.py +593 -0
- vllm/scalar_type.py +349 -0
- vllm/scripts.py +15 -0
- vllm/sequence.py +103 -0
- vllm/tasks.py +11 -0
- vllm/test_utils.py +129 -0
- vllm/third_party/__init__.py +0 -0
- vllm/third_party/pynvml.py +6140 -0
- vllm/tracing.py +136 -0
- vllm/transformers_utils/__init__.py +24 -0
- vllm/transformers_utils/chat_templates/__init__.py +5 -0
- vllm/transformers_utils/chat_templates/registry.py +70 -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_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 +1102 -0
- vllm/transformers_utils/config_parser_base.py +20 -0
- vllm/transformers_utils/configs/__init__.py +63 -0
- vllm/transformers_utils/configs/arctic.py +207 -0
- vllm/transformers_utils/configs/chatglm.py +72 -0
- vllm/transformers_utils/configs/deepseek_v3.py +101 -0
- vllm/transformers_utils/configs/deepseek_vl2.py +216 -0
- vllm/transformers_utils/configs/dotsocr.py +69 -0
- vllm/transformers_utils/configs/eagle.py +84 -0
- vllm/transformers_utils/configs/falcon.py +90 -0
- vllm/transformers_utils/configs/jais.py +237 -0
- vllm/transformers_utils/configs/kimi_vl.py +37 -0
- vllm/transformers_utils/configs/medusa.py +63 -0
- vllm/transformers_utils/configs/midashenglm.py +101 -0
- vllm/transformers_utils/configs/mistral.py +165 -0
- vllm/transformers_utils/configs/mlp_speculator.py +68 -0
- vllm/transformers_utils/configs/moonvit.py +33 -0
- vllm/transformers_utils/configs/nemotron.py +205 -0
- vllm/transformers_utils/configs/nemotron_h.py +259 -0
- vllm/transformers_utils/configs/nemotron_vl.py +56 -0
- vllm/transformers_utils/configs/olmo3.py +80 -0
- vllm/transformers_utils/configs/ovis.py +176 -0
- vllm/transformers_utils/configs/qwen3_next.py +275 -0
- vllm/transformers_utils/configs/radio.py +91 -0
- vllm/transformers_utils/configs/speculators/__init__.py +2 -0
- vllm/transformers_utils/configs/speculators/algos.py +32 -0
- vllm/transformers_utils/configs/speculators/base.py +111 -0
- vllm/transformers_utils/configs/step3_vl.py +123 -0
- vllm/transformers_utils/configs/ultravox.py +116 -0
- vllm/transformers_utils/detokenizer_utils.py +199 -0
- vllm/transformers_utils/dynamic_module.py +60 -0
- vllm/transformers_utils/processor.py +299 -0
- vllm/transformers_utils/processors/__init__.py +16 -0
- vllm/transformers_utils/processors/deepseek_vl2.py +362 -0
- vllm/transformers_utils/processors/ovis.py +420 -0
- vllm/transformers_utils/processors/ovis2_5.py +458 -0
- vllm/transformers_utils/runai_utils.py +104 -0
- vllm/transformers_utils/s3_utils.py +93 -0
- vllm/transformers_utils/tokenizer.py +292 -0
- vllm/transformers_utils/tokenizer_base.py +154 -0
- vllm/transformers_utils/tokenizers/__init__.py +10 -0
- vllm/transformers_utils/tokenizers/mistral.py +521 -0
- vllm/transformers_utils/utils.py +108 -0
- vllm/triton_utils/__init__.py +16 -0
- vllm/triton_utils/importing.py +96 -0
- vllm/usage/__init__.py +0 -0
- vllm/usage/usage_lib.py +259 -0
- vllm/utils/__init__.py +3566 -0
- vllm/utils/deep_gemm.py +319 -0
- vllm/utils/flashinfer.py +443 -0
- vllm/utils/jsontree.py +178 -0
- vllm/utils/tensor_schema.py +235 -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 +919 -0
- vllm/v1/attention/backends/flash_attn.py +795 -0
- vllm/v1/attention/backends/flashinfer.py +1181 -0
- vllm/v1/attention/backends/flex_attention.py +861 -0
- vllm/v1/attention/backends/gdn_attn.py +332 -0
- vllm/v1/attention/backends/linear_attn.py +67 -0
- vllm/v1/attention/backends/mamba1_attn.py +81 -0
- vllm/v1/attention/backends/mamba2_attn.py +232 -0
- vllm/v1/attention/backends/mamba_attn.py +52 -0
- vllm/v1/attention/backends/mla/__init__.py +0 -0
- vllm/v1/attention/backends/mla/common.py +1783 -0
- vllm/v1/attention/backends/mla/cutlass_mla.py +248 -0
- vllm/v1/attention/backends/mla/flashattn_mla.py +271 -0
- vllm/v1/attention/backends/mla/flashinfer_mla.py +114 -0
- vllm/v1/attention/backends/mla/flashmla.py +203 -0
- vllm/v1/attention/backends/mla/flashmla_sparse.py +544 -0
- vllm/v1/attention/backends/mla/indexer.py +342 -0
- vllm/v1/attention/backends/mla/rocm_aiter_mla.py +255 -0
- vllm/v1/attention/backends/mla/triton_mla.py +177 -0
- vllm/v1/attention/backends/pallas.py +409 -0
- vllm/v1/attention/backends/rocm_aiter_fa.py +549 -0
- vllm/v1/attention/backends/rocm_attn.py +426 -0
- vllm/v1/attention/backends/short_conv_attn.py +94 -0
- vllm/v1/attention/backends/tree_attn.py +451 -0
- vllm/v1/attention/backends/triton_attn.py +361 -0
- vllm/v1/attention/backends/utils.py +990 -0
- vllm/v1/attention/backends/xformers.py +438 -0
- vllm/v1/core/__init__.py +0 -0
- vllm/v1/core/block_pool.py +416 -0
- vllm/v1/core/encoder_cache_manager.py +333 -0
- vllm/v1/core/kv_cache_coordinator.py +440 -0
- vllm/v1/core/kv_cache_manager.py +399 -0
- vllm/v1/core/kv_cache_utils.py +1291 -0
- vllm/v1/core/sched/__init__.py +0 -0
- vllm/v1/core/sched/async_scheduler.py +47 -0
- vllm/v1/core/sched/interface.py +158 -0
- vllm/v1/core/sched/output.py +166 -0
- vllm/v1/core/sched/request_queue.py +224 -0
- vllm/v1/core/sched/scheduler.py +1296 -0
- vllm/v1/core/sched/utils.py +69 -0
- vllm/v1/core/single_type_kv_cache_manager.py +671 -0
- vllm/v1/cudagraph_dispatcher.py +125 -0
- vllm/v1/engine/__init__.py +203 -0
- vllm/v1/engine/async_llm.py +742 -0
- vllm/v1/engine/coordinator.py +357 -0
- vllm/v1/engine/core.py +1235 -0
- vllm/v1/engine/core_client.py +1334 -0
- vllm/v1/engine/detokenizer.py +349 -0
- vllm/v1/engine/exceptions.py +17 -0
- vllm/v1/engine/llm_engine.py +370 -0
- vllm/v1/engine/logprobs.py +201 -0
- vllm/v1/engine/output_processor.py +576 -0
- vllm/v1/engine/parallel_sampling.py +133 -0
- vllm/v1/engine/processor.py +545 -0
- vllm/v1/engine/utils.py +860 -0
- vllm/v1/executor/__init__.py +0 -0
- vllm/v1/executor/abstract.py +137 -0
- vllm/v1/executor/multiproc_executor.py +726 -0
- vllm/v1/executor/ray_distributed_executor.py +108 -0
- vllm/v1/executor/utils.py +23 -0
- vllm/v1/kv_cache_interface.py +375 -0
- vllm/v1/kv_offload/__init__.py +0 -0
- vllm/v1/kv_offload/abstract.py +165 -0
- vllm/v1/kv_offload/backend.py +96 -0
- vllm/v1/kv_offload/backends/__init__.py +0 -0
- vllm/v1/kv_offload/backends/cpu.py +61 -0
- vllm/v1/kv_offload/cpu.py +75 -0
- vllm/v1/kv_offload/factory.py +56 -0
- vllm/v1/kv_offload/lru_manager.py +132 -0
- vllm/v1/kv_offload/mediums.py +39 -0
- vllm/v1/kv_offload/spec.py +61 -0
- vllm/v1/kv_offload/worker/__init__.py +0 -0
- vllm/v1/kv_offload/worker/cpu_gpu.py +171 -0
- vllm/v1/kv_offload/worker/worker.py +142 -0
- vllm/v1/metrics/__init__.py +0 -0
- vllm/v1/metrics/loggers.py +741 -0
- vllm/v1/metrics/prometheus.py +82 -0
- vllm/v1/metrics/ray_wrappers.py +152 -0
- vllm/v1/metrics/reader.py +246 -0
- vllm/v1/metrics/stats.py +257 -0
- vllm/v1/outputs.py +161 -0
- vllm/v1/pool/__init__.py +0 -0
- vllm/v1/pool/metadata.py +77 -0
- vllm/v1/request.py +241 -0
- vllm/v1/sample/__init__.py +0 -0
- vllm/v1/sample/logits_processor/__init__.py +294 -0
- vllm/v1/sample/logits_processor/builtin.py +275 -0
- vllm/v1/sample/logits_processor/interface.py +97 -0
- vllm/v1/sample/logits_processor/state.py +161 -0
- vllm/v1/sample/metadata.py +43 -0
- vllm/v1/sample/ops/__init__.py +0 -0
- vllm/v1/sample/ops/bad_words.py +39 -0
- vllm/v1/sample/ops/logprobs.py +26 -0
- vllm/v1/sample/ops/penalties.py +43 -0
- vllm/v1/sample/ops/topk_topp_sampler.py +292 -0
- vllm/v1/sample/rejection_sampler.py +623 -0
- vllm/v1/sample/sampler.py +285 -0
- vllm/v1/sample/tpu/__init__.py +0 -0
- vllm/v1/sample/tpu/metadata.py +124 -0
- vllm/v1/sample/tpu/sampler.py +213 -0
- vllm/v1/serial_utils.py +423 -0
- vllm/v1/spec_decode/__init__.py +0 -0
- vllm/v1/spec_decode/eagle.py +1011 -0
- vllm/v1/spec_decode/medusa.py +66 -0
- vllm/v1/spec_decode/metadata.py +62 -0
- vllm/v1/spec_decode/metrics.py +211 -0
- vllm/v1/spec_decode/ngram_proposer.py +276 -0
- vllm/v1/spec_decode/utils.py +14 -0
- vllm/v1/structured_output/__init__.py +295 -0
- vllm/v1/structured_output/backend_guidance.py +245 -0
- vllm/v1/structured_output/backend_lm_format_enforcer.py +167 -0
- vllm/v1/structured_output/backend_outlines.py +320 -0
- vllm/v1/structured_output/backend_types.py +134 -0
- vllm/v1/structured_output/backend_xgrammar.py +327 -0
- vllm/v1/structured_output/request.py +86 -0
- vllm/v1/structured_output/utils.py +454 -0
- vllm/v1/utils.py +396 -0
- vllm/v1/worker/__init__.py +0 -0
- vllm/v1/worker/block_table.py +210 -0
- vllm/v1/worker/cpu_model_runner.py +175 -0
- vllm/v1/worker/cpu_worker.py +156 -0
- vllm/v1/worker/gpu_input_batch.py +863 -0
- vllm/v1/worker/gpu_model_runner.py +4160 -0
- vllm/v1/worker/gpu_ubatch_wrapper.py +399 -0
- vllm/v1/worker/gpu_worker.py +710 -0
- vllm/v1/worker/kv_connector_model_runner_mixin.py +132 -0
- vllm/v1/worker/lora_model_runner_mixin.py +183 -0
- vllm/v1/worker/tpu_input_batch.py +587 -0
- vllm/v1/worker/tpu_model_runner.py +1946 -0
- vllm/v1/worker/tpu_worker.py +346 -0
- vllm/v1/worker/ubatch_splitting.py +192 -0
- vllm/v1/worker/ubatch_utils.py +27 -0
- vllm/v1/worker/ubatching.py +224 -0
- vllm/v1/worker/utils.py +344 -0
- vllm/v1/worker/worker_base.py +65 -0
- vllm/v1/worker/xpu_model_runner.py +57 -0
- vllm/v1/worker/xpu_worker.py +179 -0
- vllm/version.py +41 -0
- vllm/vllm_flash_attn/.gitkeep +0 -0
- vllm/worker/__init__.py +0 -0
- vllm/worker/worker_base.py +279 -0
- vllm_cpu-0.11.0.post2.dist-info/METADATA +348 -0
- vllm_cpu-0.11.0.post2.dist-info/RECORD +1398 -0
- vllm_cpu-0.11.0.post2.dist-info/WHEEL +5 -0
- vllm_cpu-0.11.0.post2.dist-info/entry_points.txt +5 -0
- vllm_cpu-0.11.0.post2.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,1398 @@
|
|
|
1
|
+
vllm/_C.abi3.so,sha256=o-Vf3tZ2MZBmzXXJUIO_vrs2Dy95cy3ScA-wlx3dm9k,30661744
|
|
2
|
+
vllm/__init__.py,sha256=MQoYb7rYoeo-kX8Fp20iKGfIoOqnTXz5WOaWoRDbncU,8622
|
|
3
|
+
vllm/_bc_linter.py,sha256=RTr7MzNcfVt1cExZAjCU0_XddMsYLaVofVJ4rZbPpZg,1130
|
|
4
|
+
vllm/_custom_ops.py,sha256=jOCAQp1_HNMNVbWQ47pbt-1kIcD79maLzUURTj0_Dp8,82862
|
|
5
|
+
vllm/_ipex_ops.py,sha256=vrvToq0fY3pfBHa0yYn57ERUDokC3R6qC3Vh14OPxck,14229
|
|
6
|
+
vllm/_version.py,sha256=luFqPHKJItj2p-ycEJGs0hqXGuVWVm3G1f_j_AzzJz4,721
|
|
7
|
+
vllm/beam_search.py,sha256=SlhWsmeczGcDv_q8ahGzsuH-2UPSn5YJWLp4JudUuyw,2638
|
|
8
|
+
vllm/collect_env.py,sha256=Wp1V9YqqxKIRAk14w4OXuxeXPctrlK1Plnd9VvQDQsQ,28332
|
|
9
|
+
vllm/connections.py,sha256=ikzr0dLJwK8Snr1UGOzB9rqf_wm9mka-qJPMfflim5c,5567
|
|
10
|
+
vllm/env_override.py,sha256=8AjyisA4M-B6jf7_Fy3Jg2uEw3_YC1BCz4YfZwV8W5g,798
|
|
11
|
+
vllm/envs.py,sha256=pwAWUhpULXv6SITA-cPvx034zQMPWXGlh3SoerNdOAM,67001
|
|
12
|
+
vllm/forward_context.py,sha256=I_XaE4f5K_dR5rbOjmbkDSPwzn_3dISLIlklAXwlyHM,16985
|
|
13
|
+
vllm/logger.py,sha256=tvf9zwIBZ3h_rHiT73Ki3tR9xR2YF8UxCPxrCf0qPGw,8163
|
|
14
|
+
vllm/logits_process.py,sha256=jwjHjce3rKtUh21j5NRAOkhQZp5U-oKfySsXtplh-aU,4461
|
|
15
|
+
vllm/logprobs.py,sha256=fINdiEWKd-jHejnSCCJdgjlJ_OntlmxBP1_5wa7S27k,932
|
|
16
|
+
vllm/outputs.py,sha256=7mCqdWO32wKcXMNS_NvWMBVXXi1fiYkz26KU-2mv04k,12179
|
|
17
|
+
vllm/pooling_params.py,sha256=5GyVVJfh4hwMlZ6jwJuwEjg7z5ZwABCM2QaoHKGE54E,6917
|
|
18
|
+
vllm/py.typed,sha256=F5LUrt0voM87SNuuOky2X9veCVDqJUgRg_VohYqDigY,65
|
|
19
|
+
vllm/sampling_params.py,sha256=ghlEJ3OufMptO2NQdDjosGVPvPAkv38DfdgO2fhgvwE,26277
|
|
20
|
+
vllm/scalar_type.py,sha256=WJBNCrw9FJN1X4v8XthULwPl9Z06D3E0Lp6e9QyhVpw,12486
|
|
21
|
+
vllm/scripts.py,sha256=GBLs96wGlHWNj7WDtb-kuwHCR7HCdQIJN-vDoPh2Ud8,501
|
|
22
|
+
vllm/sequence.py,sha256=2edblYgGoLaixu_A3l4CdfUHg4zcoFqT1YSHagwthag,3611
|
|
23
|
+
vllm/tasks.py,sha256=VT3C8VC8S7yL8fxhxjjXGPZWOhsYmiuGjUJTSeqSscQ,398
|
|
24
|
+
vllm/test_utils.py,sha256=OhWk4tlIKWr7CT-NlNrOMnPFyfHI_w3fB8ZzbYPY95U,6015
|
|
25
|
+
vllm/tracing.py,sha256=xSfM1V5r4pQ7UJ5ZINIPx35C6D26xLt3PlskVpfLioQ,5113
|
|
26
|
+
vllm/version.py,sha256=j5_jpV6lcpUIkq56JF2uxJS02TJjG_7nGrzjvf7ptDI,1375
|
|
27
|
+
vllm/assets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
28
|
+
vllm/assets/audio.py,sha256=03OUK2QRgJDgEucc2HDl3vdrwgiRAuBxzckas015Ces,1254
|
|
29
|
+
vllm/assets/base.py,sha256=Yv1bK5DmfZbWr_1Uqhb-mawh5M6yC1tlFT6gRkHtcgs,1265
|
|
30
|
+
vllm/assets/image.py,sha256=X9uLm_fdT8IPGHvyFoBh1yTjmy1bWfFuYlkP1C75KdY,1570
|
|
31
|
+
vllm/assets/video.py,sha256=Ky8mj9vIXdm5-RJM4BY4KZXoImmHSwBKFed55ERKjZo,4476
|
|
32
|
+
vllm/attention/__init__.py,sha256=IeZgSJDl-7Lc4UBDBX0Et8jz45qHAyWsmv6CfreGQFU,474
|
|
33
|
+
vllm/attention/layer.py,sha256=gxNv9T4QQyL1qxQlwZA411xOqLBghbYnrxMhGjm8JlM,26695
|
|
34
|
+
vllm/attention/selector.py,sha256=jUVvGByH1R3RJc4ajV1ecEYU5EI32jycwdRl3bxqz9U,8022
|
|
35
|
+
vllm/attention/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
36
|
+
vllm/attention/backends/abstract.py,sha256=dlkmhn3iKQGjVRdV5qrAE3RlC3iJVJfniVm7Ic9kvDo,6291
|
|
37
|
+
vllm/attention/backends/utils.py,sha256=wnegtbRVT1EnfOjBXr6aKVtixeuBnDHfYGSlSqQXqLE,887
|
|
38
|
+
vllm/attention/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
39
|
+
vllm/attention/layers/chunked_local_attention.py,sha256=fdZOyXdSpv29X4p8SFMCLYp6dfykHRoRQr9CPG4P6vs,3547
|
|
40
|
+
vllm/attention/layers/cross_attention.py,sha256=nU5BDWosytA3yzK_Nf5TDRmrdgyguCtzhmleWgSWJN8,6096
|
|
41
|
+
vllm/attention/layers/encoder_only_attention.py,sha256=F31atlHXMQm2HAReWZ5K_XkDnZhZgc6Sr2o9QuHs6I0,3225
|
|
42
|
+
vllm/attention/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
43
|
+
vllm/attention/ops/chunked_prefill_paged_decode.py,sha256=a4Hyg_vF_3QvbuYxgVIhkOCZu60ndEFiCfB0TtH5zak,13610
|
|
44
|
+
vllm/attention/ops/common.py,sha256=Rw39HowgdNHn0W0LZ9jPSHLFaOD0FxLOGn-oDT8bCy4,11856
|
|
45
|
+
vllm/attention/ops/flashmla.py,sha256=dUKA6Drtnp5RPELnlyQCD7HdTFm3LSOGMKJ1w3TEX0w,7205
|
|
46
|
+
vllm/attention/ops/merge_attn_states.py,sha256=1ed_lE3BuH_ahf1PW4d0I6izUasZuKbQdKSeVLu6ESw,1706
|
|
47
|
+
vllm/attention/ops/paged_attn.py,sha256=P04ugYaamXJoyIuyoYhHi0rZwmjOqC9a3toAUhz36Uw,8592
|
|
48
|
+
vllm/attention/ops/pallas_kv_cache_update.py,sha256=aHiYya1JXNCULxzQRS0qP1JHCfsW_kXVKf8w7cQwFNw,4232
|
|
49
|
+
vllm/attention/ops/prefix_prefill.py,sha256=gFX53IC-FyesklWsii5WXvCONXIyXgtp4XCyJJtLeJo,32191
|
|
50
|
+
vllm/attention/ops/rocm_aiter_mla.py,sha256=xfSzRsAYlysmHNIszg_df1JMsV-zURso0PLwwGABo94,3697
|
|
51
|
+
vllm/attention/ops/rocm_aiter_paged_attn.py,sha256=oFwCpksGqTOHikbdaj0zhXUBxDi1f3fmNxh85voS-so,3968
|
|
52
|
+
vllm/attention/ops/triton_decode_attention.py,sha256=i8H-bY7ynjTAv4Mzc9wwnHBYcrSyTZI5lSKE0QpdIIo,19520
|
|
53
|
+
vllm/attention/ops/triton_flash_attention.py,sha256=qt0ss9DjryWVXSdAIdxoDK-KiqKso3yd_CzSnhHT5aY,32379
|
|
54
|
+
vllm/attention/ops/triton_merge_attn_states.py,sha256=gKRLVpClXSa4wBO3HkFk4OBKtUPaNOUq7oJkKHQ5X0o,3563
|
|
55
|
+
vllm/attention/ops/triton_reshape_and_cache_flash.py,sha256=5sPFCVIP-YZhCAHNYuwG9VlblWoPUd1HykUHpbm5oIc,6020
|
|
56
|
+
vllm/attention/ops/triton_unified_attention.py,sha256=0WV-NO2wOIQiOtemMbAmMAZS7xfEHCboHVlYMvUM8o8,33108
|
|
57
|
+
vllm/attention/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
58
|
+
vllm/attention/utils/fa_utils.py,sha256=mUY49jb7iOVtOZGtZV0mZ0-eZMVq0PdM-j_EfcSqwVA,3192
|
|
59
|
+
vllm/attention/utils/kv_sharing_utils.py,sha256=UsGA1xmBsfJlCrPwFA-28bydHX2f895hTPWzIQ44x3g,1701
|
|
60
|
+
vllm/benchmarks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
61
|
+
vllm/benchmarks/datasets.py,sha256=3O_iYnOrkF8teXbXSdqPRpF879p6T8PbHjWjR4fwxLY,103886
|
|
62
|
+
vllm/benchmarks/latency.py,sha256=OwiM2sNAdWK9NFWoq8kKR5EqbTnPjBeN2rov6jAWJVI,6141
|
|
63
|
+
vllm/benchmarks/serve.py,sha256=Xc-8nLc1RQ2Tmcxl16f-ytjpuEHF9-oPrZDw6wt2jZc,53690
|
|
64
|
+
vllm/benchmarks/throughput.py,sha256=7eHkhlYV5jRMPipalQNLqh5w1L063Vw8B6hnWi6xOPc,28109
|
|
65
|
+
vllm/benchmarks/lib/__init__.py,sha256=BlbNrv7ga0LXYeHLKKiey2woiGh5MkW36g7QG6L6BN0,142
|
|
66
|
+
vllm/benchmarks/lib/endpoint_request_func.py,sha256=88SC3PqQKXzCS2Zn38jE-NQ7aCHTH56mHMUJW_dvH-0,19070
|
|
67
|
+
vllm/benchmarks/lib/ready_checker.py,sha256=kXb2Zg5zPybT_3erJdz9Kofx0bDAl7xtmJPi6Pyf69Q,2421
|
|
68
|
+
vllm/benchmarks/lib/utils.py,sha256=sNpbrvBcediO7xu5nU-WqPdmzDf9KW0QsaERbtDtFX8,2522
|
|
69
|
+
vllm/compilation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
70
|
+
vllm/compilation/activation_quant_fusion.py,sha256=J59wDTSJYEjAL5Ju19sSuS2AIfLk58whoa2Vq64T6ic,7028
|
|
71
|
+
vllm/compilation/backends.py,sha256=QSMpa2wmuGfo0FkjmYauMITUWEG0T50oFn2Yf8FyH10,26281
|
|
72
|
+
vllm/compilation/base_static_graph.py,sha256=BgDM37gRN74A6HunQ8AM1lGAAVGebxJ39VIwGrkeXo0,1980
|
|
73
|
+
vllm/compilation/collective_fusion.py,sha256=0-KZcjTR5Psrs7yvYmruw6rpHGf_R7TLRhAxW-NwyVE,46434
|
|
74
|
+
vllm/compilation/compiler_interface.py,sha256=YRKPS4fxEhJHgvJ75SGptpuNv6B2Rsg_uU9McnQancY,23653
|
|
75
|
+
vllm/compilation/counter.py,sha256=vBHbjJRU8z2Us8uUL6n4jxNesQLuRQrASkCdn1Kxydo,1612
|
|
76
|
+
vllm/compilation/cuda_graph.py,sha256=JrL5b3xOLGVOMC2buzoqsaggycVUYDYzDYYaVzPEzJg,9078
|
|
77
|
+
vllm/compilation/cuda_piecewise_backend.py,sha256=oCBTmpLy6LArUrrrAE3UB0qkE3JyX4pwQ2_NU7Vav6E,4422
|
|
78
|
+
vllm/compilation/decorators.py,sha256=3Rgqia5YFl-lpxy7YBiReUGnDws7IKYVQwcENYhaIkk,16258
|
|
79
|
+
vllm/compilation/fix_functionalization.py,sha256=HaW-vVwa-_sk1AOCDmJZOGKjmLk6pD_2zy42kyLOukQ,9205
|
|
80
|
+
vllm/compilation/fusion.py,sha256=LB8P44WttcbbM6xKzuXLGGaMgKcA_KCtQkwpAX-aRok,14554
|
|
81
|
+
vllm/compilation/fusion_attn.py,sha256=BZ7fcEuI18pZSoR21sgDewoSuzVsA7Aq73uKS1-dc-A,12208
|
|
82
|
+
vllm/compilation/fx_utils.py,sha256=NTw_6bSgwkGsBuCyWfNU-KC8kzd2BOueEQNpD_s69bI,2931
|
|
83
|
+
vllm/compilation/inductor_pass.py,sha256=-eJV4R2z15_NFDT8jwN6SCO93BQCoNoK9Yq-UQVgxWI,4094
|
|
84
|
+
vllm/compilation/monitor.py,sha256=npXL2K-tPC01q0WrUbqqr3mme4HWrk7upPTc_2RzYqk,2065
|
|
85
|
+
vllm/compilation/noop_elimination.py,sha256=k--GCsiybQApj87h-e3ZHuMwIM_gDQJH5zrjJXyIv3g,6182
|
|
86
|
+
vllm/compilation/pass_manager.py,sha256=gqqZZdgY8-sMyYeQFi5uWzY0MsAEE2m886eAbRHKph4,4536
|
|
87
|
+
vllm/compilation/post_cleanup.py,sha256=eVaXynqGXSwczVjLlVlEyPBl6wyAFwDFx6BG9DIYfUE,757
|
|
88
|
+
vllm/compilation/sequence_parallelism.py,sha256=HFh-xlwQV0qbFNkKe8Vx2QlVwdO-ecagw3gLZisplMY,18586
|
|
89
|
+
vllm/compilation/torch25_custom_graph_pass.py,sha256=OTZc1hc3eLlS8LhG4MvHwpglY5_1E_voPW7ShGS5HJs,1430
|
|
90
|
+
vllm/compilation/vllm_inductor_pass.py,sha256=uZ7h7lA0ixljntkSdXixtTwDTVscUhLyIAlUeOtxfe4,5971
|
|
91
|
+
vllm/compilation/wrapper.py,sha256=qVLG5BeUU2uV8Kik6c8iAiDE2RLtUSa8Q-xgSSWPg40,6107
|
|
92
|
+
vllm/config/__init__.py,sha256=TGVKErV8UXk5lUu64KH2YGP73rR9GobV-WXT-NVuWaU,37181
|
|
93
|
+
vllm/config/cache.py,sha256=RqnBnBTYkkW-C5r4H3Sm96VI8nxLXMNuDx1lWQwF7QE,10266
|
|
94
|
+
vllm/config/compilation.py,sha256=ebjTk5y6xju8q8_7JVP-Doqu1OXoJ-y3R0JJWmMMDHU,30370
|
|
95
|
+
vllm/config/device.py,sha256=5buYnT1kssccykBzzMhcSpBO0YpCp1yeJZMsHq1RmfE,2788
|
|
96
|
+
vllm/config/kv_events.py,sha256=r5T4niCkwkJISARBzhANMwctJeM-k8EkWHE2ZFrSvkM,1446
|
|
97
|
+
vllm/config/kv_transfer.py,sha256=3lsnU3h8_LhafFR1NvsVRXWLeoyfH86yhFPt0OxKlCw,3989
|
|
98
|
+
vllm/config/load.py,sha256=MilccTna8lHdLiqRsNCFOV2mDSRQY1buTyVK03BPyCs,5213
|
|
99
|
+
vllm/config/lora.py,sha256=Lak9ay1x3lNNUtk-IgDN-pNoDND8xrY8cA0EuU5idPs,5596
|
|
100
|
+
vllm/config/model.py,sha256=zcVu_eiAA7OZIEEoyXCGuo7Qa3EX4uEszb0HC4iS02I,82694
|
|
101
|
+
vllm/config/multimodal.py,sha256=N2Dk43dU4mpVQuNCQ9_y5ADHz57sZKwfDaIpV7qWtNg,5412
|
|
102
|
+
vllm/config/observability.py,sha256=hBGvI5xwFUaIZ7PuVLWlpPQWEGoTAZ33I9bioS0ARgM,4124
|
|
103
|
+
vllm/config/parallel.py,sha256=M97zu0bOEKQ9882Xh5pCmbJeSL6s7t6CA-GUHEPEFeE,24252
|
|
104
|
+
vllm/config/pooler.py,sha256=1kkwa6brekecSnwTDcq3lP36YAwuoQlvXMVukaM1OCw,3344
|
|
105
|
+
vllm/config/scheduler.py,sha256=GLYVNXeOiOsD1N8ipGR6kQH9AT5GbdpZTBl8YY6lt00,12737
|
|
106
|
+
vllm/config/speculative.py,sha256=3AJanTAC6Ac3BGse_bxKcKXwvF0RkQSzEXwT7AM6h-0,26443
|
|
107
|
+
vllm/config/speech_to_text.py,sha256=sMHc2IfZ-1zGlNeBhD5j503yLq9Jyj9-6lQ8tQJixP4,1493
|
|
108
|
+
vllm/config/structured_outputs.py,sha256=n0XGfcJ3TnLMRuKsfop3lT32T2fJD4OvQsEO22uDC_M,2885
|
|
109
|
+
vllm/config/utils.py,sha256=PHfuI_WsjIeOniJiZQbiHA4NbI1GuVHzo5MP77i_DiM,4831
|
|
110
|
+
vllm/device_allocator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
111
|
+
vllm/device_allocator/cumem.py,sha256=rvcfVkDUZr-UUrVRqzxfcNnphY84EFquSQfKwZQeBUI,12505
|
|
112
|
+
vllm/distributed/__init__.py,sha256=l_KMMLMmYq-MqxY5OeTuQjA38RYwdS4TtVy8JafQq3E,191
|
|
113
|
+
vllm/distributed/communication_op.py,sha256=igCBXNoAhJ8eZooR79KhpzgYlVP1TUgnPF5C7BSpSJE,1562
|
|
114
|
+
vllm/distributed/kv_events.py,sha256=IyzLUC18jtO25Vt9wN1tgrTGuqhjfhCGK3HSYNyPBPI,12540
|
|
115
|
+
vllm/distributed/parallel_state.py,sha256=mnj7KNOAtaGIoaxiei5od8rLGFtHtAtdkofi0fCvok4,60471
|
|
116
|
+
vllm/distributed/tpu_distributed_utils.py,sha256=OOCkNrzouRGPCot0UMVeQPKSbBhXZnNaaRz1c6VKimE,7827
|
|
117
|
+
vllm/distributed/utils.py,sha256=K2CNfdyDZChfy6QWoMx-n6pDzbG8X4SBmdutEnhPNqQ,21012
|
|
118
|
+
vllm/distributed/device_communicators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
119
|
+
vllm/distributed/device_communicators/all2all.py,sha256=ocNYhZ5ZXVVUPwRD15-GDHR2MPZKtWpX3DU5pazhD9s,15448
|
|
120
|
+
vllm/distributed/device_communicators/all_reduce_utils.py,sha256=CkDiC5kJ1NCBtQ_LnfNYeW6lQlZrp7i9Qni6Wds6lvc,12223
|
|
121
|
+
vllm/distributed/device_communicators/base_device_communicator.py,sha256=Mi0aqJ03tepnJBgF9jsMb6aGTO9fjMa3PJAtsmcXRVg,11404
|
|
122
|
+
vllm/distributed/device_communicators/cpu_communicator.py,sha256=WsVwXfEcvKUnr1mdXIVMWicUDjT0mOywRc7VqvLK7kw,7526
|
|
123
|
+
vllm/distributed/device_communicators/cuda_communicator.py,sha256=prcL499TcC_BCtfrSkdlrhoHiYhGqyzSExbBG0Dk4fM,13915
|
|
124
|
+
vllm/distributed/device_communicators/cuda_wrapper.py,sha256=1I1OZOc9-St5Zlr4gUmoDm7HxdS-T9ZE1ixOJGJK55s,7185
|
|
125
|
+
vllm/distributed/device_communicators/custom_all_reduce.py,sha256=oGX3FYfd7sUWbe63Ho-hTDybnX2pWHT4LIwIlON-s60,13095
|
|
126
|
+
vllm/distributed/device_communicators/mnnvl_compat.py,sha256=ok8wHrWvlVpSV5Nbyo0NczcKtN_sqFLZopY2Z_ewEhU,831
|
|
127
|
+
vllm/distributed/device_communicators/pynccl.py,sha256=4Xk70Vdw3yRja9vtVDblIGiXr9dPXDfpn4D4teT3lJU,13729
|
|
128
|
+
vllm/distributed/device_communicators/pynccl_allocator.py,sha256=FjethTxZGHPCybHl_-Jq_kmrDWXVSJmaHWiWhqYJLuI,6247
|
|
129
|
+
vllm/distributed/device_communicators/pynccl_wrapper.py,sha256=utZzjJap0LF50WE_JtjPfANEFj1WET_5ha-Ptyb_bFs,16969
|
|
130
|
+
vllm/distributed/device_communicators/quick_all_reduce.py,sha256=-TnB_helsIyosJoUMdIg7bfJKe6AbKXQPBjxirHMLtQ,10886
|
|
131
|
+
vllm/distributed/device_communicators/ray_communicator.py,sha256=MCrdpPjXpwsMwev4JHrjx0RxylqAjsom8XOXJuRNUNs,9172
|
|
132
|
+
vllm/distributed/device_communicators/shm_broadcast.py,sha256=W5SLJGiXps-FDgjviyJeS8ZmctpcSsxLD5NxEUHoTEs,25338
|
|
133
|
+
vllm/distributed/device_communicators/shm_object_storage.py,sha256=XH5ML4Iw_8yxRXk-qORfpsZIoP0S3sDo9ZE2FVhoPr4,25771
|
|
134
|
+
vllm/distributed/device_communicators/symm_mem.py,sha256=WbkQyerbeoOba7XMMulf4AxdvIguYD0SBVE0K1PmUKE,4878
|
|
135
|
+
vllm/distributed/device_communicators/tpu_communicator.py,sha256=dIWViwqW3r-7C76aYzkFV6VquFv1dtBGiwDpuMtAVrE,4251
|
|
136
|
+
vllm/distributed/device_communicators/xpu_communicator.py,sha256=lim9qnf60lMigMgndnEAHzhGDM8zXZTFhiUq3L8j3E8,3796
|
|
137
|
+
vllm/distributed/eplb/__init__.py,sha256=iDRi-3lUn2DaLMC9aCQ1xdvvLrRNpT1YFieBjVnYKr8,213
|
|
138
|
+
vllm/distributed/eplb/eplb_state.py,sha256=UnIV6JixTMBU68r9Nb0YkswbcQBHeubxZqye_p-leiQ,23249
|
|
139
|
+
vllm/distributed/eplb/rebalance_algo.py,sha256=_oNzKehngRxhfEP-u71DJk6exmnG7AvO3cpIigzi1_w,9114
|
|
140
|
+
vllm/distributed/eplb/rebalance_execute.py,sha256=xpM7VBgya6q9kJuMDEv1YNc1E2KvTgPYQlE-2VatrvU,14997
|
|
141
|
+
vllm/distributed/kv_transfer/README.md,sha256=cKIw6vXYSxBlf0wWwO7haP82CX2oB2QzW0-RxZE5mT4,2007
|
|
142
|
+
vllm/distributed/kv_transfer/__init__.py,sha256=Ahm9bFQ6fpDLzOzgx2pQq90i4o5OUu25_hYKE4-PHwA,525
|
|
143
|
+
vllm/distributed/kv_transfer/disagg_prefill_workflow.jpg,sha256=fOFUEx-2Fm1uxHCGopvCREaRqdvR87Z7C0bMqEVH3Iw,142656
|
|
144
|
+
vllm/distributed/kv_transfer/kv_transfer_state.py,sha256=UHvTyR3qsB6qEuR8zJ5lO7nF31RYGPhjIfCoKRRb3WA,2294
|
|
145
|
+
vllm/distributed/kv_transfer/kv_connector/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
146
|
+
vllm/distributed/kv_transfer/kv_connector/base.py,sha256=KuKixI9XMfNTMWanVED-kedkMyMFtdcT34QO26lweJ0,370
|
|
147
|
+
vllm/distributed/kv_transfer/kv_connector/factory.py,sha256=P7cBpmOHdDO6vDW93QKlnW54kLMmoDpKrzG-vZlBBQg,4153
|
|
148
|
+
vllm/distributed/kv_transfer/kv_connector/utils.py,sha256=j-iEtMf-2U6IzfXAhIrKQn9BnP6Cndv3nb_o_esHgWY,10712
|
|
149
|
+
vllm/distributed/kv_transfer/kv_connector/v1/__init__.py,sha256=Vgcn88rEfiLwJ3-YkZKWsvMurr-vsV4_47b9_Mv-vlo,265
|
|
150
|
+
vllm/distributed/kv_transfer/kv_connector/v1/base.py,sha256=VsQo-B7PPgsVkP_8GkX2ykfJpdXo2pNU90xAFlxUQEc,13836
|
|
151
|
+
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py,sha256=wP3ZUU9HrEqb7dpejhRlhZNyZgrIkKPFdwoSvE0KA9s,6546
|
|
152
|
+
vllm/distributed/kv_transfer/kv_connector/v1/metrics.py,sha256=yzPXTKtKTfJO7sPhYWvb4vYF0qCO4WFNH51ytY_7UTQ,4028
|
|
153
|
+
vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py,sha256=Nb6oJailbaKc11qCtr7wZG3hvvGBS8dluW-LTs3R1b4,13288
|
|
154
|
+
vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py,sha256=FHblPQ3e-TgfYp0Qs-IRZ_2IlfFTn7oa70h12G4FPR4,66248
|
|
155
|
+
vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py,sha256=IW55ZWsTYUpF0QlzMrqE5J-nWsRtNtKhtfBiCCmElg8,19578
|
|
156
|
+
vllm/distributed/kv_transfer/kv_connector/v1/shared_storage_connector.py,sha256=r_LozRs-CZ4OdGyQb2wFeJw-NC9tPW9Rnb6pyOg1kUQ,17102
|
|
157
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
158
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py,sha256=xJYEBCxSNvfOsUqPCpuB_JeSH840nOpKuI6ZY8omwbI,18822
|
|
159
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py,sha256=yvTrHN7HfrkLM99CKW3R8jhGEnNgh2TKwMMv_pZv3qE,22221
|
|
160
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py,sha256=AUiY6TIyqJ1SyH6N1KTVm5jsm79kxMo1y7L3vAfwIUY,9451
|
|
161
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
162
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/base.py,sha256=ZZYJZBDDny_StDcmXUFwOtDslRrTCL9iSUcr8XWe08g,6280
|
|
163
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/mooncake_store.py,sha256=atXfrR3n4MZAB88TtNmVAC5Gn9FhyVFcVRO1VjjL4uA,5679
|
|
164
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py,sha256=m8XNP5UiFwq2g33f3fiJeLMu87OhKwSvjWcI2jppztk,9156
|
|
165
|
+
vllm/distributed/kv_transfer/kv_pipe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
166
|
+
vllm/distributed/kv_transfer/kv_pipe/base.py,sha256=FHfg3C53oZjBBZjEWHmxMOPKTvJitfBOXXFzh8j70cU,2156
|
|
167
|
+
vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py,sha256=_yti48_vO7pZ9VxyLNr9AuzQRJi16-SBebDdlWotkAM,12402
|
|
168
|
+
vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py,sha256=tEXGnAOiL122p9cvUUuOiSozR7RjmCgEOQ_GMKRBig0,9727
|
|
169
|
+
vllm/engine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
170
|
+
vllm/engine/arg_utils.py,sha256=Ijit6HK190eDMPqcoSFDiVIOCJkVggkOPgPi_qvPlaw,82435
|
|
171
|
+
vllm/engine/async_llm_engine.py,sha256=B4Xf26qGXnF7yc06F_OM2CH8k5CLUU34tjUEafnIg2U,197
|
|
172
|
+
vllm/engine/llm_engine.py,sha256=h0FBz_1vf8ThMr1PHUQVus1sEQH-N8XZsiQwNZrs1W0,212
|
|
173
|
+
vllm/engine/metrics.py,sha256=u1b02I981lRv_qC1TD8OfPL-0GXWREXXlrbTPz_FiA8,24295
|
|
174
|
+
vllm/engine/metrics_types.py,sha256=MKvHu_x4U0ZVvDv5KTmIRTfMuHhCqkPNPqGX6ISEgrQ,2737
|
|
175
|
+
vllm/engine/protocol.py,sha256=s36F69y6kS3WenIV0_Yl6tBylXl6BRnbwxiod_9Deh8,12024
|
|
176
|
+
vllm/entrypoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
177
|
+
vllm/entrypoints/api_server.py,sha256=F1c5uZ-WFzmNtrpSH158bOzv6p623tmY7gimPZiwMGY,5818
|
|
178
|
+
vllm/entrypoints/chat_utils.py,sha256=vdhiITXc4nm3kPXpcBjtCvv2NfdF1xWGmUBpX9yTD84,57739
|
|
179
|
+
vllm/entrypoints/constants.py,sha256=ZX2zFNKkQjQM46StHeaSFaQIJEToSYcyJ7EBr98ZpWs,335
|
|
180
|
+
vllm/entrypoints/context.py,sha256=2oXqpPua334QlmSGbGrzyeWYGiWUrsfWdMrAe6HTa2k,19559
|
|
181
|
+
vllm/entrypoints/harmony_utils.py,sha256=VujETkVdkbES8MijhUtIPIpYg-iN6X6OetV82NnwUlw,17415
|
|
182
|
+
vllm/entrypoints/launcher.py,sha256=Gw4JGUID1CnzCFi-Ej4HqyWPQVaFkHPvCaCRFVvgGMk,6057
|
|
183
|
+
vllm/entrypoints/llm.py,sha256=7koa6Qj24EuCLI71W7Hs_4mngc7pCUSj2YnoUoa2SJo,73189
|
|
184
|
+
vllm/entrypoints/logger.py,sha256=-2pe5uquycCb6BR9gsCI1MBfuGmVSZ_nhfFj8huMoxo,2527
|
|
185
|
+
vllm/entrypoints/renderer.py,sha256=Py0pGIcjbffvclw7lQpqu9y16QIAqywW4_gbMikPYIA,15287
|
|
186
|
+
vllm/entrypoints/score_utils.py,sha256=xAIWZww6Ual6cOeqaWhskza2MVvuJn2r35s5QZ8t5D0,8009
|
|
187
|
+
vllm/entrypoints/ssl.py,sha256=2InxP04Dt_I84ORXewngn5cUdXvRkrK_zZB6o8Ng60k,2805
|
|
188
|
+
vllm/entrypoints/tool.py,sha256=twgXy0yY2t1Cvx9YlUmvVJu0phNxEPLqYda987RA7So,4552
|
|
189
|
+
vllm/entrypoints/tool_server.py,sha256=d-qd88-wEJ7k1KuQm7NemJuRz5ewqPwBmIovs8wSQy0,7223
|
|
190
|
+
vllm/entrypoints/utils.py,sha256=WX1NPF1QrFBugUFootVgyhQZUXMBg5w8q-1HgdL6yaA,9732
|
|
191
|
+
vllm/entrypoints/cli/__init__.py,sha256=GRsSDBSSOHMLZfY8jjf-h5gFMOaOaicDAgcIGCVZdI8,482
|
|
192
|
+
vllm/entrypoints/cli/collect_env.py,sha256=GebDsiNF6qvxWrzz8RaQdOnHZtFeoDnNGCMrSvq5krA,1069
|
|
193
|
+
vllm/entrypoints/cli/main.py,sha256=hksvxYeLjOkMwRUwFzLewd_1J9h4ziQwzbm63AwLLwc,1791
|
|
194
|
+
vllm/entrypoints/cli/openai.py,sha256=VKjuDF47auLtkT_WWfgVXlm-P3XROPo6Wbb7QVi1pPA,7909
|
|
195
|
+
vllm/entrypoints/cli/run_batch.py,sha256=yufW0Mdr654Ca_GM2VjLDGwStxMk5bdpnm2EGY_frEw,2225
|
|
196
|
+
vllm/entrypoints/cli/serve.py,sha256=7Zf__aZOgTpN1ypkMrX-H_U1YaloZVwRf3-lJm_WImE,8835
|
|
197
|
+
vllm/entrypoints/cli/types.py,sha256=horNt6_2wEsuLNQ1-zoQ3BWsMkvMxJAxcTC-eQS4O1E,785
|
|
198
|
+
vllm/entrypoints/cli/benchmark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
199
|
+
vllm/entrypoints/cli/benchmark/base.py,sha256=r1QkRTjaUCcjO78Zw9zuDeRhMdaGw22N3hqO8kgrOsI,674
|
|
200
|
+
vllm/entrypoints/cli/benchmark/latency.py,sha256=MYxv7pF4kq6StJN5uZYxOm51lIHfNyvMIvXU--szia4,653
|
|
201
|
+
vllm/entrypoints/cli/benchmark/main.py,sha256=VwRzcIjAHRtkrkiDFOG4X2iBPRwvleQ3I3qqpyJzrcs,1854
|
|
202
|
+
vllm/entrypoints/cli/benchmark/serve.py,sha256=izuara3nwC64MtoealX_FzR9cB6u4YQv0fDikj-VdNI,635
|
|
203
|
+
vllm/entrypoints/cli/benchmark/throughput.py,sha256=YN5PAz4aDjxXkao1a_RjrR8hLGzzjYPecO_OIp1TVwQ,652
|
|
204
|
+
vllm/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
205
|
+
vllm/entrypoints/openai/api_server.py,sha256=lSlxho3kLH5rvWKDIQ2s_YXYDh4uIoWhg3RMJ6au85M,74835
|
|
206
|
+
vllm/entrypoints/openai/cli_args.py,sha256=HkyTKM14bKGLRqy7lgTT3aZDCAHLl-5uXVpj5IYcTW0,13062
|
|
207
|
+
vllm/entrypoints/openai/logits_processors.py,sha256=QAJn3DMAfFySExoA5aaSNVjXwtlOXGCv1DX6Fltj2ZY,3230
|
|
208
|
+
vllm/entrypoints/openai/protocol.py,sha256=FfGg3pwov7IHKmi6ttZvM0mROZMRg5L7N6GPIZelTto,103648
|
|
209
|
+
vllm/entrypoints/openai/run_batch.py,sha256=WjxXJFxQHc79Ti1S-1ZDxS_0cYAltaLBtQtPuFu1EBM,18543
|
|
210
|
+
vllm/entrypoints/openai/serving_chat.py,sha256=oSP2cCg3wQYdvaia3pinwEs0-O14fdjHJNfu7uLHjwY,76032
|
|
211
|
+
vllm/entrypoints/openai/serving_classification.py,sha256=AZS96bQQsCNZ0MHGWpw6Jx0pjoVkGPq53rtE7vzM0JE,5855
|
|
212
|
+
vllm/entrypoints/openai/serving_completion.py,sha256=2bdR0R05Hnzi6A5mLVpbvWzbTiWTrj4EfciyfFlg-zQ,29777
|
|
213
|
+
vllm/entrypoints/openai/serving_embedding.py,sha256=_LiCsJHqzQFwZOnqfVY6vjaYphuPl_PeyS-JKDo3738,26134
|
|
214
|
+
vllm/entrypoints/openai/serving_engine.py,sha256=x9bln1AwGpbyzFBG3I9s3D6zTTzYbNIjQMshGc1K9ik,36592
|
|
215
|
+
vllm/entrypoints/openai/serving_models.py,sha256=s3pgymW5GFPRSloTErKzX0ed90_SElhYhclkh5nMLg4,11558
|
|
216
|
+
vllm/entrypoints/openai/serving_pooling.py,sha256=Nh4HQbpB-lczdu-IJbTfDN9lR4eVzmszq7YWP78mHTc,10767
|
|
217
|
+
vllm/entrypoints/openai/serving_responses.py,sha256=9RLbMEadW95b9L-4U8FmP1LqNYlRjyTDDUsMHhrQg8Y,78208
|
|
218
|
+
vllm/entrypoints/openai/serving_score.py,sha256=xF8dbChpt8SY-jKXlllt8yr5QSrSWmC8OiZiQK-3-84,17956
|
|
219
|
+
vllm/entrypoints/openai/serving_tokenization.py,sha256=8IoQ10egc8E59DYGWcs0AgoZiQy8y0RTeG8yLtO8FMw,7618
|
|
220
|
+
vllm/entrypoints/openai/serving_transcription.py,sha256=gNGsdcznBTwf2Ij3jwxlKnPKfX0WSviMIUQJzKersGY,5600
|
|
221
|
+
vllm/entrypoints/openai/speech_to_text.py,sha256=avKA7WZPF5NuqVQikQ4P3D1V8KvTewElLcZLzBXRZdE,16436
|
|
222
|
+
vllm/entrypoints/openai/tool_parsers/__init__.py,sha256=UNs0p-7xvA84WFNeESXxOZIL48ADTfsYCWTh3aHym1M,2088
|
|
223
|
+
vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py,sha256=UyO8engPSTh8Ej8EuQay-mDz9YPzHAsmzJA43-4vmq8,6095
|
|
224
|
+
vllm/entrypoints/openai/tool_parsers/deepseekv31_tool_parser.py,sha256=E7mOfxtT8B4cN7neTb59Ta7v4W7LTkPj5f6ktrE4I5I,16524
|
|
225
|
+
vllm/entrypoints/openai/tool_parsers/deepseekv3_tool_parser.py,sha256=Tgr__jUTZFKNbX5JJ7GM_aI4yyOTtSsXdRy2g_It5mI,16688
|
|
226
|
+
vllm/entrypoints/openai/tool_parsers/glm4_moe_tool_parser.py,sha256=dmRFoDMlYZ819f3Y0GGRq-oGlzZIjmi2Xh7Dy1REcHk,7881
|
|
227
|
+
vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py,sha256=JUDqbsw7CAMDSFqViqCio1fiAttQxf8VNmpZet_4WV0,11498
|
|
228
|
+
vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py,sha256=biTD8_t7Hg86-rksZb7qm7Yj3ovbYohUIOJzq6_9cF4,10719
|
|
229
|
+
vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py,sha256=BCtZ7lXnCP8aC1c0ynF_hizpeOrcFiw8F3jqFcnTKBo,21096
|
|
230
|
+
vllm/entrypoints/openai/tool_parsers/hunyuan_a13b_tool_parser.py,sha256=PaIJ3YqCz5h-QSlCWiAMSDzrHV5GEQvSi7g0sTLVewo,16238
|
|
231
|
+
vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py,sha256=qELeSPWN0h7lSuUNMhcnaJSjBR16m9sXFIgIQHyxZ0k,9460
|
|
232
|
+
vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py,sha256=3B7JF2J6CQ-pW-QPusclBAXHjRYpXIkdK_6tG-9P5Go,13943
|
|
233
|
+
vllm/entrypoints/openai/tool_parsers/kimi_k2_tool_parser.py,sha256=TIXaxhjXo6C-aF3oYG_p42-yLKeK6fISInZME4Om9sA,17076
|
|
234
|
+
vllm/entrypoints/openai/tool_parsers/llama4_pythonic_tool_parser.py,sha256=BQ0YsnJ9-bLFmAvc-GCjNkXZsx8Euc7PMBVDh6maiZo,13257
|
|
235
|
+
vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py,sha256=pJ63Xb6B4zitFeYPVXzjf4ZoGBOlog5EtJY3tn_nHcI,12505
|
|
236
|
+
vllm/entrypoints/openai/tool_parsers/longcat_tool_parser.py,sha256=FJaQ-y22FpFq_jlnL5D7yf_Yi6EX4YaWLrvChOkHQBs,1443
|
|
237
|
+
vllm/entrypoints/openai/tool_parsers/minimax_tool_parser.py,sha256=ZKChv22q8JaS9bM4KuWhlpZIuuAwMBaBSLKuNHbHieU,29330
|
|
238
|
+
vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py,sha256=hb63cYdfoWNUJ2Igyvi1h-d9peONMBmd7gaX-LKD7SA,16545
|
|
239
|
+
vllm/entrypoints/openai/tool_parsers/openai_tool_parser.py,sha256=OYLFEoDMJ6QUQCGuTEZaKrJ0ksXXEaEPtNALVpBp62k,3603
|
|
240
|
+
vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py,sha256=ul0h98fxIIgo8Ugj4NA5Vh5atgl40CvfIypVHL3IAmQ,4342
|
|
241
|
+
vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py,sha256=yXO5XGgV1j0QmyFoaYGLeUrD0R5XrvV9yLfmu_HYLLM,12635
|
|
242
|
+
vllm/entrypoints/openai/tool_parsers/qwen3coder_tool_parser.py,sha256=XbuLexCQQbTITBnMB5phgSOKyRqs-FV-yDLZBD3u7W4,32119
|
|
243
|
+
vllm/entrypoints/openai/tool_parsers/qwen3xml_tool_parser.py,sha256=3lEYsUlAStu9vRMWcedhlQNL7ov0XfSVMugR2_p0mUQ,49075
|
|
244
|
+
vllm/entrypoints/openai/tool_parsers/seed_oss_tool_parser.py,sha256=XZOOXDXeXjgjBfrojFpIu1yEpS19SEYFE_7Skkv32_I,30531
|
|
245
|
+
vllm/entrypoints/openai/tool_parsers/step3_tool_parser.py,sha256=fgfd05Xflm6fuxMiqF8xh5yAotXudTfAsEaGhbYi7nM,12512
|
|
246
|
+
vllm/entrypoints/openai/tool_parsers/utils.py,sha256=RrvMsSpaYYMPefvM1ktVKzo9Gs5KsHpi21QaP1h4EKU,3874
|
|
247
|
+
vllm/entrypoints/openai/tool_parsers/xlam_tool_parser.py,sha256=zzp0l-1cIREuCHDy0Cn0aZIgfJN1JOTvoM03i5coUEQ,24599
|
|
248
|
+
vllm/executor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
249
|
+
vllm/executor/executor_base.py,sha256=AlIYB4P6qp_AVhfjNhpQXxr-KjXU2bBUxx49Sp1Yt0Q,15191
|
|
250
|
+
vllm/executor/msgspec_utils.py,sha256=Mq3r85TXhqff3ljqOzlnGmIj3gmOaGNFQor6ugyzW_w,1209
|
|
251
|
+
vllm/executor/ray_distributed_executor.py,sha256=WqVuvOQ4PiU8bF9sbmXDfq6LoGdHD9a--4FsfVqViY0,30992
|
|
252
|
+
vllm/executor/ray_utils.py,sha256=je_lfNCYC5vfPqx2IHagjxF7OZA9QI1Og1jCSRBoByo,17475
|
|
253
|
+
vllm/executor/uniproc_executor.py,sha256=-NK2c7URLFwnoYwprxEvrIrEGfRhqr8qvp1KRMgEOlo,7227
|
|
254
|
+
vllm/inputs/__init__.py,sha256=09rzGxoQW2nLN9WfHebfZTqKGVDsLOl4Vqn7n1TncvY,979
|
|
255
|
+
vllm/inputs/data.py,sha256=ZlEZFdCUy7lj2Xoh8aKHIN5NiavLH4jRuTtLxz1Yrpo,11733
|
|
256
|
+
vllm/inputs/parse.py,sha256=_Lbf4PQyczm3OPsLgvyPf3CiKGNP1Ctd4bW_AnuORpk,4499
|
|
257
|
+
vllm/inputs/preprocess.py,sha256=NHofOufog8zymZJ_wWja3ZGyB6CxjDIZE6KQA3mYelc,24271
|
|
258
|
+
vllm/logging_utils/__init__.py,sha256=MU0sAgeBaQM4PJW5VAFq2WsnszAGljJ79cCmXvihA0c,268
|
|
259
|
+
vllm/logging_utils/dump_input.py,sha256=g9nr91If5qsBTNXuKD9FeCOs8Z9N4zsj-kMpJISODKk,3071
|
|
260
|
+
vllm/logging_utils/formatter.py,sha256=Yi12ADzbS9tI3J_pFhTevzYb6zFVgs4JQZI6uIY64_M,2847
|
|
261
|
+
vllm/logging_utils/log_time.py,sha256=bAlfYkIc5OC7WXA_BCLarWcWEN7UcqNeMEWdRX7Uz7w,819
|
|
262
|
+
vllm/lora/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
263
|
+
vllm/lora/lora_weights.py,sha256=euJ8f04c8osKtaM06fOkF1982I43w6w5_v4uSR3W-Rw,6294
|
|
264
|
+
vllm/lora/models.py,sha256=ZpSD4PIMSavpX3GbYLiZKntReM13KxGFBYVmOFZxnXI,35031
|
|
265
|
+
vllm/lora/peft_helper.py,sha256=H9FY8VNaxEkKM-BjBsw_z1g8jDI2NSmFy6N4--LjDWo,4871
|
|
266
|
+
vllm/lora/request.py,sha256=JLxCPuMt2aPaMqOnNDfxyd5K4PrFJRkGiUi6Zz8PZwk,3190
|
|
267
|
+
vllm/lora/resolver.py,sha256=6iZpDMfxWGcy8MWlj3nCCcVmgr6nKs8EzzOhaN4TiCs,2881
|
|
268
|
+
vllm/lora/utils.py,sha256=VwuKftS-kwksgBYN-ACC40SuP-KHtO2a8RVqMSoWd_w,9413
|
|
269
|
+
vllm/lora/worker_manager.py,sha256=-qgHAt1BjJIw2m0E8WcQmLo4sXd7DesjRSrPauhtHq8,11295
|
|
270
|
+
vllm/lora/layers/__init__.py,sha256=tE8Jprt4oSDFBvhCL7ydkKZrszspefYPdxNqfgvHv2Y,1471
|
|
271
|
+
vllm/lora/layers/base.py,sha256=fN0rPYPWhz-Udi5dnRB_j6J9Uo9CIULm_JkYsUWK1Ic,1944
|
|
272
|
+
vllm/lora/layers/base_linear.py,sha256=8wHQ-CwIFJUYLuTp8AdnwLBOSM5QATb-sdP6aF3ugtc,7130
|
|
273
|
+
vllm/lora/layers/column_parallel_linear.py,sha256=8FDnmhEycQf6x-9McHGPP4sHWCAt3vx7seq6iVDHWFM,23021
|
|
274
|
+
vllm/lora/layers/logits_processor.py,sha256=WVK8eN_JgZF5GhvYBzvU4_DLkOq4seT1iTTdspJs1H8,8533
|
|
275
|
+
vllm/lora/layers/qkv_x_parallel_linear.py,sha256=inUvsOTycDKUXpbQiZ_i34PhW1qeYNCDjeh58c3boLk,233
|
|
276
|
+
vllm/lora/layers/replicated_linear.py,sha256=GIPH07e9fJWeSnCXtQuTTB26MLUlsGAzzQJhNPTeTEA,1821
|
|
277
|
+
vllm/lora/layers/row_parallel_linear.py,sha256=Wn65lLrRO-jfBhdbWpbgvUe8pyYJXVUlg8Gm72OoJ1Q,6937
|
|
278
|
+
vllm/lora/layers/utils.py,sha256=-0AFacCkJtSRllPQ6b9I7ifuKvGm7lSb2mgooUbz6Oc,1980
|
|
279
|
+
vllm/lora/layers/vocal_parallel_embedding.py,sha256=SB5xGD7SCWmthluwJRuSFi8ZzHKUjGjK7ztxfSCwDlc,6544
|
|
280
|
+
vllm/lora/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
281
|
+
vllm/lora/ops/ipex_ops/__init__.py,sha256=BGJ5bmli1rUC-Bc-vKw7zC4GHWeJu_vFetmC-sUo1_8,306
|
|
282
|
+
vllm/lora/ops/ipex_ops/lora_ops.py,sha256=MRGhU-LHiQhWXXRW1ZB9jklfkYV6WY4OGnAVANZYat0,1593
|
|
283
|
+
vllm/lora/ops/torch_ops/__init__.py,sha256=ywu1d5miStgp7A9BRAo6kUvuE3AcgOAOJHxYHD4cKvQ,535
|
|
284
|
+
vllm/lora/ops/torch_ops/lora_ops.py,sha256=LOSdfKpQM365cIWVkyElcLpfgn8cF44IVw-KUN2NMKs,4517
|
|
285
|
+
vllm/lora/ops/triton_ops/__init__.py,sha256=arDrNt_kvrDaC4mN3RNbu6-0YACXQRp9Md2cJxXI1ao,384
|
|
286
|
+
vllm/lora/ops/triton_ops/kernel_utils.py,sha256=3P-CWMjNQR2vp3QUNynjXAIaWQy06mEFDTRLRQljDME,8509
|
|
287
|
+
vllm/lora/ops/triton_ops/lora_expand_op.py,sha256=NjcFCu8dg8bMXsTEh5qketmeGY5b7EsFg2Acxz7i6bk,8963
|
|
288
|
+
vllm/lora/ops/triton_ops/lora_kernel_metadata.py,sha256=mY4MuD0if25DX-f46YOXslxSH1-9gKqekA7slSWRBW4,5989
|
|
289
|
+
vllm/lora/ops/triton_ops/lora_shrink_op.py,sha256=weJc-QbIj57DODvnjBDp1s4hh8VxoLF9pU4qHz8m5Y0,7994
|
|
290
|
+
vllm/lora/ops/triton_ops/utils.py,sha256=Ljg-GwRcsGZruXe3fsdqu8RE2rZDOTd4duH4a2nPW4c,5216
|
|
291
|
+
vllm/lora/ops/xla_ops/__init__.py,sha256=2Yh5hqiUt7hGz9SwznSZlj-_G7-SknTauNyHGDcUjBY,304
|
|
292
|
+
vllm/lora/ops/xla_ops/lora_ops.py,sha256=Uibo6XBhRclQh2cVU8OQJXEmDxYG-xt_opLLsNcHGM4,4324
|
|
293
|
+
vllm/lora/punica_wrapper/__init__.py,sha256=A5cDJmdCPRBN23kwLfemRlWI4YA-t_7qIxeoeimCkT8,313
|
|
294
|
+
vllm/lora/punica_wrapper/punica_base.py,sha256=buFvKbdfl3bJcyJKiIIpnpE5mTunBfsMIMnCLjbU0Xo,17298
|
|
295
|
+
vllm/lora/punica_wrapper/punica_cpu.py,sha256=sFBBu_qBEL8LGALamK7hE1ympyipYNT4qpav-V1nllU,12527
|
|
296
|
+
vllm/lora/punica_wrapper/punica_gpu.py,sha256=cfrSPXJWsUs37qTAset8c6FKEughykIS7wxm0aiwRh8,10209
|
|
297
|
+
vllm/lora/punica_wrapper/punica_selector.py,sha256=Of6p5uYMMLnA6g46VK7M3xJT8Xq4q1VFoeOpTIsPf3s,799
|
|
298
|
+
vllm/lora/punica_wrapper/punica_tpu.py,sha256=ueg200f9ZO7oLa3zDa9AcoAHqQGwcHWgYtBAkjjYom8,15561
|
|
299
|
+
vllm/lora/punica_wrapper/punica_xpu.py,sha256=abBmR7Dnr7tGYBN_ZJ7TYnyV5GjYHn962UsJAUB_aS8,10427
|
|
300
|
+
vllm/lora/punica_wrapper/utils.py,sha256=bBA7sN1SI2lw48b8TJLt82gwmgS69NSNDxdb2vzRRsY,5568
|
|
301
|
+
vllm/model_executor/__init__.py,sha256=TRJkRE9TvFAg_QWpDg-bOblQg9YmAnUpheiljHk235A,378
|
|
302
|
+
vllm/model_executor/custom_op.py,sha256=Wmk_LAbhh0T4XUuZFfvoiqctSdUd6bkdVik7X7MdYFQ,7532
|
|
303
|
+
vllm/model_executor/parameter.py,sha256=ndB7SdRBS-eRKQA7NCsFS7uOFL8q2yu0ECJvZCCVLuI,23542
|
|
304
|
+
vllm/model_executor/utils.py,sha256=o4L0hUcm3UEcntn4IRcbcp31m7STpmoYD2TGqkH4gL8,3227
|
|
305
|
+
vllm/model_executor/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
306
|
+
vllm/model_executor/layers/activation.py,sha256=WlFMeC4fXe3DJmqJKlAAPRAsSrXkqjanab784sBy7mg,20611
|
|
307
|
+
vllm/model_executor/layers/attention_layer_base.py,sha256=bDN8w5Suq8j2C7xOG-xc9dS3XMfpqOphWPMKazGxEVo,715
|
|
308
|
+
vllm/model_executor/layers/layernorm.py,sha256=h4rgnAmlSjVlx0CpkySUa5nmCBDugpe-mFCVF1m74CI,12605
|
|
309
|
+
vllm/model_executor/layers/lightning_attn.py,sha256=PLUhvCJT2-ujjnSPfZ6AXK33V66Z3Eruuy3FeJZHYCY,21156
|
|
310
|
+
vllm/model_executor/layers/linear.py,sha256=ssw8sY0WGXapV_C3CvMCKRuqZqrtmSKUl2dPJm4arE0,69055
|
|
311
|
+
vllm/model_executor/layers/logits_processor.py,sha256=PcLrhSaw7Emq45MCLbSI2SIL4_pQeJPR0b_5RCUptW4,4029
|
|
312
|
+
vllm/model_executor/layers/mla.py,sha256=tQnwIwNW-FHvdSBwYnOCxUG6J1e36cbmit0zZxYjaLE,6481
|
|
313
|
+
vllm/model_executor/layers/pooler.py,sha256=GiMDeduQ6MboL6TmSdeuEtz8AxcF2ye6A1TjIfYxFRo,23584
|
|
314
|
+
vllm/model_executor/layers/resampler.py,sha256=jDG2clcusNHfxLptLZUbbwxmxC3f_I-KJ8tJIdjyuLM,10506
|
|
315
|
+
vllm/model_executor/layers/utils.py,sha256=cQL7D6Odzzvu9PcDBze-Q5nS6lvz3WcSNeIgMFz6CGs,7394
|
|
316
|
+
vllm/model_executor/layers/vocab_parallel_embedding.py,sha256=90y_mIKuWUSc5HE806wkt3vfWlhXcDmcWWiygfWRpuc,22790
|
|
317
|
+
vllm/model_executor/layers/fla/__init__.py,sha256=Xbv6P8KG7bLpcOF17zPO5PYYHImweE9aiYYgGyMS9U4,391
|
|
318
|
+
vllm/model_executor/layers/fla/ops/__init__.py,sha256=Tx9ajmbsCCptuJofX-QpCC_Ut2SwZBTT56SUjGXGNs0,642
|
|
319
|
+
vllm/model_executor/layers/fla/ops/chunk.py,sha256=F9ZSa0TANKOLmICyibK2dak49zNkIO6PZrQBEnVbbWE,9482
|
|
320
|
+
vllm/model_executor/layers/fla/ops/chunk_delta_h.py,sha256=z5DwEoIzTsdB15uVlKuuu_qp2UeMaICWKu8JXrWIJIU,11155
|
|
321
|
+
vllm/model_executor/layers/fla/ops/chunk_o.py,sha256=S656q3AJeqpM2-bN4LTQMrj3LfjO8gOp4HIYtitnFhw,5239
|
|
322
|
+
vllm/model_executor/layers/fla/ops/chunk_scaled_dot_kkt.py,sha256=2it3RIhRTd7Rt6RuzdzfHZVFIyv6jqIq6mFnCh5IUoM,4555
|
|
323
|
+
vllm/model_executor/layers/fla/ops/cumsum.py,sha256=86UJl0V-dxqJ8fiAhAjMLnh38JsFivYAMNpcWjbWKhE,8869
|
|
324
|
+
vllm/model_executor/layers/fla/ops/fused_recurrent.py,sha256=rQLcvglC8FrqEXf-QwXIsF5ZraEAKEQcHfkk951NpWU,12692
|
|
325
|
+
vllm/model_executor/layers/fla/ops/index.py,sha256=Lgr5AFHESHhsvgCwQwcAluSBoW2fXte2XjyExBikRas,1266
|
|
326
|
+
vllm/model_executor/layers/fla/ops/l2norm.py,sha256=FR8gjI7Rc3Ahzbxpjc7cUj6of5dyzEqF2aDqsK0ZDEk,4024
|
|
327
|
+
vllm/model_executor/layers/fla/ops/layernorm_guard.py,sha256=pqhp1evGXs0VlEE3-MHaf3ghyyhhmUT41VCp6x-nQx0,11537
|
|
328
|
+
vllm/model_executor/layers/fla/ops/op.py,sha256=7l3ZIAw4i4f6VsmMR8QcbDRD2G-9BCbkdQFj9vv_wT0,1074
|
|
329
|
+
vllm/model_executor/layers/fla/ops/solve_tril.py,sha256=HBubDK4Rq1qK9KZjzqBnoMSYqnxV2ZGaPNA4x6CcAP0,15368
|
|
330
|
+
vllm/model_executor/layers/fla/ops/utils.py,sha256=_f_kk6e-KthBPPggp_-9hI2IV-V6n9PJ5PdgKyxttT4,5980
|
|
331
|
+
vllm/model_executor/layers/fla/ops/wy_fast.py,sha256=YfOPsfu7CPC6NcRd-nHR664d5NG-HDimD0IKZBiP9_k,4280
|
|
332
|
+
vllm/model_executor/layers/fused_moe/__init__.py,sha256=DoweKTpwuJqu77PFhgmGsBzbATR00fgbc539pkOL9MU,3042
|
|
333
|
+
vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py,sha256=QwsfyXIMekvlOEE1KmSoPNcJ1RIdQmbZjpE_ME2Dgbs,11543
|
|
334
|
+
vllm/model_executor/layers/fused_moe/batched_triton_or_deep_gemm_moe.py,sha256=ot4sGPlegMjSqBvGyXCEyuDXOL2qp83rwa0lmvghMZU,5658
|
|
335
|
+
vllm/model_executor/layers/fused_moe/config.py,sha256=6yhLHAASiCf4OuvwYRU2BfnfDPmfK8b02VUh20JqEi0,28449
|
|
336
|
+
vllm/model_executor/layers/fused_moe/cpu_fused_moe.py,sha256=HRH76x6IZsc8vM5imwfAF97ACGVkUjQPalibgNDHeS0,11058
|
|
337
|
+
vllm/model_executor/layers/fused_moe/cutlass_moe.py,sha256=h09nWG7F3TVWwjfymFTT5cvuwQy_iluOml9jCHPIUs0,35539
|
|
338
|
+
vllm/model_executor/layers/fused_moe/deep_gemm_moe.py,sha256=_pDkxtm7laPihRFIGKWG1wWUaXpGg4y0jJhQ1tcROso,13593
|
|
339
|
+
vllm/model_executor/layers/fused_moe/deep_gemm_utils.py,sha256=i6wE2J38oTU5JiSqJvcjJGCZxjeYbuKkt3XAvP9U_zs,13936
|
|
340
|
+
vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py,sha256=3Iv6x8FEJanRAXDrt1IT1jTh11Y5oOirnlKycs6qydY,14028
|
|
341
|
+
vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py,sha256=K2rRqXBGFuHKtCMZ4U4rOwpCQyA8wc7NnCP-uiIExJA,10054
|
|
342
|
+
vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py,sha256=1mu1gmi8q09jjeMLAuWsiw8QYIZTq-_OYcrM_da_B20,9618
|
|
343
|
+
vllm/model_executor/layers/fused_moe/flashinfer_cutlass_prepare_finalize.py,sha256=1GhcU9-NyBonTpA4OQPmobIWUViBOFGGtidfbWkEvhA,9578
|
|
344
|
+
vllm/model_executor/layers/fused_moe/flashinfer_trtllm_moe.py,sha256=wFMC2alcC4B4k5KdjYUW-r08V86WNQBFnfR6_JXI0-Q,6859
|
|
345
|
+
vllm/model_executor/layers/fused_moe/fused_batched_moe.py,sha256=LluK2WojudYW2x3ZcVbI7VdRiuBKyCNJE3a7BvqAi-o,32730
|
|
346
|
+
vllm/model_executor/layers/fused_moe/fused_marlin_moe.py,sha256=E3E1dIdOrkxN5BGwqvFdY0_BFRXIweRGlW4yaeHlrYE,9599
|
|
347
|
+
vllm/model_executor/layers/fused_moe/fused_moe.py,sha256=i-hHemU4lBlO9cUJWvwoewQJpR2YBZCjbdQ8hHH2dA4,74023
|
|
348
|
+
vllm/model_executor/layers/fused_moe/gpt_oss_triton_kernels_moe.py,sha256=DYm3Tvu9Hcsz5ErrKtlpUPlGP53mHlydrDuSKHDMoYY,10626
|
|
349
|
+
vllm/model_executor/layers/fused_moe/layer.py,sha256=QO1JMK6sDATsUos8Xt3X_4RjoZraIRpGzQjE2zvQYGM,95244
|
|
350
|
+
vllm/model_executor/layers/fused_moe/modular_kernel.py,sha256=aIp7CtkOTsjqKSqkuODQPGEjBLfEc90OcpECfyfEGcA,39511
|
|
351
|
+
vllm/model_executor/layers/fused_moe/moe_align_block_size.py,sha256=rAvSB8cd6NtanQk8vNL7fLkpL3ul0sacX_BBIZk8aR8,3985
|
|
352
|
+
vllm/model_executor/layers/fused_moe/moe_pallas.py,sha256=-OiAA6igR4VE9FbrEHBtxc8Ugzt85uX9_7ubsmciatw,3163
|
|
353
|
+
vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py,sha256=XDZHXEkfWKAW1GFwOR3pzM0NzbwhKD--Iy335T6E4XI,8766
|
|
354
|
+
vllm/model_executor/layers/fused_moe/moe_torch_iterative.py,sha256=ZSvVVU8rUzENLnHycTypPg2UhO9eF_eu6wm1HEtpl-s,2156
|
|
355
|
+
vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py,sha256=sMxdQdCPKb20R20EBP4JwAa9AOntCv18Eufb4v7pOKI,11808
|
|
356
|
+
vllm/model_executor/layers/fused_moe/prepare_finalize.py,sha256=2_n9ZUbcwf13l85QkgUpZqqja918oi13RAUl1K40Ixg,2487
|
|
357
|
+
vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py,sha256=jIiAZcWwmtFShSkVfQf33P1w0evBMdNigrCtvK2ZB9M,14731
|
|
358
|
+
vllm/model_executor/layers/fused_moe/routing_simulator.py,sha256=mccQRQsqTHTglvzrD8cUY8Z4q_CH9yWZf8itmbdJ0so,10487
|
|
359
|
+
vllm/model_executor/layers/fused_moe/topk_weight_and_reduce.py,sha256=-9BidYNhyAjc1ddZwRiQv4Cm1MIdEw28a_ifm9k8qXY,5750
|
|
360
|
+
vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py,sha256=JQpd8pmc3pebUrT1fGJbUG8Cw_25xGj_HnCqn8U5NlY,5316
|
|
361
|
+
vllm/model_executor/layers/fused_moe/trtllm_moe.py,sha256=619onnLjTbOwJrkltjBjnL2SVX0qj40tydPfXTlVlB8,6349
|
|
362
|
+
vllm/model_executor/layers/fused_moe/utils.py,sha256=8h7Q6-vtdgInaTmly3CQYQeMEurYPkYcnLcnJis6VcY,9204
|
|
363
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
|
364
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=hH5rRN9Wtyv35azxMzyUMHWtiKgOHev5tNjIG8j6dsE,2751
|
|
365
|
+
"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
|
|
366
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=s47lb8VLnyxMgWlqcIR4BdPBsjKWL4olXF49uZvygzQ,4140
|
|
367
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=gzfjrYDcS0vsACq7ONGVkNA3FqVjr3e89q9fO9kokkg,4133
|
|
368
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Np7yRX9Z7Y7Z5Nutbl02wpKdZRltbt4WqlPlleiYs2E,4146
|
|
369
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=XsNfNXY8v0eatazkLCDiDclI0FnTudUGLYO01e1_4aA,4149
|
|
370
|
+
"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
|
|
371
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=arPqstZMzZjz8BNpY3alKT4vGCJyUj5I2hEeK02aq98,4152
|
|
372
|
+
"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
|
|
373
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=7WHPz_0fxeI3Ed0D9VIpZVoeN9RtJVVARvptfcmQu40,4146
|
|
374
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=2kWS9Qvy5Q3mvUFmbPVures5iZAriAXsy8WrtE5wu00,3727
|
|
375
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=D2dn9vXyN4FCKsZCf7VYgAWLedCx8XpPjbkQVVAvwAA,4737
|
|
376
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H100,dtype=fp8_w8a8.json",sha256=IAD1itR3hNQyHzj6AyfNj7G974sVQEaYafewGm_OKdU,2747
|
|
377
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=5QqFljwwA8OaPlFnXy1zogl5oi6aE0OqN39xk2IUC64,3245
|
|
378
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I3k416HbXU_rYb8scD8gAI4fuBlElHl06PM347Qa11w,3253
|
|
379
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20-3e.json",sha256=CoC3pMKx0vkjI9T6rqRLTIwbDskxljTj31fCHI34B5w,3232
|
|
380
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20.json",sha256=RgV8C4F1LO09h01YsgF_eqX6GNoBtC7ulPfJRUUbg_g,3241
|
|
381
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H200.json",sha256=nsNEuDNks0tVLfQfIm7xxFwEeptTfQcoa9fJy0NS8xQ,3247
|
|
382
|
+
"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
|
|
383
|
+
"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
|
|
384
|
+
"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
|
|
385
|
+
"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
|
|
386
|
+
"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
|
|
387
|
+
"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
|
|
388
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e.json",sha256=gkimxy2r78McckKxx4U4R3xahTI1KMH2pMOdUFOUdu8,3234
|
|
389
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20.json",sha256=vS2DRIDOqWyiBvbG6H746ownfkD1F8Aj2YZ0ET9xll8,3232
|
|
390
|
+
"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
|
|
391
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200.json",sha256=xqhl748it8GV2KXX0XixitE_ywnsKksqK8AGL7tAgT8,3254
|
|
392
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=FsWbV4Q6AzAtgegVuENBDz2ZcSJsqNiwUIVfQbpP7hQ,3244
|
|
393
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=W8C1GtP4K43SK9128U52DD5WWofvPleAJE4us2Qju1k,3251
|
|
394
|
+
"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
|
|
395
|
+
"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
|
|
396
|
+
"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
|
|
397
|
+
"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
|
|
398
|
+
"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
|
|
399
|
+
"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
|
|
400
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json",sha256=10Ntu2aVD5vGLonx-jW0qNw-tgZWdZmzMGx7utDVeng,3237
|
|
401
|
+
"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
|
|
402
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200.json",sha256=JraM-Nvbg5V_TJkSl6UPFYZN1zHHoIbr2pAcksenoTY,3248
|
|
403
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=96,device_name=NVIDIA_H20.json",sha256=JtcHRlPz8xQEAqJ9EWI63oYvdmjQFG6VTHqtt85VOSA,3221
|
|
404
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=f3iM3xm8hGUirJ4ilAIPO6Pe9bs4sm3qaRKMswN9SKE,4731
|
|
405
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=Pux4G7sjfPL22uOJU6t35TXe-VU3OaoPA97TDj9_wZQ,3251
|
|
406
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200.json",sha256=he873aoOy7KfFg-uMoTFV4IP7Yk0Dk7mOTuLCTqwZZc,3250
|
|
407
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H100.json",sha256=Bq57MPQXuSib06u6OwiEmSzOr3XvPYoD6ohYDJaBnII,3244
|
|
408
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=pCCKkdUzzuBVtljyk7AEIAbeDf12DUiieXaODZXzm5E,3254
|
|
409
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=trX2-c4N6hTTD6zFNi6A2bT3FkhxKjkM2rPl-o1K9ss,3250
|
|
410
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I4d56uD7E1JMXD9RAxq3FebdPquDsnNEkVaIY9Ctm9w,3246
|
|
411
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ypuAxMQ7JESPXLBltt68wly2wTrJzlnobhUMip6xAmc,2751
|
|
412
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=tUptlureu5QgyAEedtx5sm7CFudXAE6fIXepOb9gfas,2745
|
|
413
|
+
"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
|
|
414
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JmXhUnhX6YOy8RsmT0zFLGyNCpRBPV2q2Db9Y9ctZeE,4144
|
|
415
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=G4PKqWxh0MlBhg7QHKj0m--_fP3Ll0gs7VJaeg-NIDM,3254
|
|
416
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=bKX9AvcxN6k-i3RUmHSchZZ3rjoYRYb4iBqhCI4L3MY,3257
|
|
417
|
+
"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
|
|
418
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Gu1wROuky-xS0dsFgbXS2QD_hOVV8yol9a5iqiYyq3s,2749
|
|
419
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=_9HO7SaR6aQeh6vqCDpo3kjHnGJ9BVKLiMwYYgd3SmQ,2913
|
|
420
|
+
"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
|
|
421
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=Twkm9DVNxijpowfvioJ_4cKwIIlAWdyNWO9TA3gxAHs,4149
|
|
422
|
+
"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
|
|
423
|
+
"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
|
|
424
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=iySqae0zI_PRBLqV-vfSCwDS4Jxcl5QjWa2NnhndL0U,2752
|
|
425
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Uhq0SrWiCrldkWbb0ZZZhWaCZ0SsvpiNL4z30KZUN5g,2747
|
|
426
|
+
"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
|
|
427
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=TtDngG7ljrU5RtWZ7g-xxdBT3uEuawiKhP8EwPr97XM,3254
|
|
428
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H20-3e.json",sha256=u09XGUdUQqSDasrUgOQeu7ydp5ft5US1oSM0iT-BT3M,3235
|
|
429
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=320,device_name=NVIDIA_H20-3e.json",sha256=JBO_l8hfxCbiQ_PvoqS3Xxqlz9i5PP7QFfXjGKLf7bw,3237
|
|
430
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=Hjpi5BF5UjT0R0uuluIeZMWihlAM9zyWdV5Y2BJu0_w,3730
|
|
431
|
+
"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
|
|
432
|
+
"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
|
|
433
|
+
"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
|
|
434
|
+
"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
|
|
435
|
+
"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
|
|
436
|
+
"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
|
|
437
|
+
"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
|
|
438
|
+
"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
|
|
439
|
+
"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
|
|
440
|
+
"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
|
|
441
|
+
"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
|
|
442
|
+
"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
|
|
443
|
+
"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
|
|
444
|
+
"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
|
|
445
|
+
"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
|
|
446
|
+
"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
|
|
447
|
+
"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
|
|
448
|
+
"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
|
|
449
|
+
"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
|
|
450
|
+
"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
|
|
451
|
+
"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
|
|
452
|
+
"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
|
|
453
|
+
"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
|
|
454
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=R4B2n2vGt4pPo6jS4Bmnx8AYtcfF9qQJE5bD7OhmXHs,3265
|
|
455
|
+
"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
|
|
456
|
+
"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
|
|
457
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=l8y606GTM4Xnd9CBdhjt7LuA_1KLQS41PInHKNfZAZM,3242
|
|
458
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=rVORXxNsxy4WmO5SJR8Sd4k7vozKqhYf50wZNCMeQzs,3239
|
|
459
|
+
"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
|
|
460
|
+
"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
|
|
461
|
+
"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
|
|
462
|
+
"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
|
|
463
|
+
"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
|
|
464
|
+
"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
|
|
465
|
+
"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
|
|
466
|
+
"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
|
|
467
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200.json",sha256=NBj9yhhUWHpNcvwYhPtBKEn1It7BbrnRMRN6Ji2Iazo,3234
|
|
468
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json",sha256=XP1z8IdGklVXVkMIbCtAzWj8nUz65GIZaqZvBvD7v4M,3242
|
|
469
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=7FM4MDavNVOcEOFldsZs5H-E5O6EIAHDY9n-aiLY_Kg,3238
|
|
470
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H20-3e.json",sha256=DaChAo79RafXGjpAOeO1CQ9DazPk7Vazb5bAEyDOYSA,3233
|
|
471
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H200.json",sha256=BB3qPMREaACzWHmhvcETQHLDYGX7GXTKr1E5cm29uC0,3235
|
|
472
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200.json",sha256=0avMzgfoHRzULbxIdzI1SVCWUSBP10kKvxy-3Mv_y_M,3243
|
|
473
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json",sha256=yIEwME0J6ZNfGq13Vj7OA9DmUyKdFZzFj8uaLVb2Yp8,3246
|
|
474
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=pnK1HQ2B5ECqCBolRa5Yb4qAClVoJ2pidBnPy3GBLeY,3244
|
|
475
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H20-3e.json",sha256=q5AAAH8gIaU--3mXhSF1VdFTFHNAy5c-gUvYcm9qhEg,3235
|
|
476
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H200.json",sha256=he8rleYTT40kpshJW1FsdiyR0nRU367CqytS-9-UZNs,3243
|
|
477
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200.json",sha256=LcMD2JddiX488ddRCsh0cXaf3my0VT0IweqQDyTWZwc,3245
|
|
478
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json",sha256=44VdfyrLo-gl23cMeSqSfoGrsqWcjv5-lXwU5y5spE8,3250
|
|
479
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=SyMqNl2wL11cbj95x14YynB4YwyQlaOf1yPPIK0jcJQ,3249
|
|
480
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H20-3e.json",sha256=npr855kvWlHILzi5M0sjYjofPAO9bf6WCF2oZZ4u3to,3236
|
|
481
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H200.json",sha256=xR_v4wy8_ae9fGyuTnhWY0d29NwC9ChPKvdCK5_PS2Y,3244
|
|
482
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_B200.json",sha256=femFBZsNptZ6DlQ32dpBu4zhFxaG-kcs4MFPTxipui0,3234
|
|
483
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H20-3e.json",sha256=iVnryOC43Rirq38PwPxzIHrWvf6pA4wHZtf1HOgGtlI,3232
|
|
484
|
+
"vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H200.json",sha256=K1HkIsowgSbvwtAppZZPudYIIni_waoSxDkARTCEQso,3238
|
|
485
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json",sha256=4UXbsSNHmrSWnD85SdRMLp4cFGRufndzJjB6hoQPclU,4736
|
|
486
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json",sha256=p6TKUp-KDeLB9E9LqThR1e7J2-ogSXPJojISdHgCxaY,4727
|
|
487
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json",sha256=gHxtmO_uvpueLVlsJgXBVE3_pS1S9EeRxNmHG_ZQszg,4729
|
|
488
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json",sha256=tVdpbIU1scsylx6oz3IADhkcwvZaNqw-_QVb7a6oVX8,4732
|
|
489
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=128,device_name=AMD_Instinct_MI300X.json",sha256=_Mn_3ZuKGqNnXtcUUZA0rr29c_lcp-b32uw57oYHgVM,4721
|
|
490
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=AMD_Instinct_MI300X.json",sha256=2eFdAHTU_YTTVad_OEcYZcSbtm5gtlHg4ChxU_v1a_k,4725
|
|
491
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=sCmfFCa-I5Nft9ap-ScL0PVEKZFibkhtVslbFs_NLQ8,3234
|
|
492
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=AMD_Instinct_MI300X.json",sha256=kKu6HpksA-NKVS4CA2ivjlAQEshl1HEufQ0Qt-lTZGM,4732
|
|
493
|
+
"vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=KmYAPOgz-2qn2c5lY8u9XRy8i8HNkmOR5m45TIuwt4s,3235
|
|
494
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=6QPLhZurIqcMVdy3w0Dd7gLViKxsyJRBz-qd8agpi6Q,3248
|
|
495
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=WPu80-OWyEJBy1hdnewLN1H1neFW8UVJrqyeDGegXc0,3250
|
|
496
|
+
"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
|
|
497
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ozS2ECxk-Dsd4Y9DgCGGwDwJlCf5T20ANf5gnTUMuSc,3252
|
|
498
|
+
"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
|
|
499
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200.json",sha256=w18R3eHB4oUhfbcCXjHyDvp0RiDSeCrfM-VFESim2hQ,3253
|
|
500
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=Nm3LPD8JxBYGflI42Cy-xyxZlBLrGvVbnkf9NUmx92U,3250
|
|
501
|
+
"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
|
|
502
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=dYpKgvuG7Jji0W0zg_E9NfIojStBAdBcKd4B3nhimqk,3263
|
|
503
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200.json",sha256=CXiHlGpea5cEGmFi28Jec34uxEZITF2XldVFcJteZX0,3251
|
|
504
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=hLFfmEnpHDZlwBlx7TzfxbjCEywqHEuhjllVR7g9yMY,3259
|
|
505
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20.json",sha256=g3M9w0Noi3DyQB7fcr3jUM62_LKZvTwbY2GtzDGd9_o,3251
|
|
506
|
+
"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
|
|
507
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tku4-yTbIr0H5TNrm1Pq3tJJFYTXqHpdzJDSEF3bk9A,3238
|
|
508
|
+
"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
|
|
509
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200.json",sha256=bM9g-XpirsThO3Q2x8ChSx3PPtHuHRXLvVMnTWt8jLI,3243
|
|
510
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=9vB_5KLq88zBCNpyz6LE7qAo2eS_sgTNsOh6awGnjT0,3235
|
|
511
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20.json",sha256=b6lqVlPt68GZ1wlYu3UtC6zkXnnnKwh4tKGltXNvTVY,3235
|
|
512
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=oxOKFDrgmw1YmgxTtRa1uoe3p09ylTLrkj_jOTqNh1Q,3249
|
|
513
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=-B6gZAEYLwMJZOnpO81pTxqs-YVKs_144Nn9BSLaMh0,3247
|
|
514
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=GPjPHicomrS7ntHu7nnvgNXcHCoUw9vhyTUewkXpppo,3252
|
|
515
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ObHUCUAgHTnld8Cq9Dy1n3ilmbBzyNC4jZcz6YYhMXA,3264
|
|
516
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=WegYsHl39QVlHu_4EZJSrgA4LQ5fYxSVNWFhoL6W2Rc,3251
|
|
517
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Hrlas0Nt7d3JMr1vTpI3OVgkzxqcRziSMfFf_U5pQ58,3267
|
|
518
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200.json",sha256=J59rmqF8NQWkqmay__ahA3t3IwaPXNu5AVNLnTaDfYA,3252
|
|
519
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8.json",sha256=0bH7NZ6VmBBycMus6v7sDXCXtort9awuEpttLLMTZms,3242
|
|
520
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20.json",sha256=VptbMpckYKHKYMJZS-EaO9G0cSL6nciL9XyeHiZN4Fg,3237
|
|
521
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=896,device_name=NVIDIA_H20.json",sha256=GNbp4W4MBoHHN4-0sXJovY0lX6rHfZzGyKicrumupGQ,3225
|
|
522
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=192,device_name=AMD_Instinct_MI300X.json",sha256=r36dUUfR5rv7yS_I8W56z99VAa8LIfaNRQko_97R14c,4720
|
|
523
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=AMD_Instinct_MI300X.json",sha256=XMMCswkzdQxVfOBDM0KXG_ryA9JnX4hFKhF2QspifsY,4724
|
|
524
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=56iA4xNOSuaGWgz2Qg-NiROhpdoBMto4NVUnisUsyD8,3238
|
|
525
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=AMD_Instinct_MI300X.json",sha256=68SI7XVkxHS0k9ApTW1-nSnIqOtbe8rmatNexWRFyqU,4736
|
|
526
|
+
"vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ICdOnZoM8waiOVeVYP18QiPDSbtg9Q6yO-OrO0-2xtI,3242
|
|
527
|
+
"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
|
|
528
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json",sha256=FsIv5bqSpkWbxK2dBfg1N6tX9epZ55ZhgkJCD7hENlY,4733
|
|
529
|
+
"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
|
|
530
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json",sha256=fnO-v4YqBz0vUo0UtOTTD0n7VDG_ivczeQ1tR6Qm9f0,4734
|
|
531
|
+
"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
|
|
532
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=QaITFIJU4UsrOBXaGdPYJwTmYJ0nT9kiiqeUiZzvd1k,3270
|
|
533
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200.json",sha256=CC_jsMhXzrYne7eIOroDa0fCBKNnffiaVW2TKd4P-ek,3260
|
|
534
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=LgHbxG1kQV36zZPkJcnurHYzwAjMh04lvEHEsfzS1t0,3732
|
|
535
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json",sha256=_fcdkmWvdMqHiH8ZAGke-zXhH7qVPQx5CmKELW5hRCA,4735
|
|
536
|
+
"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
|
|
537
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json",sha256=JKYW21c0CzR0fgE5ZnYp6C1sY_tVRlm8L_lgak5V5zE,4736
|
|
538
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=yTf2R9cngSf4OafucAYlDDn4-bftaMFKaY7qhaBZPqQ,3739
|
|
539
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json",sha256=_1eVE7ok935L2V43-3D3bVNWSVaoViia19sh0VrXmXM,4735
|
|
540
|
+
"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
|
|
541
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json",sha256=18v6YruKbQ95pXPV8ocV4VdM1zNw3aZFp3WByeUkNSM,4736
|
|
542
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=AffDc0_51ML8HiA3757zbD10TZJdUsUDIYIqO4g0yUw,3250
|
|
543
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=IEYBNjt9HGnzoOVSWvL0A0jUqq926QD0_BvVYR4RA1Y,3252
|
|
544
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=Ns9Y12aZbJnFhcG3nwb67bDqqiQAo9tdTAIe8K2Ajz4,3255
|
|
545
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=uGSLFPZXK_JQ3GTDUAEiIecDor1yjbC3bJvMolF0Xl8,3267
|
|
546
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200.json",sha256=8q6ol5JQBWj6yVfzFOn7Gz5MSXTaW9javL7qQmYVOwg,3245
|
|
547
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=6jRC0oOpVpq5c1xePFKNRy-Xtmb038i4LE9N2zao2W4,3730
|
|
548
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json",sha256=cFWeyNJtEbs-Bfohgzclxo1rcYGU863oV0BzJyQ4T0w,4734
|
|
549
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=SMtsqtQeqcyy8aNwl9hPxRvx_XQdT7I3SBDNJ3OIvwY,3728
|
|
550
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.json",sha256=ZyOFJB6GUgGZsAjjT43XJwG8P-QrZ5yTvmgzQP7ThQY,4734
|
|
551
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=HOxWmCI2ifHmWc0or2y8nEen86jDeLDov1-tuMzuhxo,3256
|
|
552
|
+
"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
|
|
553
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=_5weLBinQCDzyV75hHKIT95Y0ce94KWft2_5BC6EkbQ,3254
|
|
554
|
+
"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
|
|
555
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=DlatRLPaSr8HJuO50gRZ2lzXoelx55EP3SDUdgIT2v4,3269
|
|
556
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200.json",sha256=TXSOoqvi-x8H13xPqrB9qz2T3opEGA-2D0v_4n5BEG4,3259
|
|
557
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ro3drDpWAdeXH7IjMvx8wYGhIuDPOl0bpbJaIB5Msns,3732
|
|
558
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json",sha256=w_R2LL8k5jNVUARcqvSgGLvNoQiQC0Mh73ciqSIAz54,4734
|
|
559
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=hjDoTXRmEFLKhhmBFEjPowQus_z23ISonxFljql3c9k,3732
|
|
560
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json",sha256=AdOTy7ASetdAXUhNM8buoU8_rLLjcUYF0m8RGFrLWRo,4733
|
|
561
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=Ru460ZgnUP4U8OsJfwF8n-AI-gfcolNR3_qzoxG6DtY,3254
|
|
562
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=K6BGrKw_oHTAtHjsZldcjp-BUM1dIecKXrrRn9OpRGs,3254
|
|
563
|
+
"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
|
|
564
|
+
"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
|
|
565
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=-5nkLIunjG1ghPoUEtt2AXEQw9oGiilP7K3UvQv9CqE,3252
|
|
566
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WKzddrIXo-KavpuXuouW3aLLAptu5Q4XJUb5K2PLgDM,3262
|
|
567
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200.json",sha256=ad1ZkkSyLJwRGb4Kf24qg5hW_DPmt0BXrKR85oAiV34,3257
|
|
568
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_L40S.json",sha256=qX5_yErBEwDRzhv2FvxrS3pEMa8zn0GHzLp5TUMX90g,3872
|
|
569
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ysRCWmxV20K2BYD9XEUtxwREFGtA3QHI191vHRA0k_Q,3733
|
|
570
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json",sha256=L8VA1sfygHoyLJ-Ybfs8DP5c0YWFmMkwxHT8yJ9PEFM,4732
|
|
571
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=FJWpDLr13XF3hHiHfJykpjbLiP7Ccu2en3U6BL-QwXw,3732
|
|
572
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X.json",sha256=FnVcfzf5gXkQRt0XgsRzIQVbDPaUDOwWJX_9qOlyvRc,4731
|
|
573
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=DxYu8regZOSFu8ugFGA_QbwWK4g8xwQUZF9a_nNY4Cs,3255
|
|
574
|
+
"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
|
|
575
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=qwKy8oaMsd3QrXgQbM_x9xcfYiHK_Ou1CEwDPL5Gbgo,3259
|
|
576
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=qUifbWbE4cOKZbIHWmmLx68VRaslQX69eZHwRIQx-7I,3269
|
|
577
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200.json",sha256=JT-ZMLhAqqzSkqivOW5ATTKRlyyaFQkqQDnaPS4DE10,3262
|
|
578
|
+
"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
|
|
579
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json",sha256=EtVorGY4khTEuimlqZu0AAlPz84PH3ZkDZmVpxLtgQw,4735
|
|
580
|
+
"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
|
|
581
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json",sha256=JPdO0azlh4yUvbpC9dEHYpRT11ELEr5LXBSb5XP4E_4,4735
|
|
582
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=BAJnXTZoewwCtzJLUPJ0oYuALv640MvDuLseGcsYaaw,3252
|
|
583
|
+
"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
|
|
584
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tme0ydWzIxdABZLk4tU8G_X2dJUYGGZNkQzNGcmcvUc,3261
|
|
585
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=g6Ivy4wvadaCAMJ4ZElbUU-CwyTMdbaa49M7IVQhVjk,3273
|
|
586
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200.json",sha256=GstQosPPHUn_I2DV3eMGtn3xXOw6kl1hb8L0EvRsbEU,3261
|
|
587
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=kF4Fx0yHUmiMSLFNXT6xqAEA4AgCaHOoy_3irv4dNss,3732
|
|
588
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json",sha256=uOlVzTdJl_4VrRK4wmxIb8JKfveFZRjO9syjw_oEeL0,4732
|
|
589
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=plnx7r9jkcYXkhvapbeeNvUg3NMGdGsIgIPSrfVy2qU,3733
|
|
590
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X.json",sha256=UC-iTgh8_dUSXRaYHOIhDH31KOiJmcfqM_Bv_UBf3ks,4733
|
|
591
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=sY2nWMPh9lsIkhPCjkHO245wpnfFbrHmzdcZDVFPVww,3265
|
|
592
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WQLKugnKzlQ0avf1N-41lRHtG6wJ56DfVPv_nip6NBc,3273
|
|
593
|
+
vllm/model_executor/layers/fused_moe/configs/README,sha256=W2yIZkP9O8GGlg97We9BJfTtWUtPbuz5ZH3esrrjBX0,572
|
|
594
|
+
vllm/model_executor/layers/mamba/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
595
|
+
vllm/model_executor/layers/mamba/abstract.py,sha256=tUai1t50-RYiRDisNYlPcli5cuhX8Tyu9yed43NnDXI,1263
|
|
596
|
+
vllm/model_executor/layers/mamba/linear_attn.py,sha256=5-TQ2lItSPtSGozOnq7X6CenGURyOj0AjUUpY1osfy0,15857
|
|
597
|
+
vllm/model_executor/layers/mamba/mamba_mixer.py,sha256=s7eVaScdmqUK5UPV91x3zvWfvcJwEnpBOT42qDGA7BY,18720
|
|
598
|
+
vllm/model_executor/layers/mamba/mamba_mixer2.py,sha256=fM5GPrgmfc33BAJXacRCWhDtKbBrBVROKDTXl3yoI9I,31143
|
|
599
|
+
vllm/model_executor/layers/mamba/mamba_utils.py,sha256=jGVBADkFYPfpa19FsgatiUqx8xdkBiAxwhL0XhsoOqI,6354
|
|
600
|
+
vllm/model_executor/layers/mamba/short_conv.py,sha256=tiRywjqNh7mESc1ALBxJgWUEy99Wl7-ej6ZJPCmUKsI,9022
|
|
601
|
+
vllm/model_executor/layers/mamba/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
602
|
+
vllm/model_executor/layers/mamba/ops/causal_conv1d.py,sha256=kdR_1kOBQg7YG9jmr0cObtTVvEACbBwVEZRi39yaZbU,43951
|
|
603
|
+
vllm/model_executor/layers/mamba/ops/layernorm_gated.py,sha256=VT5YCFzEKdUJzwGci9cOxy3JsSaTB_vPrYeNP8GWNrE,6074
|
|
604
|
+
vllm/model_executor/layers/mamba/ops/mamba_ssm.py,sha256=SZv6dt9OlnjU6cOqpU6kxPEbFcqLI1JgF-4vOJGRYLE,14282
|
|
605
|
+
vllm/model_executor/layers/mamba/ops/ssd_bmm.py,sha256=cSXjU40kbuZTows07anJfvrfSwLXKNIqkXr5upP3jy4,7976
|
|
606
|
+
vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py,sha256=DHbU8Hu5_AzMtAJHLYJYsS2LNn1zLiwymAfbiMqGhn4,19870
|
|
607
|
+
vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py,sha256=FxPp69wEJGKzxLN8zUPukb-TTF-YQhikXTMszibI92M,26434
|
|
608
|
+
vllm/model_executor/layers/mamba/ops/ssd_combined.py,sha256=S1iKyTH96J3rlxSIlRUMMqvOBVABAoVwjOsMlbdt0js,8704
|
|
609
|
+
vllm/model_executor/layers/mamba/ops/ssd_state_passing.py,sha256=Fm5eoL7VnOY_tkU83Im2i7YIKKxCwCSux89yzDVHgXQ,8172
|
|
610
|
+
vllm/model_executor/layers/quantization/__init__.py,sha256=WK_AQXb1Cs9ZjDAKH7haT5oOZk4T15__gzrA4P--V6Q,5200
|
|
611
|
+
vllm/model_executor/layers/quantization/auto_round.py,sha256=CAPoIwHAz8MAVEldGRFe7XiBbIhETO8sdWnwfiGfH40,15302
|
|
612
|
+
vllm/model_executor/layers/quantization/awq.py,sha256=wlzw9mmHYQgKHiz62ATIIgsxgCe0aUJ_ROKJT6riQRA,8967
|
|
613
|
+
vllm/model_executor/layers/quantization/awq_marlin.py,sha256=IsTBoK3A2Byei-LVNNlk-Onj5KhhOUn0c-RSNqVnACw,22959
|
|
614
|
+
vllm/model_executor/layers/quantization/awq_triton.py,sha256=o8Lqo9lLcyhlMANnDc2NHB63lTRutStBxi93KVQMC0U,12484
|
|
615
|
+
vllm/model_executor/layers/quantization/base_config.py,sha256=pG3r92jvsBL-kvWpCp19M_HZjqJJiq5uCZVMD4AjIlo,5940
|
|
616
|
+
vllm/model_executor/layers/quantization/bitblas.py,sha256=xUGZuAcBUAUcNve_afPDJmCFmo5kwGMrvlmFIZkGOPw,17677
|
|
617
|
+
vllm/model_executor/layers/quantization/bitsandbytes.py,sha256=Wqu4YqPT2uVtHDxEim8u7mf-IAr6T1wQ6BKFO49xOsE,23491
|
|
618
|
+
vllm/model_executor/layers/quantization/deepspeedfp.py,sha256=9bCs0a9MGMToo0-IXR03U5ZTxrLJPy6vXiz-thiahIA,7346
|
|
619
|
+
vllm/model_executor/layers/quantization/experts_int8.py,sha256=LJWyeIIXuAtgJ9eT_P_JJ5zw1XZMcr1y8fULcr6v1l8,8877
|
|
620
|
+
vllm/model_executor/layers/quantization/fbgemm_fp8.py,sha256=53t0aYukyt9O8j_GARyOUtHRFhXoQsE5tIkHcVX9zOM,6986
|
|
621
|
+
vllm/model_executor/layers/quantization/fp8.py,sha256=X2vE_soEyWUhq8ZfFW8cwZr7HWrVDZnn1nC_mayD0Rk,51487
|
|
622
|
+
vllm/model_executor/layers/quantization/gguf.py,sha256=65G_LQUslfcMBHO4_hbRskt4o5Q_-rfvEzf_wKNYB8c,22732
|
|
623
|
+
vllm/model_executor/layers/quantization/gptq.py,sha256=RWOmHh_rq9SzT6YgkYLIyTGV0EO6kjFVwys0FhFGotM,13736
|
|
624
|
+
vllm/model_executor/layers/quantization/gptq_bitblas.py,sha256=M8PcwO5s-jzXYzbpCEsayaEvkObahNvZ0OyeiXdKWOg,17132
|
|
625
|
+
vllm/model_executor/layers/quantization/gptq_marlin.py,sha256=nMgjW3TeIoJ4_Zh-nqtk8iuKObmZaKq-r_DN4SM6aDg,30389
|
|
626
|
+
vllm/model_executor/layers/quantization/gptq_marlin_24.py,sha256=f72YUgTT0ijIZoALWx4wn6M0L8aYpZxxKrb-cRWmZKU,11018
|
|
627
|
+
vllm/model_executor/layers/quantization/hqq_marlin.py,sha256=VJJ9BPxOfO2tYT9xKE7J6MVS1YelQtvA6pGdbs0eDD4,13012
|
|
628
|
+
vllm/model_executor/layers/quantization/inc.py,sha256=Ye2xP-vg0fK1t4QwWHP7pzelKuK08tyKl2BeFB0LeH0,2300
|
|
629
|
+
vllm/model_executor/layers/quantization/input_quant_fp8.py,sha256=59TzbtRnayrCAqZjJJaGsca3k9s-KtyvjJsrheUnKJ8,6282
|
|
630
|
+
vllm/model_executor/layers/quantization/ipex_quant.py,sha256=SPuypSOOL1bX4aYo1_ESIcoPZkdoI7Qp9La8Nn2zvmU,17187
|
|
631
|
+
vllm/model_executor/layers/quantization/kv_cache.py,sha256=uh_XD6SRHRADFWdfB9hhK0PLqZKZVIWqzd7hr6VrROc,6383
|
|
632
|
+
vllm/model_executor/layers/quantization/modelopt.py,sha256=oJi4EN96QxsB-_ZQ0BZMGgBn6UWUEPEi_hJ9tYzyp3I,69245
|
|
633
|
+
vllm/model_executor/layers/quantization/moe_wna16.py,sha256=id6_g4XGXYmBz0mCMj1g6VMLZbJf4a_TsynlO_2cEiY,21569
|
|
634
|
+
vllm/model_executor/layers/quantization/mxfp4.py,sha256=afQQVkC9Rm1GPM-TAhZNNekpn46SKFaN1SqcfWYUa3U,44395
|
|
635
|
+
vllm/model_executor/layers/quantization/petit.py,sha256=Ef9_0u3Rt9G2lYZOaYCGBMI_li1tud_LoMJsVgTEclo,11719
|
|
636
|
+
vllm/model_executor/layers/quantization/ptpc_fp8.py,sha256=0PQY-cMiMcKvB9bUENLneP_egRdGwPyRQCtzR-_p7Fc,5452
|
|
637
|
+
vllm/model_executor/layers/quantization/rtn.py,sha256=MtKCh19cqlPMbEkANIEoRgVY9_E8WaG1X1O_jCYKkSE,17040
|
|
638
|
+
vllm/model_executor/layers/quantization/schema.py,sha256=x7y16hNaValmG7etgyK0RwpeBCPapT1_GznqWBQ5kGg,3749
|
|
639
|
+
vllm/model_executor/layers/quantization/torchao.py,sha256=v-nfqHGdV3W0O5-czoCkOC9n6IjtEvSfnFEkm_jPJwA,7697
|
|
640
|
+
vllm/model_executor/layers/quantization/tpu_int8.py,sha256=otNiEBTZm5XFlkeLfNjPF3CMG0QR5u0U8AQy-BL59Kk,4795
|
|
641
|
+
vllm/model_executor/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
642
|
+
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=b2-oNO_Vvwas9vOXnXVIsS0qq3CJfzDz0u2yjAdTzG4,35863
|
|
643
|
+
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=s8Nu_UXMfUUe9T7Kq80XVWl2o3NkrSuU7eP1ix9US94,90288
|
|
644
|
+
vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py,sha256=nbbIQHQ0e7RzGJKHz6j4BeHtV_pFO5ewl1_jjaI9zRo,7851
|
|
645
|
+
vllm/model_executor/layers/quantization/compressed_tensors/utils.py,sha256=cBduNYE8ud9bePaFyzAZ6dbUz_kztBcs2qsvSIYShQw,7854
|
|
646
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=EGvkXV4Hm2DiyS_NqQZi_35do7oqGTLfbDYjnRLHaeI,1391
|
|
647
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py,sha256=NlMyJIAZgOIgSgMGDLZNV1kC4bAtk6TCcukTVJUCkjI,14500
|
|
648
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=phymTDNBBnHfLXhq9vmwklinzKDZKdYrfp59en2VOok,1596
|
|
649
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py,sha256=002voQj76mVNI3xF3d3IDmI5LM3-_eGXs7VJOarOWuU,6270
|
|
650
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py,sha256=Lgr2COqF2sCxUTnwlBu-P9J9N01aNlf0fqFL8y_d3U0,4649
|
|
651
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py,sha256=7lqY45pOwzlMVUZAPS8Tt8DbnoLJuGBkj2-M5962N_I,7875
|
|
652
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_fp8.py,sha256=5C2bhbprusbPVykruQy7EuB06Rzxla0i_-x3awZWH3g,7152
|
|
653
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_int.py,sha256=SF6TWUoz3TYVncl5BTVeIhpLAqDkbVFjk6R3uUvsgKg,5573
|
|
654
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=Z1-7Bh_1qTwnKkbbj2xO1zn19O76iU-uLWRZwdH08QA,5491
|
|
655
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=eDVZyF8zA9AU0j3uh6wz-CebatD3OSH75AmCYDR7jOc,7022
|
|
656
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py,sha256=TpqBbRB2j5Jbvo4Gczvjy4vqlIEP-j8fljl_nQ66UtI,4930
|
|
657
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py,sha256=tmixOaeebRl-bVTUwRwZMlqr-vhBXE6BeixzhzAqCdg,8541
|
|
658
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
659
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/linear.py,sha256=IumTseLxRkaLhiRzD9NA8NtEg0CpMMjEc_gXBFXd9BU,10075
|
|
660
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/module.py,sha256=AlGwxJC0WAW4EJaKSeUs00qOSFZsyTk-1OSIcOVGvpU,6231
|
|
661
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/utils.py,sha256=zOt-O0AsZ978entPoKuAqg2gzEgMVK5FmW14GVBLfso,349
|
|
662
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
663
|
+
vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/linear_qutlass_nvfp4.py,sha256=_maAL5VJSR9aJFRZwRBeWKeCkzVdoXHWuv9Cix6pVk4,1922
|
|
664
|
+
vllm/model_executor/layers/quantization/kernels/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
665
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py,sha256=DCfiQO0bOUfpuAp5z_sdu4B1agRfbCvtKTZQDn8wC7M,2984
|
|
666
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py,sha256=oMHyhFIyt70Osib76WlW7Sv5rhdOGOLTG6t9VjvTuWo,3760
|
|
667
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py,sha256=feWdTXJ4hDpJjQEIQhabjfyZs56JVY-uza8UD81i5MA,4444
|
|
668
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py,sha256=uoVMlDWnlsv27rsrlhguwnXJ2hA-vNRsKGhGcOKCIQU,12117
|
|
669
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/conch.py,sha256=4FApYttHzs4eM9QPmuzSbM3uqtOqvsayctk8bi9AEl4,3329
|
|
670
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/cutlass.py,sha256=GdkuG0t-O4n0eOT6FduCUnqVr3b5H-OMRpmENK2xZ8A,4508
|
|
671
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/dynamic_4bit.py,sha256=cjvAg-jeIUYP9ZfDTVdOzpw3sP7Adi7pFs2B5sy7n4k,3794
|
|
672
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py,sha256=rKbWF_TyxXjbkm_a28tge9GhOowg121HECmWJIIAm-o,6213
|
|
673
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py,sha256=1uYA__lRJv7g8L9OiHUttOHqX4mjGRVR7GDbG4yZgnM,6194
|
|
674
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py,sha256=L2h7Lt-5u611NpqhMVjP2a5J1IanYdcqtScF80-s6GU,6130
|
|
675
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py,sha256=0cL2WbqxsGFMJMlg4AgAt5_EDOncrIB2z3vlg6FoOk8,2108
|
|
676
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py,sha256=VR6lep_0vVQcxg1CZ86q1K-ekAy26behEGO1VL5_Cc8,3608
|
|
677
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py,sha256=vZrTYKPbsxfkm4eRQMdoJMgabwJYh6aS_fHg8ZqpPws,5995
|
|
678
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/cpu.py,sha256=Og_Fw6Sxlbqnzjhhk6hYcUNe2WdiG7gzESp6YAVIhhY,8141
|
|
679
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py,sha256=ShCi8lhNicAqCuMQzxotER04YFowxqUAHX6XSeqTmBQ,6021
|
|
680
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py,sha256=CgQydI5ERFdaOzOJNR5SPTYIkAUDI-pWr8BqydEB46A,1345
|
|
681
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py,sha256=81LnTkHDJLJ4Yu2nZPVAYq1bFXtzBqIgH0ok97zuuBc,4040
|
|
682
|
+
vllm/model_executor/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
683
|
+
vllm/model_executor/layers/quantization/quark/quark.py,sha256=OaT5OGOD2E8UZ7E8n_tXrSHRr_UEomixUmOHnaBIgMg,18500
|
|
684
|
+
vllm/model_executor/layers/quantization/quark/quark_moe.py,sha256=Rq0NUS75rIlWquRFa-2dm9aIN-zudvbGC4rTIv5orcQ,24615
|
|
685
|
+
vllm/model_executor/layers/quantization/quark/utils.py,sha256=Y1MHt_RTfPOCSb7_kQHK2CQZCaQvG1A6mMA9s70vbDQ,3658
|
|
686
|
+
vllm/model_executor/layers/quantization/quark/schemes/__init__.py,sha256=TvlHrwGTaJp9nBDtUl4n5xtuuPCR18XQVyYGa11AdMM,353
|
|
687
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py,sha256=YkvgTw1sECoubOhGXMixFd47StURg3bzGiYsur_izzg,1560
|
|
688
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=XlX4kbxtaWLP7cmkHvKgNYM59JB4C1uNBSQnQ_ctUwM,9200
|
|
689
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py,sha256=s2L9TRTV1J8FQVAXpSUwH2Vjo29dYV-kQwLYOBNN8PU,7222
|
|
690
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py,sha256=TAZaMWM1lydY9bxKj-mdzRbMcUhSVTIPXvUmt8vll0I,5462
|
|
691
|
+
vllm/model_executor/layers/quantization/utils/__init__.py,sha256=k9dh5aEvZi-6ECfjG_Jq2iijwEfjmdRA9fcHjG9uKd8,235
|
|
692
|
+
vllm/model_executor/layers/quantization/utils/allspark_utils.py,sha256=ejjOMJ4V0UhgYiSvYJf5_x6zJA5iQkAYtzLqaw2AuXE,2260
|
|
693
|
+
vllm/model_executor/layers/quantization/utils/bitblas_utils.py,sha256=p7A4Wa0OyHl34fJKUvy-hUH310Y2oZrouEE6wSz7f-c,8290
|
|
694
|
+
vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py,sha256=lW50RaC0e9zBRNJS3GbfDg0Q6GkZct73W1hbXbMt5zE,3200
|
|
695
|
+
vllm/model_executor/layers/quantization/utils/flashinfer_utils.py,sha256=Pdx2zDsE86bFUNuKe48c6PAnXaeZoIen4oZoPOVVrqA,9529
|
|
696
|
+
vllm/model_executor/layers/quantization/utils/fp8_utils.py,sha256=luZ7bnCy-Jcp80wLP9igtWIvmEdkWYxHjFQskLIcE_Q,34340
|
|
697
|
+
vllm/model_executor/layers/quantization/utils/gptq_utils.py,sha256=35EjGkQtziWnFF_6I5v89ka6oqo9Z3POpZY26tK9eII,5837
|
|
698
|
+
vllm/model_executor/layers/quantization/utils/int8_utils.py,sha256=1r57sgGDuv6gEjl9cBYqCMsq9XrzoBixmgzGKRMncs8,15420
|
|
699
|
+
vllm/model_executor/layers/quantization/utils/layer_utils.py,sha256=KwNOkW1XYBIOjb8UJgyEKd6T_chNqE_YVskWMtrOmyo,1631
|
|
700
|
+
vllm/model_executor/layers/quantization/utils/machete_utils.py,sha256=1lvRUPFOjZj_wNl5XMTxntf_sM_J1KS-8WFj4vFxeRQ,1658
|
|
701
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils.py,sha256=YKpWRCQ1nZ1n3w4gupURf6wLgFaCzxPiNI_Bnwq9O-s,19199
|
|
702
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py,sha256=Mz8-V7C-qqGAdTGjbDatQECVlbyg5Cahmbuxx0shXO8,15507
|
|
703
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py,sha256=J5FjdJQ5PERg6zZ7Wl7O0op4IKjiK40RvMQbrgw9J8w,13880
|
|
704
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test.py,sha256=BHHOmEjch5r24JPZN4FHzKYxb6lhYPGPA0AYDiSznBE,5374
|
|
705
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py,sha256=3_204vZjqNj1Em7VxymB0CfK3TpoHpaS0xY0p29WyDY,17603
|
|
706
|
+
vllm/model_executor/layers/quantization/utils/mxfp4_utils.py,sha256=ljAv2GSEohkcDipvH1i_x2Cgyek9nXhloYHIoxZ0lCk,5745
|
|
707
|
+
vllm/model_executor/layers/quantization/utils/mxfp8_utils.py,sha256=5_KEE10L4lxpjZ0DuIh1JA7weu5Me3aLQt0tyf-5NR4,621
|
|
708
|
+
vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py,sha256=SnaxN2W5uooX9ug8_GuRERhoj61_3XpoJh3h2_pO66Y,4846
|
|
709
|
+
vllm/model_executor/layers/quantization/utils/nvfp4_moe_support.py,sha256=2F5j7BbMir6tZ61pmbW-Mxwj0tIjAOBwsW6jblDRdnk,1990
|
|
710
|
+
vllm/model_executor/layers/quantization/utils/petit_utils.py,sha256=XhbU70TgTv8iBHfv3YoSrRZIF54ueKDMRsH28BeJb4Q,4186
|
|
711
|
+
vllm/model_executor/layers/quantization/utils/quant_utils.py,sha256=FUmQMPqMZc2JNyLF5aaLYOLel8oH-rv8qN-09XFRkWc,21468
|
|
712
|
+
vllm/model_executor/layers/quantization/utils/w8a8_utils.py,sha256=1lUnGnB-OJClVL-UW-6N5YYS5_fVNVKckLcDWUYQlhA,18976
|
|
713
|
+
"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
|
|
714
|
+
"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
|
|
715
|
+
"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
|
|
716
|
+
"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
|
|
717
|
+
"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
|
|
718
|
+
"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
|
|
719
|
+
"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
|
|
720
|
+
"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
|
|
721
|
+
"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
|
|
722
|
+
"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
|
|
723
|
+
"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
|
|
724
|
+
"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
|
|
725
|
+
"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
|
|
726
|
+
"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
|
|
727
|
+
"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
|
|
728
|
+
"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
|
|
729
|
+
"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
|
|
730
|
+
"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
|
|
731
|
+
"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
|
|
732
|
+
"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
|
|
733
|
+
"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
|
|
734
|
+
"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
|
|
735
|
+
"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
|
|
736
|
+
"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
|
|
737
|
+
"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
|
|
738
|
+
"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
|
|
739
|
+
"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
|
|
740
|
+
"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
|
|
741
|
+
"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
|
|
742
|
+
"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
|
|
743
|
+
"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
|
|
744
|
+
"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
|
|
745
|
+
"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
|
|
746
|
+
"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
|
|
747
|
+
"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
|
|
748
|
+
"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
|
|
749
|
+
"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
|
|
750
|
+
"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
|
|
751
|
+
"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
|
|
752
|
+
"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
|
|
753
|
+
"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
|
|
754
|
+
"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
|
|
755
|
+
"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
|
|
756
|
+
"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
|
|
757
|
+
"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
|
|
758
|
+
"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
|
|
759
|
+
"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
|
|
760
|
+
"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
|
|
761
|
+
"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
|
|
762
|
+
"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
|
|
763
|
+
"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
|
|
764
|
+
"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
|
|
765
|
+
"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
|
|
766
|
+
"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
|
|
767
|
+
"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
|
|
768
|
+
"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
|
|
769
|
+
"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
|
|
770
|
+
"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
|
|
771
|
+
"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
|
|
772
|
+
"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
|
|
773
|
+
"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
|
|
774
|
+
"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
|
|
775
|
+
"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
|
|
776
|
+
"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
|
|
777
|
+
"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
|
|
778
|
+
"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
|
|
779
|
+
"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
|
|
780
|
+
"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
|
|
781
|
+
"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
|
|
782
|
+
"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
|
|
783
|
+
"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
|
|
784
|
+
"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
|
|
785
|
+
"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
|
|
786
|
+
"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
|
|
787
|
+
"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
|
|
788
|
+
"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
|
|
789
|
+
"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
|
|
790
|
+
"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
|
|
791
|
+
"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
|
|
792
|
+
"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
|
|
793
|
+
"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
|
|
794
|
+
"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
|
|
795
|
+
"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
|
|
796
|
+
"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
|
|
797
|
+
"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
|
|
798
|
+
"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
|
|
799
|
+
"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
|
|
800
|
+
"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
|
|
801
|
+
"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
|
|
802
|
+
"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
|
|
803
|
+
"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
|
|
804
|
+
"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
|
|
805
|
+
"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
|
|
806
|
+
"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
|
|
807
|
+
"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
|
|
808
|
+
"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
|
|
809
|
+
"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
|
|
810
|
+
"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
|
|
811
|
+
"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
|
|
812
|
+
"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
|
|
813
|
+
"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
|
|
814
|
+
"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
|
|
815
|
+
"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
|
|
816
|
+
"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
|
|
817
|
+
"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
|
|
818
|
+
"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
|
|
819
|
+
"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
|
|
820
|
+
"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
|
|
821
|
+
"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
|
|
822
|
+
"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
|
|
823
|
+
"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
|
|
824
|
+
"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
|
|
825
|
+
"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
|
|
826
|
+
"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
|
|
827
|
+
"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
|
|
828
|
+
"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
|
|
829
|
+
"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
|
|
830
|
+
"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
|
|
831
|
+
"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
|
|
832
|
+
"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
|
|
833
|
+
"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
|
|
834
|
+
"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
|
|
835
|
+
"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
|
|
836
|
+
"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
|
|
837
|
+
"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
|
|
838
|
+
"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
|
|
839
|
+
"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
|
|
840
|
+
"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
|
|
841
|
+
"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
|
|
842
|
+
"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
|
|
843
|
+
"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
|
|
844
|
+
"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
|
|
845
|
+
"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
|
|
846
|
+
"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
|
|
847
|
+
"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
|
|
848
|
+
"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
|
|
849
|
+
"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
|
|
850
|
+
"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
|
|
851
|
+
"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
|
|
852
|
+
"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
|
|
853
|
+
"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
|
|
854
|
+
"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
|
|
855
|
+
"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
|
|
856
|
+
"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
|
|
857
|
+
"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
|
|
858
|
+
"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
|
|
859
|
+
"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
|
|
860
|
+
"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
|
|
861
|
+
"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
|
|
862
|
+
"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
|
|
863
|
+
"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
|
|
864
|
+
"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
|
|
865
|
+
"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
|
|
866
|
+
"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
|
|
867
|
+
"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
|
|
868
|
+
"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
|
|
869
|
+
"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
|
|
870
|
+
"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
|
|
871
|
+
"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
|
|
872
|
+
"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
|
|
873
|
+
"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
|
|
874
|
+
"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
|
|
875
|
+
"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
|
|
876
|
+
"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
|
|
877
|
+
"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
|
|
878
|
+
"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
|
|
879
|
+
"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
|
|
880
|
+
"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
|
|
881
|
+
"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
|
|
882
|
+
"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
|
|
883
|
+
"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
|
|
884
|
+
"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
|
|
885
|
+
"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
|
|
886
|
+
"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
|
|
887
|
+
"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
|
|
888
|
+
"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
|
|
889
|
+
"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
|
|
890
|
+
"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
|
|
891
|
+
"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
|
|
892
|
+
"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
|
|
893
|
+
"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
|
|
894
|
+
"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
|
|
895
|
+
"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
|
|
896
|
+
"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
|
|
897
|
+
"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
|
|
898
|
+
"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
|
|
899
|
+
"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
|
|
900
|
+
"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
|
|
901
|
+
"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
|
|
902
|
+
"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
|
|
903
|
+
"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
|
|
904
|
+
"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
|
|
905
|
+
"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
|
|
906
|
+
"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
|
|
907
|
+
"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
|
|
908
|
+
"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
|
|
909
|
+
"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
|
|
910
|
+
"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
|
|
911
|
+
"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
|
|
912
|
+
"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
|
|
913
|
+
"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
|
|
914
|
+
"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
|
|
915
|
+
"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
|
|
916
|
+
"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
|
|
917
|
+
"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
|
|
918
|
+
"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
|
|
919
|
+
"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
|
|
920
|
+
"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
|
|
921
|
+
"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
|
|
922
|
+
"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
|
|
923
|
+
vllm/model_executor/layers/quantization/utils/configs/README.md,sha256=kfjjurECwd-xH4EDjuueS0Xezi86c_pYu2yELgiw8Ew,102
|
|
924
|
+
vllm/model_executor/layers/rotary_embedding/__init__.py,sha256=wmSdMuRmpVk-JUxdABiOL91XDRj-x9Oa-G3LiAXeu4U,9263
|
|
925
|
+
vllm/model_executor/layers/rotary_embedding/base.py,sha256=cnS3lZFI9YBzRzdzY7dC539FGWgd7IP7_l7o-PprXyQ,7530
|
|
926
|
+
vllm/model_executor/layers/rotary_embedding/common.py,sha256=jpdt5FKJFTIgjXvI7tZfN5AZQ-Ipqx8CxbbJUY2L3uc,4475
|
|
927
|
+
vllm/model_executor/layers/rotary_embedding/deepseek_scaling_rope.py,sha256=Nw15aDY5S-iB5yNKBKu7axSiqSoXsEJOnnUeAgGAnuY,5286
|
|
928
|
+
vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py,sha256=QlsW1NxIUKS4F9xpYJXqh163BqRnKO9P_YaaLsewa68,8562
|
|
929
|
+
vllm/model_executor/layers/rotary_embedding/dynamic_ntk_alpha_rope.py,sha256=NmdcYm_hogzvcboo1hgu021DqDZmK41PvkPUwnhccSY,1316
|
|
930
|
+
vllm/model_executor/layers/rotary_embedding/dynamic_ntk_scaling_rope.py,sha256=if7N5noDPXCfKo4nsy4xGs-pyANctGCXp7StSIQqgMA,2714
|
|
931
|
+
vllm/model_executor/layers/rotary_embedding/ernie45_vl_rope.py,sha256=vAJYBkHhfM8c2ATaDkS9PXFJyuvoWGxEB4q8rJyJlBE,3280
|
|
932
|
+
vllm/model_executor/layers/rotary_embedding/linear_scaling_rope.py,sha256=bnM9AVzJE79EoUMqXd8LG-dyfIOITDLp9DEO1Kk8WEA,4677
|
|
933
|
+
vllm/model_executor/layers/rotary_embedding/llama3_rope.py,sha256=W57lR5Ysnnk8hbSxtrGj6rM08nA9zkXiqPqmC0aK66s,1798
|
|
934
|
+
vllm/model_executor/layers/rotary_embedding/llama4_vision_rope.py,sha256=O6PRDfD79l4Fm7CbjDVd-Z5RMcSHv84qVYlx7igBdwQ,3135
|
|
935
|
+
vllm/model_executor/layers/rotary_embedding/mrope.py,sha256=_ddQBME_Jq6WPiVsas2sp5HWMTHCBBdCYHSED9PWwdc,55672
|
|
936
|
+
vllm/model_executor/layers/rotary_embedding/ntk_scaling_rope.py,sha256=mtAMpJFecIkAHIq9mhHDNuo2FrdrRVWt724yWde_F40,1546
|
|
937
|
+
vllm/model_executor/layers/rotary_embedding/phi3_long_rope_scaled_rope.py,sha256=pFfzb2nW6S2KcwP5t6ONQXTQqtAv7tCysYaEMPI4r9Q,4727
|
|
938
|
+
vllm/model_executor/layers/rotary_embedding/rocm_aiter_rope_ops.py,sha256=TO9pFgyCCdPMNIsxeSkJvj8lx17KdVsu2PDHFSpoaoQ,2471
|
|
939
|
+
vllm/model_executor/layers/rotary_embedding/yarn_scaling_rope.py,sha256=Gvj17F4m12WxJ8DG-vLavmQyGKMx7WYTIjiwLcSFqUk,2662
|
|
940
|
+
vllm/model_executor/layers/shared_fused_moe/__init__.py,sha256=b3NSsmahdIdHBmu24qp1xTq_QvXPE5uN7C49OC2b5ek,232
|
|
941
|
+
vllm/model_executor/layers/shared_fused_moe/shared_fused_moe.py,sha256=0KI0seYhUNqYNH15p_siLdW_CHYc2hec6P6OYI8VmH0,1936
|
|
942
|
+
vllm/model_executor/model_loader/__init__.py,sha256=D_j1yd1s84kp2bi9lJQI8NShjMalHp7d7azhzL1qT_U,4823
|
|
943
|
+
vllm/model_executor/model_loader/base_loader.py,sha256=i324mXF1ZbyqS9bp2iJwksnv30AbdCE4I_NarDvhF_Y,2065
|
|
944
|
+
vllm/model_executor/model_loader/bitsandbytes_loader.py,sha256=RmkN6vD6zHD5kk11JFkeAn3XwFH5vhhua-90B6S93oM,35627
|
|
945
|
+
vllm/model_executor/model_loader/default_loader.py,sha256=BueT0tZtOHJIXKeVZNTZv-cvrCzcRBMaQ8sMOGZQXbg,11257
|
|
946
|
+
vllm/model_executor/model_loader/dummy_loader.py,sha256=nyzNttnUITmIT24_a5NkzYW0cO2MGfC9by4DaVNMT1Y,1126
|
|
947
|
+
vllm/model_executor/model_loader/gguf_loader.py,sha256=o1ujuu8xCcU45CY1sBJsJFOVRANwTAJB_JOhvfhNPGs,7368
|
|
948
|
+
vllm/model_executor/model_loader/runai_streamer_loader.py,sha256=nJWRfPE6W4oRFbiwIfMHEGqkXuea4fMdmrxWQTeAb_s,4291
|
|
949
|
+
vllm/model_executor/model_loader/sharded_state_loader.py,sha256=th2edcpO0n4OCf8rfClC_2cSPnpOPmsOrM_Rh4wHMZA,7996
|
|
950
|
+
vllm/model_executor/model_loader/tensorizer.py,sha256=_SaOZTAoo_7f_IOCueVmWhTPu6O0r4pj6j_TL7stBXA,30360
|
|
951
|
+
vllm/model_executor/model_loader/tensorizer_loader.py,sha256=3m776NeJNF1B4XtB4D1Ol0zbVmAZ_0OxwIBtePIjCYU,5935
|
|
952
|
+
vllm/model_executor/model_loader/tpu.py,sha256=P5Vdz-x22ei7gwao0UKfR_4IHOZa4MJBLahrDZL27sg,4809
|
|
953
|
+
vllm/model_executor/model_loader/utils.py,sha256=7LQDMobOSQ0Bkqk8V2toY7DqiQo3IfRBQSZYR9eidiY,11648
|
|
954
|
+
vllm/model_executor/model_loader/weight_utils.py,sha256=7raVys3tJa5czf3Fud9efGXNLUE_KSMMQqlPyocRKpM,37484
|
|
955
|
+
vllm/model_executor/models/__init__.py,sha256=DNa8BGashOTmIYuYmg3cimkpdYjfrujcL6ap3I6HrcU,1137
|
|
956
|
+
vllm/model_executor/models/adapters.py,sha256=JHbuk_gA6mOmygtcLcyKjy9fi9-r4oVlrKnOEmhECvk,19802
|
|
957
|
+
vllm/model_executor/models/aimv2.py,sha256=fzq5a8XtmAmoEHnQT0kEqJRb5XX0gXR1E8bANLy3YOc,8661
|
|
958
|
+
vllm/model_executor/models/apertus.py,sha256=tesw2NT0yuzCFb-1mjLmrv92oiryUa0jLJIUlXfJWi0,23597
|
|
959
|
+
vllm/model_executor/models/arcee.py,sha256=d9AfGF4S9GUAZFbp6I7EBugGePYO12nF2c3dHuySlDM,17743
|
|
960
|
+
vllm/model_executor/models/arctic.py,sha256=m3MPIc855ZKa0ZY6Z6YGriLrwlVHwHSwFRRaqaBN37g,24392
|
|
961
|
+
vllm/model_executor/models/aria.py,sha256=A4gssrcLNij2S6XVHgq-bwEeMMsjRuCtgtG8J2bFvnE,25057
|
|
962
|
+
vllm/model_executor/models/aya_vision.py,sha256=MX20VhAnI5_z6rstwMoOUTPbcHtZ75vp6sV7DIyXtq8,18642
|
|
963
|
+
vllm/model_executor/models/baichuan.py,sha256=qckdFTGRYD9JumsrSxcwtskspxXnkrMZ1cl9uVnqovo,18930
|
|
964
|
+
vllm/model_executor/models/bailing_moe.py,sha256=PBbpjiu6HYzVuDhn_yMV_KY981Q9qaGN8HJ0IrS5EUw,24217
|
|
965
|
+
vllm/model_executor/models/bamba.py,sha256=LkaZmjfAo3m0eLtDY__7f6T3er-x5LV-uyKmxrAXXDU,19845
|
|
966
|
+
vllm/model_executor/models/bert.py,sha256=4xnfZH2F_X4-KeZBErc7WvqGKXd7xo57Eqy7gySBQWU,25051
|
|
967
|
+
vllm/model_executor/models/bert_with_rope.py,sha256=1r0gwIE35fkUenD1YJ6DKHgYoDhCd13lemiol3ay064,27146
|
|
968
|
+
vllm/model_executor/models/blip.py,sha256=E0Qw2SGxfBPBttkLIqhuIZTmwkS6tAy2-9R48mc3NYM,12402
|
|
969
|
+
vllm/model_executor/models/blip2.py,sha256=TTV9T3vHoJ5b42Hdzj3cDO3Uu0GcWaDlHNX2kk3UMlk,25725
|
|
970
|
+
vllm/model_executor/models/bloom.py,sha256=vJd5qlhui2WBuAAYkB1y_DtRXBzXlB8MXAUd7pOy8Vo,14530
|
|
971
|
+
vllm/model_executor/models/chameleon.py,sha256=dfEZ3A_HNr-AfR_ZRwRGbryDjFBf9feKUYm5cZ5-r2M,45533
|
|
972
|
+
vllm/model_executor/models/chatglm.py,sha256=h_dTjGPjKqMY-VNJwTWVZ_GxjFcazN9ieQLgRtm_BR8,18334
|
|
973
|
+
vllm/model_executor/models/clip.py,sha256=rrt1JfGp1KSVWV9ioWgIks6wZEw_WT2HKvGRuf0T0lY,14924
|
|
974
|
+
vllm/model_executor/models/cohere2_vision.py,sha256=NqrjACsjqF7JcuO2rKjUiZqnw33SvCqYLo3QLfCcZDY,18670
|
|
975
|
+
vllm/model_executor/models/commandr.py,sha256=arz_10DUaOz8_wkbPD1bMTSi3rfYqmKZUCjUbXStC6I,19064
|
|
976
|
+
vllm/model_executor/models/config.py,sha256=mbj59Yo_2vQ29YSUb_tZyFSsQ_gPgFyaEgB8g3TtshI,17744
|
|
977
|
+
vllm/model_executor/models/dbrx.py,sha256=hVQmhjcU1VokX3aZj9hFVRnm01t0hkdg91kfOLUgSeQ,18329
|
|
978
|
+
vllm/model_executor/models/deepseek.py,sha256=G_cMLRXqR19bIYqJ1pm4fvPRmJfJIFp3ipMgNm4LY_o,20065
|
|
979
|
+
vllm/model_executor/models/deepseek_eagle.py,sha256=YHaQ08kb-aWSqwDFAYNOP_oP27kl36L8QsCSRWDb4-I,9410
|
|
980
|
+
vllm/model_executor/models/deepseek_mtp.py,sha256=3p9K03Di0FBKT3R6J6Kcj4vtmfZlk2k0LjrlqH3cmOo,11946
|
|
981
|
+
vllm/model_executor/models/deepseek_v2.py,sha256=-Ug1lMjM9a86Z6tu69DVX_7o23_Hn5oPMPbbhEjcZ-0,60519
|
|
982
|
+
vllm/model_executor/models/deepseek_vl2.py,sha256=haHziojqCI2b5ayyYLs36vV1N6M5TwYMwceMyi7EorY,26157
|
|
983
|
+
vllm/model_executor/models/dots1.py,sha256=wyuKIG3glh9fyqS0AvtsH8f64BC0sec6w1kfdnc4uS0,21952
|
|
984
|
+
vllm/model_executor/models/dots_ocr.py,sha256=AYpcOCYfZLa3CUJfvqbga-TNntBJeIBsPrak1IFZe10,34580
|
|
985
|
+
vllm/model_executor/models/ernie45.py,sha256=VhFbDQ0JTS1Qj-mHNJ1ohprdz9OYg-Jp_qxqWx7e6C8,1971
|
|
986
|
+
vllm/model_executor/models/ernie45_moe.py,sha256=mXbw_kY_FYeKxMfzlYru064sMXVN0lr9mIwoMjNA0JU,24140
|
|
987
|
+
vllm/model_executor/models/ernie45_vl.py,sha256=Xh4NpsCi40t72qQPOaYAV0hX-X6sMsbHYYi8BGSFnf4,57795
|
|
988
|
+
vllm/model_executor/models/ernie45_vl_moe.py,sha256=Yhh7VZXOU-jySpX_9BgpwdZRb_JA93z-b6WQkH6kBcs,29647
|
|
989
|
+
vllm/model_executor/models/ernie_mtp.py,sha256=zUa5OE2I-2Y1EXpXJDRm4eZZWCwnUaCJ8ClJYHB-D_o,10751
|
|
990
|
+
vllm/model_executor/models/exaone.py,sha256=tePVnmZdKb6rSf4ovhYzmud23D3gWcDZSgaGaZ51MSQ,21071
|
|
991
|
+
vllm/model_executor/models/exaone4.py,sha256=BGK_cjvDwGpTziNLk3yXJcpRIhwwoTvDL9e3ABnttMo,20650
|
|
992
|
+
vllm/model_executor/models/fairseq2_llama.py,sha256=62IX9r3OrOKXD-TiNJRx_mI_TMLyqUOvmQxk8aoUZ-g,6555
|
|
993
|
+
vllm/model_executor/models/falcon.py,sha256=WFenIaTlFtRf5l3q2aJZp2U8uKG0mFwmi7et1Uvv5TY,21307
|
|
994
|
+
vllm/model_executor/models/falcon_h1.py,sha256=Ch5HxNoae4ro4PcYiOj5lxHuG2TpQKTE4f_5z52juQs,25706
|
|
995
|
+
vllm/model_executor/models/fuyu.py,sha256=UBe6XsDEla0IEwo3sIcKCtoxc8Xf0tBBNpHfxaEZWOQ,14776
|
|
996
|
+
vllm/model_executor/models/gemma.py,sha256=wjUDRnZpf7XEmvFG0akp4WWPB5PZdi-OltANHBDJ4ZM,16252
|
|
997
|
+
vllm/model_executor/models/gemma2.py,sha256=XJZfQTv6cPSDEn7DvhL1ZtQ1Rkz3PKVhys3pElE3i6o,17210
|
|
998
|
+
vllm/model_executor/models/gemma3.py,sha256=CroKVo1Zcu0uh7ilwyMPZgQ4bkf55F3TizP-D7A-Fd4,22713
|
|
999
|
+
vllm/model_executor/models/gemma3_mm.py,sha256=1OLAjnj85vMnRIWmOIlE0-shkElbNDejm7teC5yPzqI,26251
|
|
1000
|
+
vllm/model_executor/models/gemma3n.py,sha256=b6ncKXGSJf1gF9EwYDsyT1YadKlUtwnKxc0GzLMtSxQ,43923
|
|
1001
|
+
vllm/model_executor/models/gemma3n_mm.py,sha256=Sws5DEwB2pfjFzbidMvcMHoEylyzuCEPHjbL6viyPKk,30750
|
|
1002
|
+
vllm/model_executor/models/glm.py,sha256=d2mDle-FA4NVjt8bVZwYQm1ddtp75b8Ji-1aVlYKb28,1059
|
|
1003
|
+
vllm/model_executor/models/glm4.py,sha256=EuqYJvWDL-EAdWDUE8BfjW9WOAC4rp3buwUtfH1IdCo,11805
|
|
1004
|
+
vllm/model_executor/models/glm4_1v.py,sha256=bUOiSY__x8QZIOv-cRPudxDXYCg9KVJDNOlUej7KKcY,65270
|
|
1005
|
+
vllm/model_executor/models/glm4_moe.py,sha256=f6UgQive_AdRugF1oJWTAMqtcShXbeCAK1UAy8cNZuA,30406
|
|
1006
|
+
vllm/model_executor/models/glm4_moe_mtp.py,sha256=RNLiDdSyfLfl0bfxqAO1HhtQvh--q5Lwm01i4KI0dHI,12659
|
|
1007
|
+
vllm/model_executor/models/glm4v.py,sha256=254goB4J7VRk8He4i26vUAj8BPmjAegbjjsA2fyCqdY,22574
|
|
1008
|
+
vllm/model_executor/models/gpt2.py,sha256=zuInv4LwvnsDFq090cbal4NC4SZXld4KNx8Tde8wFKo,14741
|
|
1009
|
+
vllm/model_executor/models/gpt_bigcode.py,sha256=tOn0wTINKHZhUOtG6juGAxADi_mufgJmPSfdKDenuZU,13472
|
|
1010
|
+
vllm/model_executor/models/gpt_j.py,sha256=csoaG6wbrMx4EX_jL5TgW3ngGQZcYJjbdYpkKuGJkHw,13208
|
|
1011
|
+
vllm/model_executor/models/gpt_neox.py,sha256=oQ3iH4soyZ1ECOLoXg4rTATFndj15OUdhixEt6vUYog,13255
|
|
1012
|
+
vllm/model_executor/models/gpt_oss.py,sha256=a6NaYpuyJgFLZE7Bv7if0suUW-wg_NnxJtLg5aDe7_4,28731
|
|
1013
|
+
vllm/model_executor/models/granite.py,sha256=VJpJgrNxFpPYLKLfEnMEueHuVSIswsJwkUDEChqglKE,20001
|
|
1014
|
+
vllm/model_executor/models/granite_speech.py,sha256=JdCjOKuoLOaOMlQEIdQ-8jclh77lM-lf9PqHl-ZFwnQ,31950
|
|
1015
|
+
vllm/model_executor/models/granitemoe.py,sha256=rXn0uIBtnDl-rVfTz8zbkev84ACO1kQO-c201ncBp9k,23114
|
|
1016
|
+
vllm/model_executor/models/granitemoehybrid.py,sha256=JmgVVpdTcMI2Q6KgH2PUChJsGO05peYF6Up12TCQpS4,25561
|
|
1017
|
+
vllm/model_executor/models/granitemoeshared.py,sha256=GmCHKxPWrzJZk2PdPR9KMJtGGBW0xAwnT9oQwQMHc04,13417
|
|
1018
|
+
vllm/model_executor/models/gritlm.py,sha256=DNXmkqAltks_j3Ouo0zitqF50GA_8mt3CN5Zmop5Y-A,9514
|
|
1019
|
+
vllm/model_executor/models/grok1.py,sha256=gw1NmOisIuU9lBChw0hd_OWt0FBLbIWOXStVBr_xN3k,22575
|
|
1020
|
+
vllm/model_executor/models/h2ovl.py,sha256=qmQDkgik90iCazP7eu9oYVsg2y5VZLBCur6Mxppw9Y4,18090
|
|
1021
|
+
vllm/model_executor/models/hunyuan_v1.py,sha256=HT0hthUxB8IymIWpepQaPdENRM9tDTsttSgxuqWZ4Xc,41878
|
|
1022
|
+
vllm/model_executor/models/hyperclovax_vision.py,sha256=YIrVNu4rvvvQF3ipuy7Elf-9-Rl1Xz1SJciQ29mW3uc,43949
|
|
1023
|
+
vllm/model_executor/models/idefics2_vision_model.py,sha256=0DCW_ReVn9vGkksAoY1n6pEDUqZzBJU7hJfcZ5X5LwI,16026
|
|
1024
|
+
vllm/model_executor/models/idefics3.py,sha256=KPgIPrl7Ac0naEntoKbvfl2-L-kOn_HktVroWdYND0o,27566
|
|
1025
|
+
vllm/model_executor/models/interfaces.py,sha256=03tqL962coKU_icHMX1kLPt6QCwhi5YbyOOJzYcHiJg,29660
|
|
1026
|
+
vllm/model_executor/models/interfaces_base.py,sha256=2FBV6chJOhpHqO5AinLQbcRedpY-mKQbLwVVAwiKRrA,5102
|
|
1027
|
+
vllm/model_executor/models/intern_vit.py,sha256=BzsLpvhHgh6VhmQPYLD9TZHEGLGxA4_HZNMxZrDyuEc,16269
|
|
1028
|
+
vllm/model_executor/models/internlm2.py,sha256=4CVrFW5xTMv766EEsXvQC8qYamyqWjVOeTzVZjmlSVM,17237
|
|
1029
|
+
vllm/model_executor/models/internlm2_ve.py,sha256=h-6wadMrKNRxOuJJH_fF2A7wVnU10O2tEsFkTQEhtzM,5839
|
|
1030
|
+
vllm/model_executor/models/interns1.py,sha256=-Ihb20gN9ZX_WNOhpebKu7U3ydQPcsysinbWmwdSyHI,33390
|
|
1031
|
+
vllm/model_executor/models/interns1_vit.py,sha256=HjZxqPHlJZC6u5LmwIZ7LZkdMipgvis_x6MCpqYrNAg,15819
|
|
1032
|
+
vllm/model_executor/models/internvl.py,sha256=Np1SB4r7pF6GKNLF4LXeUm6gS3swqrf--F5TiG0yBug,52188
|
|
1033
|
+
vllm/model_executor/models/jais.py,sha256=VVgHslyemG_PO0ZTFcR2vpRKcJswmmRqRsOsrOtW0DM,14612
|
|
1034
|
+
vllm/model_executor/models/jamba.py,sha256=SqG8Lj5HPCAB8LzE1GjrowwMZ5RRIHgefqNbifrjT-c,23838
|
|
1035
|
+
vllm/model_executor/models/jina_vl.py,sha256=eUmhiNQQS6bbc8nApR11xUPIliTuoig7tLuLUqFtXJU,5610
|
|
1036
|
+
vllm/model_executor/models/keye.py,sha256=2gEOua8CB84BGimiC0hFxas0mnFNXfLORUQWqpxn43A,61260
|
|
1037
|
+
vllm/model_executor/models/keye_vl1_5.py,sha256=qq1JRhhXxYE_7bXhItQCoN9m5eelgF3jNApGUdor8-c,23182
|
|
1038
|
+
vllm/model_executor/models/kimi_vl.py,sha256=w8mRavwgRSo--VFmTFf1Rgx0n5WC_Xto1-ZhWunNNQA,26334
|
|
1039
|
+
vllm/model_executor/models/lfm2.py,sha256=9rBWQb7wyNAdCY1mOnoG5jM7dAb__pkkhjxC6IMrhYU,20471
|
|
1040
|
+
vllm/model_executor/models/llama.py,sha256=E1zF50hnIFfhUot_IcenZ8VtLqRDi3OtYOPPo3Q9hhM,27276
|
|
1041
|
+
vllm/model_executor/models/llama4.py,sha256=4m79xQ0fwhlDyBNxndohfBO24_9YRFaBKlmJD6ypdO4,32504
|
|
1042
|
+
vllm/model_executor/models/llama4_eagle.py,sha256=5z7TcqEw_ZXKXG1zq4v6Pc7uQ0Rm-b02jVWmzN1ufFQ,9558
|
|
1043
|
+
vllm/model_executor/models/llama_eagle.py,sha256=3JhuJUMblgcuThAc2Uifoqg5LLdUvm8otOEfB8rKOIc,6535
|
|
1044
|
+
vllm/model_executor/models/llama_eagle3.py,sha256=RYojdeOhhDhConrXj1y5-Yf4A9J4qJad_Q-yoNsTO4I,10916
|
|
1045
|
+
vllm/model_executor/models/llava.py,sha256=NXWLn-yFTMEXXGGBWeyxBe21Db2Ggf9OWySCDXFetoI,32562
|
|
1046
|
+
vllm/model_executor/models/llava_next.py,sha256=kCVjqukfWkofVXje7jpgv63E67hwW27LLvNvSs9rHuU,23706
|
|
1047
|
+
vllm/model_executor/models/llava_next_video.py,sha256=qcdU6mviFvmMhxEGuEW8C4N-Lt75MO9NKL7N1Jbo9Ag,18066
|
|
1048
|
+
vllm/model_executor/models/llava_onevision.py,sha256=ERqqB2PPt-CxmAUbtsZ633FI7ZZyHy58T6RQwjavAKw,36565
|
|
1049
|
+
vllm/model_executor/models/longcat_flash.py,sha256=z-U33KPvmGioDwt9ezbBPtb09gG_rHOpTzRYDqW5k-c,28335
|
|
1050
|
+
vllm/model_executor/models/longcat_flash_mtp.py,sha256=s1eklLa_DkupnnpKAqWnkTxQLdTv54jxYx2OIW3eMl0,15946
|
|
1051
|
+
vllm/model_executor/models/mamba.py,sha256=36BAgB5cOiZ1GmTct6br5WsVjzByb3G6DY_z7p0PlKU,11539
|
|
1052
|
+
vllm/model_executor/models/mamba2.py,sha256=jTBaURd8b_rP-_ODGngKPrIPigYEqUw9ZF9Nfg1Gh-o,11830
|
|
1053
|
+
vllm/model_executor/models/medusa.py,sha256=khwLUVIKzshOuEWedhghItnwURJHAobiwbHwak_bT5M,6909
|
|
1054
|
+
vllm/model_executor/models/midashenglm.py,sha256=Xr0vM-FZApncusmORXSGlgJ7M_iM00jt5-yAEXnGkmM,28938
|
|
1055
|
+
vllm/model_executor/models/mimo.py,sha256=UH5J-NRmobzYzfcsCOiDQk_8ORqVjTu7pDP4-lb9inM,7688
|
|
1056
|
+
vllm/model_executor/models/mimo_mtp.py,sha256=h-IoK47J-m3ms6Srg6D3OHVdTUOFXDHjWv9532Ed4uw,11281
|
|
1057
|
+
vllm/model_executor/models/minicpm.py,sha256=EnHxLK_ioiA6RyHlFEqPb1dUcPNyFoBwMk90eQoSvT4,25522
|
|
1058
|
+
vllm/model_executor/models/minicpm3.py,sha256=3gR9YhnAHhgoi9hfQupHmNhhAt--aeyMDMerp7sncuw,9429
|
|
1059
|
+
vllm/model_executor/models/minicpm_eagle.py,sha256=AVfBVTQgR4vSOryww9jzryW-IHv23UYvp2-78sHo_kU,15783
|
|
1060
|
+
vllm/model_executor/models/minicpmo.py,sha256=35vy2i_ym1jkuTQpyhW-xLsuxKUJQ3ezglTF9I2nAls,29235
|
|
1061
|
+
vllm/model_executor/models/minicpmv.py,sha256=tl2G_fuWdLJxPoy5M2nbtMnuLavxLJycCtSc_8LQf5Q,66125
|
|
1062
|
+
vllm/model_executor/models/minimax_text_01.py,sha256=ef9QJA_FHAp1nsR5Iu80cv0lbsMxYcQMvX9mlWFidfo,39329
|
|
1063
|
+
vllm/model_executor/models/minimax_vl_01.py,sha256=Htr0BHM9vSEw1rR7Om9otrSmDQY_L6jS9K7R9y8iup4,17200
|
|
1064
|
+
vllm/model_executor/models/mistral3.py,sha256=4rA7EfsQxZCnydHAIWLSLpu4DJRnfa3HkZvk9HZvT10,24104
|
|
1065
|
+
vllm/model_executor/models/mixtral.py,sha256=GeWm8LS2JjErcEFYCA1YaJ6tMh-8PXmefCdUuDARmt4,25313
|
|
1066
|
+
vllm/model_executor/models/mllama4.py,sha256=YmFBS3VezAx5yNJSv1htBCFn2YfpawcVxWoExVL6A4k,40820
|
|
1067
|
+
vllm/model_executor/models/mlp_speculator.py,sha256=GA5FZXfVz7JX1e8EwfP0IDcwIiGBB3HTrbIOHoj1UHU,8011
|
|
1068
|
+
vllm/model_executor/models/modernbert.py,sha256=kH1_7XJWtBP5CgcSKKEdln44dR-zd4NTDtAYl8MCxPE,14114
|
|
1069
|
+
vllm/model_executor/models/module_mapping.py,sha256=vNEOOezDnDR5JgMltbviAANLu8CM6tQdr3RX6tZu_i0,1844
|
|
1070
|
+
vllm/model_executor/models/molmo.py,sha256=dRYkd19EbJHZ-ucLcMFLFLaskL7jAlofjJHX_ku00vU,54900
|
|
1071
|
+
vllm/model_executor/models/moonvit.py,sha256=5NC7MQo1KQf5oRr6zx3cCSxMSOlo_xlplry6ZIHOt0k,26340
|
|
1072
|
+
vllm/model_executor/models/motif.py,sha256=7Fj0iyl7H23Wa6hOvwWjvnwLiri8NLKTMP2vOvsAAYs,13929
|
|
1073
|
+
vllm/model_executor/models/mpt.py,sha256=uGJJKmnJrDhOnrHvnAuwsmBcrMuBfbAuBHwgT2Q4rac,12581
|
|
1074
|
+
vllm/model_executor/models/nano_nemotron_vl.py,sha256=Xm71a8tdXHdFbnRfKAn8RPLoAdpVXoi_g6ujuvPOkkM,52164
|
|
1075
|
+
vllm/model_executor/models/nemotron.py,sha256=ZDj_R6MpltXd87suNWQPp_PyCCJD22yJ-t8KQK34Fos,20639
|
|
1076
|
+
vllm/model_executor/models/nemotron_h.py,sha256=H3vVOlisxLtDuzLs31spVfNsuyOi-Ozknl4UbtzM6EI,20299
|
|
1077
|
+
vllm/model_executor/models/nemotron_nas.py,sha256=V37JYi9Vw99x1YdwZYFiu-VgFh_bA3i694wTuO74Bjk,19049
|
|
1078
|
+
vllm/model_executor/models/nemotron_vl.py,sha256=iGuGvgG2QZ0bmPPz04guKrLgrexOWUcGAqjCY6f7pbE,23976
|
|
1079
|
+
vllm/model_executor/models/nvlm_d.py,sha256=13ydfbCEUpu9XkGdO_sbj1zpaH5H3hKgv5-PGJTHujQ,7622
|
|
1080
|
+
vllm/model_executor/models/olmo.py,sha256=42tTL1UD7oleCr75ip60bx8fhHsr7BnbwB2an_CyDGg,15314
|
|
1081
|
+
vllm/model_executor/models/olmo2.py,sha256=lZJbrwlHvZb2GYqDTx3DUhp1amdLuga2Z6T3Rtyuyt8,16918
|
|
1082
|
+
vllm/model_executor/models/olmoe.py,sha256=4KCiuk3XepXTFPa4s2V3krFuNBPytuu95J0nnUGa56E,19785
|
|
1083
|
+
vllm/model_executor/models/opt.py,sha256=wv326uuQA2FVGFYcAEIVwvg_jCJqnnS5XYWjCurjWBQ,16569
|
|
1084
|
+
vllm/model_executor/models/orion.py,sha256=3ZgUUB0yhP9ZnWK5BHEVYKyVHF6Too5S4iWL0p1AOQs,13808
|
|
1085
|
+
vllm/model_executor/models/ovis.py,sha256=SMjjs_F8aoZH_pMr_79YQlqOnl9x3eyCqDnU3uz9FAk,21683
|
|
1086
|
+
vllm/model_executor/models/ovis2_5.py,sha256=8DuKb2qZGk9wouy1JPDdcZYix6NylwnTF1ApkVd_1_k,24834
|
|
1087
|
+
vllm/model_executor/models/paligemma.py,sha256=y17kVaiU87Hip-dhPjyuI62bN08i8ON57D_U-H0Cb70,15215
|
|
1088
|
+
vllm/model_executor/models/persimmon.py,sha256=J7_MnEQqSXH3sfVUiEjJLzL6D83T_XHSOi4HwDJu3EA,14274
|
|
1089
|
+
vllm/model_executor/models/phi.py,sha256=mJcGWW0cfL_ouuy7RwFEt9To_n-kmi8Pp27wqeavqXY,14157
|
|
1090
|
+
vllm/model_executor/models/phi3.py,sha256=OdDcrMZ2IYHzg_R_gu89ae3lijNSFlxUXKTw4mmcR8U,457
|
|
1091
|
+
vllm/model_executor/models/phi3v.py,sha256=J4ubMhjiQaQZpF-HH5xEcnrBOsm3Nw4_tdbWEc5uRWA,27516
|
|
1092
|
+
vllm/model_executor/models/phi4_multimodal.py,sha256=F33yRK8PM2Cle4Kxcu9d_K27Mk8tryjPnDP8phc5G8Y,57893
|
|
1093
|
+
vllm/model_executor/models/phi4mm.py,sha256=MzQgH8s6eymy4w-dB-a86gFg6rkZ-XQmMxvsRJZ4KWU,50148
|
|
1094
|
+
vllm/model_executor/models/phi4mm_audio.py,sha256=OtLomyHZ1aR_0GP9H5e49-u1HX3PiA81TcQelWaoW_w,51162
|
|
1095
|
+
vllm/model_executor/models/phi4mm_utils.py,sha256=8RE6JOwyxFfL89OEykkbSlLalOFk_2zsHASi6VOtP8w,67478
|
|
1096
|
+
vllm/model_executor/models/phimoe.py,sha256=L0gsg1HD4q5V4FqK5R4Pb3Ou2GQ6ya5v08V8o2eew8c,25243
|
|
1097
|
+
vllm/model_executor/models/pixtral.py,sha256=z2oHm3C1jLw95T2kFrqn3LukUlXNT-Oi6_VnNzTFW18,49528
|
|
1098
|
+
vllm/model_executor/models/plamo2.py,sha256=FFvm27x-6yfrbHZqIiHi_ggONiZWeQWp3Rb7waaarP4,39290
|
|
1099
|
+
vllm/model_executor/models/qwen.py,sha256=VJOot2FPboOrlQOg4bTgOHk0NV6Qv_i4JypKYTJhtCc,13862
|
|
1100
|
+
vllm/model_executor/models/qwen2.py,sha256=rlfYStKiy8mGU4ziIdCC9GYuFpQTmI3ar0pIU53uG_8,20928
|
|
1101
|
+
vllm/model_executor/models/qwen2_5_omni_thinker.py,sha256=t_TYpdEyLcjmZj1Q6E227c7gU_uVdXZGojAWN8Z4pX4,40445
|
|
1102
|
+
vllm/model_executor/models/qwen2_5_vl.py,sha256=-kafXF2QU8NMU2OqE8DPdT4yWShs3vBulfF7i_VHGAE,59638
|
|
1103
|
+
vllm/model_executor/models/qwen2_audio.py,sha256=uCLcoi5Mw5NvDqiNPjQQn2-4QtYHlZHn-QJ2BZETx3M,19274
|
|
1104
|
+
vllm/model_executor/models/qwen2_moe.py,sha256=8CO1EWYG2WsEo3nKINqNo5mSe4H1PgODORe04sSnPQQ,24154
|
|
1105
|
+
vllm/model_executor/models/qwen2_rm.py,sha256=lD5LAuxhTKxac4RuRqzbFZBtwb5RYn1ahXPB2IY_oQ8,4438
|
|
1106
|
+
vllm/model_executor/models/qwen2_vl.py,sha256=CE-eyFNB4dqatf5nkdOLL6yOzublTbOrU7eElbQ_-vM,64456
|
|
1107
|
+
vllm/model_executor/models/qwen3.py,sha256=68-gH1MOzXwSPN3cYIXQFd2AnLCgGJiHoJ-KF6EfAOw,13140
|
|
1108
|
+
vllm/model_executor/models/qwen3_moe.py,sha256=iVEysC2LYsTKjQ5kVqkry2SRqZ607-4nRqn5rp1WK3s,30134
|
|
1109
|
+
vllm/model_executor/models/qwen3_next.py,sha256=EgYL3isi4c-DZQEpJsxFoXVnuznvKhLaOCRtHC-SYRc,51087
|
|
1110
|
+
vllm/model_executor/models/qwen3_next_mtp.py,sha256=VUkqz2HmOqUdY5ZrauprODQMuP43_oV9K0xyY02WcvA,11721
|
|
1111
|
+
vllm/model_executor/models/qwen3_vl.py,sha256=GtiFQQDEw51mTrI3k-vs06Zd7_njczswpYSMCOdqRy8,68104
|
|
1112
|
+
vllm/model_executor/models/qwen3_vl_moe.py,sha256=dDq_M0obn8-tDXPLdK_JCAFSgg_czQR4E_pYQi1YUpI,16988
|
|
1113
|
+
vllm/model_executor/models/qwen_vl.py,sha256=AJ7YwxuqV3XvW1b2MdU-SCXc8WLITYmscqIu6lxH4ZI,27261
|
|
1114
|
+
vllm/model_executor/models/radio.py,sha256=hy2KP3J8DJI5r5ha-vzL0LZ4B1Id3o-B3bIz61V1x-k,19790
|
|
1115
|
+
vllm/model_executor/models/registry.py,sha256=Zswc0yRSOTKMhq9J3eRqyYv--jteUtA462g8LQYHbCU,43556
|
|
1116
|
+
vllm/model_executor/models/roberta.py,sha256=_NmoejqZikPqCWKJ8T3e62WQN1eRhI-dWXEcHFjgV5g,10559
|
|
1117
|
+
vllm/model_executor/models/rvl.py,sha256=lHKPSwg6Oby1fR19Eci9kAYxNoKlTl5yv1-XLCsCNdc,3411
|
|
1118
|
+
vllm/model_executor/models/seed_oss.py,sha256=wckaUj1q09uCfEgvubgGHIMn4KsVnrdbITY9YOG04vI,18812
|
|
1119
|
+
vllm/model_executor/models/siglip.py,sha256=OwdhHM4EfPXSR5HYSRBozR-VvtxyN25ERabjXnR-wOo,19605
|
|
1120
|
+
vllm/model_executor/models/siglip2navit.py,sha256=XVkLkqNMEi55OCBe2f6zsyrVJioPc45Fu5LuyX0jO3M,27402
|
|
1121
|
+
vllm/model_executor/models/skyworkr1v.py,sha256=PTHk_vNDCvERDK47-_hZTPUE8pbV_IUiJDpewmfL1aE,32758
|
|
1122
|
+
vllm/model_executor/models/smolvlm.py,sha256=UHJHGKiMjLelyQBxxetY_MjFsB5neGCTXE3FgGkSIlE,1614
|
|
1123
|
+
vllm/model_executor/models/solar.py,sha256=3JKhURUD8U9VYtk47-wGUBp7olR2LzBFvuPGSgbAT7U,19833
|
|
1124
|
+
vllm/model_executor/models/stablelm.py,sha256=D__qHUe9ZPtCmV2ZwU_y0x55d7oPv5Q--9kFTbL_NJs,14875
|
|
1125
|
+
vllm/model_executor/models/starcoder2.py,sha256=_cCB7QNfMcQ6vZc5LZGnnHj_dmTG9w4bepit07qXmz4,14478
|
|
1126
|
+
vllm/model_executor/models/step3_text.py,sha256=z42drTRKr3aPIDYbmssTL8gHTKSRg4wp3mgon7ZUCkc,21205
|
|
1127
|
+
vllm/model_executor/models/step3_vl.py,sha256=rdRKwkXbLnq3Ix6Xuep-GTL1HLY8gHOijFbV7hpqze0,41993
|
|
1128
|
+
vllm/model_executor/models/swin.py,sha256=u0ocae8ZHEbpPMPxgIdJGhwiuy-COZBqCcSguEDYz_M,18103
|
|
1129
|
+
vllm/model_executor/models/tarsier.py,sha256=pguBDSEeKZOBOl4eV0z557ohGzt8VNAj-uH0ZOmBYEw,25831
|
|
1130
|
+
vllm/model_executor/models/telechat2.py,sha256=aLab_2TYAW_ogYlYpFuTyZ7eqIsA5zvrOWXzNuC-Rhk,6395
|
|
1131
|
+
vllm/model_executor/models/teleflm.py,sha256=8BsSo5Ox4ENo4Y1UKicd2nq41lksPZhW-ippU-498NU,3212
|
|
1132
|
+
vllm/model_executor/models/terratorch.py,sha256=eIZtd9OjwjebxqH_fl3ACQW_n8FEdiZ4tz78QCh6dOc,11103
|
|
1133
|
+
vllm/model_executor/models/transformers.py,sha256=dHTmhGyoma-XDGijL9HbJxAd1xmmA2xfcJeVEF3EV9c,38542
|
|
1134
|
+
vllm/model_executor/models/ultravox.py,sha256=Ga3RsckuKVoag7Yb__YwPjyfo_GAsB_L9VMmpbo0bMY,26650
|
|
1135
|
+
vllm/model_executor/models/utils.py,sha256=oj9UOJDNdMiEdty0SJRwEDALQRI-2tkyDE4OmtWxDjo,27947
|
|
1136
|
+
vllm/model_executor/models/vision.py,sha256=onxd_8tOkFBt3aLGbNwBhGOnTIYnOsLYy8fDRRMu2EY,15859
|
|
1137
|
+
vllm/model_executor/models/voxtral.py,sha256=_dRE7_eNGFNmBSc3eyBFQyUDY1fDNxaDGHe-casVA3w,31807
|
|
1138
|
+
vllm/model_executor/models/whisper.py,sha256=B7ikTK_UBekCJ9riPoHq0y1ge3C8GKDjO7slxB96-x4,34780
|
|
1139
|
+
vllm/model_executor/models/zamba2.py,sha256=XfjgvKu4eoX1vVLt9rw1xzAVb-kcp41E9tPJ-Eod81M,37770
|
|
1140
|
+
vllm/model_executor/warmup/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1141
|
+
vllm/model_executor/warmup/deep_gemm_warmup.py,sha256=LWqH_Rsp6g93qgVf7Hcn4wJdhXjqz29qSKpHooekvdA,8617
|
|
1142
|
+
vllm/model_executor/warmup/kernel_warmup.py,sha256=8QSw5vJ_nFXoPmzT5KzygWRpG123FyBmLmuD01km9_g,3249
|
|
1143
|
+
vllm/multimodal/__init__.py,sha256=QgdukALGMTNZ4OmibSLGC2BQw3-A-NRn2nYxnleluGQ,1055
|
|
1144
|
+
vllm/multimodal/audio.py,sha256=RNLMLOanqAS4yS9WcD-NA1SPvC8gDYLuYyS5O3JHJd8,3476
|
|
1145
|
+
vllm/multimodal/base.py,sha256=GaUsf7apDyxuLATMm4iqkuLd3EkDDfiNDzFI70G_AKU,702
|
|
1146
|
+
vllm/multimodal/cache.py,sha256=a6631NpXuvFjU21wgo3J2TJRo13_8XCwCfJ6AceaDB8,22216
|
|
1147
|
+
vllm/multimodal/evs.py,sha256=2V_0NRi5wF6wJeN6FqVVHnycFF7Lu0y4GbwVw2d1ci0,11140
|
|
1148
|
+
vllm/multimodal/hasher.py,sha256=NOoo3E59KVDdwBxnsSvWxpjQICfGgZapsxCQVhLNF_c,3656
|
|
1149
|
+
vllm/multimodal/image.py,sha256=aLJbqxgnsdtv-DZpE8rXsK-bK5FlIsofw6Duag1K-1Q,4428
|
|
1150
|
+
vllm/multimodal/inputs.py,sha256=I_LWOkXlL19aN0FQhHf33koFkV1Opi30ZYeFgEaG6fI,31585
|
|
1151
|
+
vllm/multimodal/parse.py,sha256=x-sQCGJVp9heflqvBedmiy3U14uhNqnKeUhjlfOa82U,16177
|
|
1152
|
+
vllm/multimodal/processing.py,sha256=Fy2vCgCyNGbbDGaEnbVlQDgHg-SXTDgKhfLldMFOg3o,71860
|
|
1153
|
+
vllm/multimodal/profiling.py,sha256=LLeV15nkqWHxDmquPhy5kdmN2s1TpJecLE4s_CV5YwE,9354
|
|
1154
|
+
vllm/multimodal/registry.py,sha256=56YT4ESym5IoLZ1XScNfgIdnDHzjtiua1tEi0P1bzEI,11846
|
|
1155
|
+
vllm/multimodal/utils.py,sha256=yxxgn5s393fkg9lSOq_nmfhvnzZoXQJIXr_2Nd1m5Ak,16722
|
|
1156
|
+
vllm/multimodal/video.py,sha256=IUVg3Ukz5GNajqY9b2ZXZyVFfMVj2TivnvKPOAyqSIY,10595
|
|
1157
|
+
vllm/platforms/__init__.py,sha256=SL8lJmGPX0NTlN_UulLPIe5xrP0dDrS_Rbo8eEcn3Mc,9715
|
|
1158
|
+
vllm/platforms/cpu.py,sha256=CnHp54pf60Q1iE-sdisnGHMMJGPJYaiCAN9O1YbTXNI,12929
|
|
1159
|
+
vllm/platforms/cuda.py,sha256=cSOi-9xkcSgyl5oUtqN2bD6kFbImkJ93HgIWfjml808,27212
|
|
1160
|
+
vllm/platforms/interface.py,sha256=_xQjEhc8Fz2uIKgwPNEPnCn6JVhiOWZVtoiNL9tz-uU,20000
|
|
1161
|
+
vllm/platforms/rocm.py,sha256=QmoC6TCqi2CoLeWyaJM2BnGFXU3qucGk7OH2IAkkpKI,19270
|
|
1162
|
+
vllm/platforms/tpu.py,sha256=APs7-AbSqy2PZG2s_Z4viaTMQjdpFh78kjEnmlTxMeU,8436
|
|
1163
|
+
vllm/platforms/xpu.py,sha256=B6fh9bm72uXjo_orIVNmOfWhnf0TRMrp8W0o2tmjiR0,9391
|
|
1164
|
+
vllm/plugins/__init__.py,sha256=ZRORMWMdEHWT5MyQCUprDf6kjLx3RpSi8nZ9MAlfx5s,2342
|
|
1165
|
+
vllm/plugins/io_processors/__init__.py,sha256=rh0ToGlPVffyddIh-JyN00AVIBnnSn1XyywoHklx55o,2548
|
|
1166
|
+
vllm/plugins/io_processors/interface.py,sha256=wyjPw_-JOW-2WIOxdqVFMIwrpakeWmag0ckSXGfBr1g,2367
|
|
1167
|
+
vllm/plugins/lora_resolvers/README.md,sha256=-QNm2DW1CJ8jXT_DReEycm4e9qCk_fI-HJMzM_CgPU8,830
|
|
1168
|
+
vllm/plugins/lora_resolvers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1169
|
+
vllm/plugins/lora_resolvers/filesystem_resolver.py,sha256=Ic4o6SWF7DeDhNAAE1dxzaAMb_0L03DNzM0590FC1Fk,2086
|
|
1170
|
+
vllm/profiler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1171
|
+
vllm/profiler/layerwise_profile.py,sha256=Kx82mqZxCUwiQtRrBbtWWOwQczd2UC7oXFpJhaeynHU,13895
|
|
1172
|
+
vllm/profiler/utils.py,sha256=zh9V6T6baIqC_EXfG39TUF2-d0z20JVqxfVtKWFDl6Q,4714
|
|
1173
|
+
vllm/ray/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1174
|
+
vllm/ray/lazy_utils.py,sha256=WrCc1ujOpiNakx6xqEXTgIPxsWyqcXAqHXZPa-3QXEI,535
|
|
1175
|
+
vllm/ray/ray_env.py,sha256=qQGwVH2dWUZsL8wLJ1Y5RRH--nAm_RywVJHM-kRhZHs,2627
|
|
1176
|
+
vllm/reasoning/__init__.py,sha256=N88nWT6h6zLvxNOGLuR6hRac5OvzA4bouhyqX8mFUAg,1179
|
|
1177
|
+
vllm/reasoning/abs_reasoning_parsers.py,sha256=sa7p_ThWsyXaaJ18sXbcJKwnjiVjyiplJbQphs5FqN0,6904
|
|
1178
|
+
vllm/reasoning/basic_parsers.py,sha256=UuO4JrPDXfIMWBGzmZTL0BlvE7sS30aU8j3xqcVAW64,6541
|
|
1179
|
+
vllm/reasoning/deepseek_r1_reasoning_parser.py,sha256=Q7scscegbUpdbrXeXUWsFbMmLyikm8ShUvw9TR_AMHk,2526
|
|
1180
|
+
vllm/reasoning/glm4_moe_reasoning_parser.py,sha256=QXyNs8xv_yWCQnnZROK9EyQw34KkIfQ3zwB5I2FfQOk,6558
|
|
1181
|
+
vllm/reasoning/gptoss_reasoning_parser.py,sha256=qT13ewgBMbdjWOLMgbVHtOCIWqh8PKVv89a8JIq4DpE,3472
|
|
1182
|
+
vllm/reasoning/granite_reasoning_parser.py,sha256=JbhkZ4vwrW4787QrpGc4og2p9IvrEqV9MaGah69bUjw,15904
|
|
1183
|
+
vllm/reasoning/hunyuan_a13b_reasoning_parser.py,sha256=zuodtDh1vKPbD6uTY7rHSZ15SbmWuZR7oiCukI_FGrk,10194
|
|
1184
|
+
vllm/reasoning/mistral_reasoning_parser.py,sha256=Bdn0fC-Lu0CP7VccAGIW8ou-4qmPtnGjZWB8yF6iWGI,2117
|
|
1185
|
+
vllm/reasoning/qwen3_reasoning_parser.py,sha256=Duw2c5dkQLV3rzTg74ITklAdk-7QlaBM6qnT7BEBkLA,2798
|
|
1186
|
+
vllm/reasoning/seedoss_reasoning_parser.py,sha256=ZCk4i11bWITZI98C-bgrPNvqjbl5wl8qxx0ioFg68CU,958
|
|
1187
|
+
vllm/reasoning/step3_reasoning_parser.py,sha256=lYDaF6W8XZaZyPmJEHxuG0eCIgiHMi4q3VwYN4I6Z1s,4283
|
|
1188
|
+
vllm/third_party/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1189
|
+
vllm/third_party/pynvml.py,sha256=HRQEbE5ZB-AgMIySG4j24hjlEgSGLrNvHJUq7UawCfA,234653
|
|
1190
|
+
vllm/transformers_utils/__init__.py,sha256=yVNs7WNM1UWvqmKYPW-R4D9NXhYWEjKYQKlfcpxL5HI,910
|
|
1191
|
+
vllm/transformers_utils/config.py,sha256=wagMR3gJPxTI2AGS2e213jHZsqTZGnboc1-8GIMpRVk,40633
|
|
1192
|
+
vllm/transformers_utils/config_parser_base.py,sha256=mHcEv_VAIJwK7oihh19ppZsX54cwoZNd95WLSJBmLu4,586
|
|
1193
|
+
vllm/transformers_utils/detokenizer_utils.py,sha256=uWAkqoehhgiYFEo-eOl-6Jk_Fj0B7kZRj35q7fDi5PY,7645
|
|
1194
|
+
vllm/transformers_utils/dynamic_module.py,sha256=LOrUwP1BGbCMJYLDrI4i7a7L5OkP-iDj32OcxCGNcRA,1852
|
|
1195
|
+
vllm/transformers_utils/processor.py,sha256=ibI67bRqUWvoGoQGn4aeEV6RK5TlWIotRs02eP5pIxI,10407
|
|
1196
|
+
vllm/transformers_utils/runai_utils.py,sha256=9HH77tPd0HZ9_4nqFUIgk_yQcJml68NWqH15gyF1Wk0,3373
|
|
1197
|
+
vllm/transformers_utils/s3_utils.py,sha256=PVHoFzIOC435t8qJ3Q8HqAohaYPzlntTCiZ4KdP0xyA,2866
|
|
1198
|
+
vllm/transformers_utils/tokenizer.py,sha256=6q8EtLAy85I7oklDgZzQho-a8pRnbjJGkzRxTNmWDE8,10377
|
|
1199
|
+
vllm/transformers_utils/tokenizer_base.py,sha256=u218Bm6E858vGZOD4ALY2MB1SZKfhdIKQZ-eUo_csUQ,4138
|
|
1200
|
+
vllm/transformers_utils/utils.py,sha256=OPUKnFxGOm6Em1iuZ8oc-Oev7GGYiKeasaTPuIiOPQA,3005
|
|
1201
|
+
vllm/transformers_utils/chat_templates/__init__.py,sha256=U1sUyX9swSjxaULlg0B6rSroU5H8upeyInuHsF74SEE,208
|
|
1202
|
+
vllm/transformers_utils/chat_templates/registry.py,sha256=GSZPdDhczCDy58WjVI7wCcMLbVpJ956ectfCW6EQz2I,2328
|
|
1203
|
+
vllm/transformers_utils/chat_templates/template_basic.jinja,sha256=DMH0156UMA7eoJelXKUMEDzB-SigjbyCOBxIu9OyFJE,78
|
|
1204
|
+
vllm/transformers_utils/chat_templates/template_blip2.jinja,sha256=ltMbjFdK7T4HUcN_OQaX4hj2r0PGlS1EJ9zhSlnTz1c,332
|
|
1205
|
+
vllm/transformers_utils/chat_templates/template_chatml.jinja,sha256=CKxCWf_KemM_DntV70Hf03WNkDvxznolyW-03SJJw54,370
|
|
1206
|
+
vllm/transformers_utils/chat_templates/template_deepseek_vl2.jinja,sha256=WX32uOZ7h8_xqrWvmsI5R-6Ns8ZcXVn74CKB7FJOifA,785
|
|
1207
|
+
vllm/transformers_utils/chat_templates/template_fuyu.jinja,sha256=hzdsPgeUMaZnd5L23QPiz2oC6_wMBy5WgZkXMVs3Dgo,85
|
|
1208
|
+
vllm/transformers_utils/chat_templates/template_minicpmv45.jinja,sha256=00aDdLodQQOp3g_FfnJOhCi5_PnVCgx9Vloo4CqDVqI,4295
|
|
1209
|
+
vllm/transformers_utils/configs/__init__.py,sha256=JnIQ6foUckOfrrtS-TrLGUuK4AWjHpmefPo5nZeNjLQ,2747
|
|
1210
|
+
vllm/transformers_utils/configs/arctic.py,sha256=8WAZRegtPG1_qaFIplNemJJLlCLHBYB3p3m8ZR5co88,9053
|
|
1211
|
+
vllm/transformers_utils/configs/chatglm.py,sha256=TqBRltbV4V7NTnWe8a4nsrfBxXOqB0jBwjNiTkZtEPo,2941
|
|
1212
|
+
vllm/transformers_utils/configs/deepseek_v3.py,sha256=krzlg66478MpOLwvCwJxsQy7USxcNUgvsff5xQV3bgQ,3463
|
|
1213
|
+
vllm/transformers_utils/configs/deepseek_vl2.py,sha256=BwZtrbgFNLRHyOu-yMpOS8uGIFamH8_DAWxw8RtzFJA,7296
|
|
1214
|
+
vllm/transformers_utils/configs/dotsocr.py,sha256=wAXzduAJr6O378ykwU6Dgd15-KEOBBQOOX5xu_dXjtw,2488
|
|
1215
|
+
vllm/transformers_utils/configs/eagle.py,sha256=ZBCLYo90dTcEcs9U50SBnga_-2o0f6Z2OUPYKMfUcLE,3160
|
|
1216
|
+
vllm/transformers_utils/configs/falcon.py,sha256=vKXtykJL5NGzcDFfSnE532vBV5KLrQvOKm7v5P58y-Y,2986
|
|
1217
|
+
vllm/transformers_utils/configs/jais.py,sha256=Cd5AgPvUjVFykcarwLXt6eBZldNAx3Gn_67TLDYQA0k,10416
|
|
1218
|
+
vllm/transformers_utils/configs/kimi_vl.py,sha256=xXtkLgTdOt5ZgSxva36iLzgZqqklIoiHaoJhCNgJyVw,1486
|
|
1219
|
+
vllm/transformers_utils/configs/medusa.py,sha256=ZZcus4c6s4A1iTOPCR2bwzJpSHKsms98dycjVpmoi2E,2012
|
|
1220
|
+
vllm/transformers_utils/configs/midashenglm.py,sha256=JKW3CXlQTMlDkjD4lxiolBwxo9bL3Eep17VVSkZzan0,3665
|
|
1221
|
+
vllm/transformers_utils/configs/mistral.py,sha256=6siObSuQP6pRijQufGIL-ARbyCooOKg8gzkKlahTB_g,5751
|
|
1222
|
+
vllm/transformers_utils/configs/mlp_speculator.py,sha256=2it7HgAv-ZqGDLoE7q66oxXjk8R_mBdnGw31_TVXI7w,2500
|
|
1223
|
+
vllm/transformers_utils/configs/moonvit.py,sha256=Egyjh8mvpzPlX-RmbfDf8ZmeBe7K9fqimYX-QgK9NrQ,1272
|
|
1224
|
+
vllm/transformers_utils/configs/nemotron.py,sha256=ykEscgI_96g5NuKcHIfZQgfU03BX-K7k5MPwXBalJlY,9041
|
|
1225
|
+
vllm/transformers_utils/configs/nemotron_h.py,sha256=TQFOKLOEAJpgWcJp9wf88OvOGhJyIoE2fYHPNeFoIbg,12235
|
|
1226
|
+
vllm/transformers_utils/configs/nemotron_vl.py,sha256=pa78Qz3-ZVwzC_7NDP53CX26ef5iYQJxIaLCpvY_XHE,2151
|
|
1227
|
+
vllm/transformers_utils/configs/olmo3.py,sha256=B7z-xZOp1WPqMNcDcAgqQ8xcWsa3_A_bpeXCI7veV4k,2701
|
|
1228
|
+
vllm/transformers_utils/configs/ovis.py,sha256=rd9b7wrJJ3PWN8e_1-6Wdvrvh0Z2tRy7ka_STa1MKck,7711
|
|
1229
|
+
vllm/transformers_utils/configs/qwen3_next.py,sha256=UVHJD5CkVcxhRKdc-GUhJ7OD1l63y9b25dbndxX_oPw,14666
|
|
1230
|
+
vllm/transformers_utils/configs/radio.py,sha256=2TNJtUmijKEzXuaYQAtIpyOumPRC13DVGep5utX_mp4,3796
|
|
1231
|
+
vllm/transformers_utils/configs/step3_vl.py,sha256=FCNUr1iCCw4si_VGfwA2fmAYmY_o2kr_J1qySNiFhGo,4500
|
|
1232
|
+
vllm/transformers_utils/configs/ultravox.py,sha256=ZeNuuHkTGbfov6zLRUf8uBiJtSRubtLbLuEPz93cZ_w,4894
|
|
1233
|
+
vllm/transformers_utils/configs/speculators/__init__.py,sha256=48Vcuw16i9R99vM3iDVkRkX107yJtFeTtdWgLQE-XFg,107
|
|
1234
|
+
vllm/transformers_utils/configs/speculators/algos.py,sha256=Zg1BJQ_ZeJPgEaNR_55xdggmd9TQUdZxuwenzvzoVOw,1057
|
|
1235
|
+
vllm/transformers_utils/configs/speculators/base.py,sha256=QRrN0mE_cE8iIogUmpb_Mz2CjVpeNHTdv9qwgwkvfuE,4428
|
|
1236
|
+
vllm/transformers_utils/processors/__init__.py,sha256=6-W37BhULZUjbu3aydrGxalPs4scPm2T7zzI6E86dik,644
|
|
1237
|
+
vllm/transformers_utils/processors/deepseek_vl2.py,sha256=K3a2z1wUEz2c13A5nuzP76eghWBbO8r2VSVeCX24chM,14565
|
|
1238
|
+
vllm/transformers_utils/processors/ovis.py,sha256=DAzKptRfKcV7wGorJQxMIiZZ-rMMRtGKg-SEoyERUzM,18929
|
|
1239
|
+
vllm/transformers_utils/processors/ovis2_5.py,sha256=F-wW_Atb18w6fDV7t6VYz6X4PydU_jKaOzD41ygCbMI,19852
|
|
1240
|
+
vllm/transformers_utils/tokenizers/__init__.py,sha256=dN6RDCTGacE-3exN7VSZHlEcHhu__4dQM6Ry0lQ43w8,372
|
|
1241
|
+
vllm/transformers_utils/tokenizers/mistral.py,sha256=fgkUnqdeRwf8hESzvScwaWSu_f6I8WObGTAJi0TNaLc,20538
|
|
1242
|
+
vllm/triton_utils/__init__.py,sha256=nYPnk0WE8v-eTi8lnnMXFWadX-uJkD8MuFLj9bFLEEE,543
|
|
1243
|
+
vllm/triton_utils/importing.py,sha256=I9_neeKeLN3rClJ7sJRQyFkf0YE0qwoirMMWytBR2ck,3475
|
|
1244
|
+
vllm/usage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1245
|
+
vllm/usage/usage_lib.py,sha256=qFy6_zSdBRAfeA4vdYFUDi5kDZqeY5o0Yaw4mjEHX-Y,9020
|
|
1246
|
+
vllm/utils/__init__.py,sha256=FWRJJtCHfZsRaU_ANilxenpH1vmVr97xQXRu04XNTOQ,122102
|
|
1247
|
+
vllm/utils/deep_gemm.py,sha256=h73jZKA2o5HchnQ2EYYqlViT9tP3eRqscrNSlayxUfA,11542
|
|
1248
|
+
vllm/utils/flashinfer.py,sha256=TfLS1nENjvYK1_-BY5SWXxMvo2v74qJycCFPd1k5loI,14778
|
|
1249
|
+
vllm/utils/jsontree.py,sha256=j1zI3Rv-n28PP0pv4v1y3PYFVRw-o3Eg5oXYc7f26Qk,3963
|
|
1250
|
+
vllm/utils/tensor_schema.py,sha256=W0irinYZWB3l1mcz4NLCQKySXr9Ql2-dMtvnws8b5QU,9275
|
|
1251
|
+
vllm/v1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1252
|
+
vllm/v1/cudagraph_dispatcher.py,sha256=j5S2LVZxHFeNNJ4qRlc2FWF2Pbybd-rAuWiuS-DltN8,5995
|
|
1253
|
+
vllm/v1/kv_cache_interface.py,sha256=vw1z2zRCtb_pbFWMNs1WAegArqmhUIyYn_5LVOjVzpg,14150
|
|
1254
|
+
vllm/v1/outputs.py,sha256=uFnePD4FfVw4zgULNbK7WyIqQFDb2D9Dw80fOxUBgSQ,5021
|
|
1255
|
+
vllm/v1/request.py,sha256=vkV3BnV_5nNMWhvZ8yYXIiduwnYW2smW1rHDPKzfpew,9124
|
|
1256
|
+
vllm/v1/serial_utils.py,sha256=8XdQfYts2LYwi-R8W1B8iDKXa3ZpieLCu8I8R7hQ63Y,17165
|
|
1257
|
+
vllm/v1/utils.py,sha256=U0ggvq3Wve0B9sssAXmEPB-AqNk2siTD_A6JgmirOBo,13505
|
|
1258
|
+
vllm/v1/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1259
|
+
vllm/v1/attention/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1260
|
+
vllm/v1/attention/backends/cpu_attn.py,sha256=tb6D9OLuEo4RfQD5Y1fryys44M6zBU6-1uOHYEmzg98,34981
|
|
1261
|
+
vllm/v1/attention/backends/flash_attn.py,sha256=EJkQ1jIAueL4KvE9vx3f96IdOwjXeSkRyJZGskOxRJM,33757
|
|
1262
|
+
vllm/v1/attention/backends/flashinfer.py,sha256=aEwOZ-AP8yVEnvrth9pW7bNYIGXPN7yJzL1MABkOGQc,52054
|
|
1263
|
+
vllm/v1/attention/backends/flex_attention.py,sha256=8V3uDCifDnynknj11HoZBIST7d-4ukHIX-FipDJLLFA,34922
|
|
1264
|
+
vllm/v1/attention/backends/gdn_attn.py,sha256=iAUhhcuAkhN3MskwR_CogWIiQm8p6eLZE-rP-oLL_Eg,14806
|
|
1265
|
+
vllm/v1/attention/backends/linear_attn.py,sha256=lpTaOYUcWKjpHSVnPsmrWcLK7_S5_5yEsXmDbDM5MCA,2381
|
|
1266
|
+
vllm/v1/attention/backends/mamba1_attn.py,sha256=PVnvEFignF_JklZ9Zcdc15zHgGnys4Py3r_uCZkkdZI,3004
|
|
1267
|
+
vllm/v1/attention/backends/mamba2_attn.py,sha256=SNM_pQNLSjL7KYVP7HETkALKImrON1qTZgXp_4OPig8,9848
|
|
1268
|
+
vllm/v1/attention/backends/mamba_attn.py,sha256=COmlM82bnFLJCbq1UAK4URYO5I6X0jHzIyD0MqVGwtc,1963
|
|
1269
|
+
vllm/v1/attention/backends/pallas.py,sha256=gs5hqJR1cSk6Z-SoZjs6xRjaWze_orUETYT8gEeKNQ8,16018
|
|
1270
|
+
vllm/v1/attention/backends/rocm_aiter_fa.py,sha256=Hz02713meBurJVT0Hw7cCee9nSGZg5wwlkkStrjXEC4,21295
|
|
1271
|
+
vllm/v1/attention/backends/rocm_attn.py,sha256=VLIW1GEQQSlrHQHhKbPteJlpxvfbQ5zSLM_8M9-gWtw,16874
|
|
1272
|
+
vllm/v1/attention/backends/short_conv_attn.py,sha256=SKtbbchpWf9B5Cvnon1r3sdkISN4z8wyN9LLsXzACMw,3528
|
|
1273
|
+
vllm/v1/attention/backends/tree_attn.py,sha256=tzoxGEUFFghC7Axzq84WK7OSD5A47HgJ8wtH4IEv-QI,17090
|
|
1274
|
+
vllm/v1/attention/backends/triton_attn.py,sha256=xYrOeTCC9L272Ab7D-8SxbMp_9-lIJVQOZPMM749UV0,14237
|
|
1275
|
+
vllm/v1/attention/backends/utils.py,sha256=Go80n6XX_jRV5E1NRGcvgVyUTlJE3CDAgO01jmqNDlc,39608
|
|
1276
|
+
vllm/v1/attention/backends/xformers.py,sha256=8vL1AhVnYAQ7wtRy7wh1oJ8KN39ABr2gE1zQkoVHhcs,16355
|
|
1277
|
+
vllm/v1/attention/backends/mla/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1278
|
+
vllm/v1/attention/backends/mla/common.py,sha256=4jr3SyeglENI8T0bQbOMmJnxCPmobeF18XBs3IGS9bQ,74400
|
|
1279
|
+
vllm/v1/attention/backends/mla/cutlass_mla.py,sha256=tjDlmZ9GgKgejltTg6Wll8Lr9JKmJAgBomuRD4YUqgE,8785
|
|
1280
|
+
vllm/v1/attention/backends/mla/flashattn_mla.py,sha256=bzLsA5lwv8Vkh2mA_ZUCZsaQEWlIk01__1_9-ZdoNPs,11217
|
|
1281
|
+
vllm/v1/attention/backends/mla/flashinfer_mla.py,sha256=FmEKgSMBEJN5nWfJovpumO6FK37KEdgDoyWN92T0pFs,4095
|
|
1282
|
+
vllm/v1/attention/backends/mla/flashmla.py,sha256=iPXuLkhb-ngD2KjclNZx6E-0dK69XMH2D15Kx_owEUo,8008
|
|
1283
|
+
vllm/v1/attention/backends/mla/flashmla_sparse.py,sha256=HrNXKqiSPuprJi0Vs7rQrOQZ53NvqpjdoiJs5PwC-9s,20933
|
|
1284
|
+
vllm/v1/attention/backends/mla/indexer.py,sha256=Vq_9c9Ur4Sv8zbzs4lUGB3H4hnpeWm4PeALIMCnJXmI,13129
|
|
1285
|
+
vllm/v1/attention/backends/mla/rocm_aiter_mla.py,sha256=4EGqUK7Y2AGEriJG_7uiCsoKDAV0v3wIuOGyMczmNH0,10379
|
|
1286
|
+
vllm/v1/attention/backends/mla/triton_mla.py,sha256=Adwa9Wl_LrF_IF5EFjPe_TwPvn54CINt_u8k_S1YhLo,6644
|
|
1287
|
+
vllm/v1/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1288
|
+
vllm/v1/core/block_pool.py,sha256=jNSy_jWibc-Kp9jo7BaSK3zT5n4CyAACaQLa2bEnQ2g,16418
|
|
1289
|
+
vllm/v1/core/encoder_cache_manager.py,sha256=AGFx9Ex5KXmnEuL3ys44UieZ0dBcnRxl2Qu67nTfFTM,13632
|
|
1290
|
+
vllm/v1/core/kv_cache_coordinator.py,sha256=GSha9ADAUlsIVTiKemNREewBv3KKyrqbcvvXk-04stw,18764
|
|
1291
|
+
vllm/v1/core/kv_cache_manager.py,sha256=8C0dCVNluDxfy57_FKyIfzUjRJW4cY8kcYohgkTdVZA,16528
|
|
1292
|
+
vllm/v1/core/kv_cache_utils.py,sha256=CCS-rgmjqPrrVOjgYF0WYQReNKM6ICbeU35oSaTHjuQ,54223
|
|
1293
|
+
vllm/v1/core/single_type_kv_cache_manager.py,sha256=kMlOW3VVr4fNYICzFOn8Jy3Z-XSfhLy_ah19bXGLTEE,28765
|
|
1294
|
+
vllm/v1/core/sched/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1295
|
+
vllm/v1/core/sched/async_scheduler.py,sha256=-YLUrdcsi2lQA6KnchxTH51Dge6CEpoUil5ECrJ4ltc,1771
|
|
1296
|
+
vllm/v1/core/sched/interface.py,sha256=igiz4ZBJhko2kZtj0iZaPwvNqqtoxammTTWLBxR4kMc,6102
|
|
1297
|
+
vllm/v1/core/sched/output.py,sha256=Wkk0y76WkrxYzVz7kr9ToUCZhn9m64IVncm2yDqIfA8,6301
|
|
1298
|
+
vllm/v1/core/sched/request_queue.py,sha256=c_fhiQL-oeOPVAoR_oKJppE2TjMRosabUDBQZgfbbI4,7533
|
|
1299
|
+
vllm/v1/core/sched/scheduler.py,sha256=NXrEFKW12ow0I5hN0f3ehgWEoNQXwwrC7iWHTqnloEw,60858
|
|
1300
|
+
vllm/v1/core/sched/utils.py,sha256=3v5d9IMvU2vfgnZNfRar2kPbi9nHy5Pr5jHfOtA_fOs,2348
|
|
1301
|
+
vllm/v1/engine/__init__.py,sha256=1M8x44efzCGYd3gDT6-wYhZNdkmnMCFsM6nuTgpd_qU,6080
|
|
1302
|
+
vllm/v1/engine/async_llm.py,sha256=Xw5hwt7k_oruO6JwXflLUGmF0EJCfPbQglzkNpdRbok,30332
|
|
1303
|
+
vllm/v1/engine/coordinator.py,sha256=x60JQ_0GnhRvFMk1_A8_6ynglBv5JM4jFldc_mojcNE,16060
|
|
1304
|
+
vllm/v1/engine/core.py,sha256=RXNWPZJsr-Dx4R67JehizjvHIq-aJEJd7HkbnUPPvt0,53666
|
|
1305
|
+
vllm/v1/engine/core_client.py,sha256=Vz8h1KGjYfsyPErzB1uhXxafKKrD2zq0EO-auRncnxc,55226
|
|
1306
|
+
vllm/v1/engine/detokenizer.py,sha256=9MGlKO17XXAh4r9iEOgZskc6cY-KJYmgQeBLebw017U,13161
|
|
1307
|
+
vllm/v1/engine/exceptions.py,sha256=OurXOSPqCuoLWzIZ2vi5ahe9NnyGESnO-HZqlvSB-Xs,731
|
|
1308
|
+
vllm/v1/engine/llm_engine.py,sha256=OvMaJNCHCaO7QAHRZlyLyJU6PMK2IkH3WPQzr6y9avo,14756
|
|
1309
|
+
vllm/v1/engine/logprobs.py,sha256=lEStN84KAzoy8JPbmxEeuPuoUwBz1zRRSmeg4JMy4cw,7242
|
|
1310
|
+
vllm/v1/engine/output_processor.py,sha256=GZnmh6GDzkt7A5tMU1e3PwrQr9iltSOD7x99HVYTJj4,23888
|
|
1311
|
+
vllm/v1/engine/parallel_sampling.py,sha256=uViFaH5NFxMQfWBz8rOdRZ5eIb_ZHMlJu3aCuhq2TIM,4834
|
|
1312
|
+
vllm/v1/engine/processor.py,sha256=hfRsBl7LHPiykjiDRzFGpynDsFVjVrcmzB36yd8fYSM,23913
|
|
1313
|
+
vllm/v1/engine/utils.py,sha256=i0PuHOceUx5MasqAqKBkibFdVQvyurJeBCJmt7QpwcA,35059
|
|
1314
|
+
vllm/v1/executor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1315
|
+
vllm/v1/executor/abstract.py,sha256=0arnEFa45Vvrz0HNzQes8UhMUR-EDl9X8id7MG6e-Qc,5687
|
|
1316
|
+
vllm/v1/executor/multiproc_executor.py,sha256=rZONNBFTMzBHC6L9tjxiKcPdoGsZO56hWsmTJ5LgzRY,29353
|
|
1317
|
+
vllm/v1/executor/ray_distributed_executor.py,sha256=GVvON6gLKnKCiS2BXpttz5OUi44Mt8bzaghCi9TdiVU,4062
|
|
1318
|
+
vllm/v1/executor/utils.py,sha256=lplFvpmu0CAtM_rzOHSEQshr-QuO0dOb95VZlr72meI,887
|
|
1319
|
+
vllm/v1/kv_offload/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1320
|
+
vllm/v1/kv_offload/abstract.py,sha256=IO2RyOgoUjIAkl3a7bPDVa_3l5WMHUbnGe5GCe-MimI,5351
|
|
1321
|
+
vllm/v1/kv_offload/backend.py,sha256=foOEeZ5BV7LdiuX6H7KiNBW74wCrjszxBGGkCxmExFM,2935
|
|
1322
|
+
vllm/v1/kv_offload/cpu.py,sha256=jKP3RsrVUEuRu0yGltJfWq5uwrthbJTenyQbf2h9DwI,3197
|
|
1323
|
+
vllm/v1/kv_offload/factory.py,sha256=vT9ypMYmMIoq1qJdkKH0a98kVHKCwKk0VOoVA0BPN88,2056
|
|
1324
|
+
vllm/v1/kv_offload/lru_manager.py,sha256=P5JymsUKqiLoaWKaWkcrr8RinP4u6-ZEvH4rcM0Hxwc,5155
|
|
1325
|
+
vllm/v1/kv_offload/mediums.py,sha256=8i5qik1oKldR3Gyf7S5veHM5h1prPZVR4xN05HSOUKQ,880
|
|
1326
|
+
vllm/v1/kv_offload/spec.py,sha256=38bubj3zVx1Nwdf3YBDZCDT2HB8V6Ay0TWkxguVFlH8,2003
|
|
1327
|
+
vllm/v1/kv_offload/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1328
|
+
vllm/v1/kv_offload/backends/cpu.py,sha256=HSUwXJ2rABsDw7yYAsx2t_RWzRzb0fT9vIKFhDePWNI,2311
|
|
1329
|
+
vllm/v1/kv_offload/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1330
|
+
vllm/v1/kv_offload/worker/cpu_gpu.py,sha256=Mz0_XhHlIiIeWcZRyx502mTwNZ88-TMREwaQy9dbkns,6909
|
|
1331
|
+
vllm/v1/kv_offload/worker/worker.py,sha256=QadSZx8kbKXDAfFTRPUzTe0z3y8H366-PH0JYXSripA,4782
|
|
1332
|
+
vllm/v1/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1333
|
+
vllm/v1/metrics/loggers.py,sha256=fl1w6pSI4qfF8dQNrta9-VbP4KFfJnyurYjZ1291C_o,31940
|
|
1334
|
+
vllm/v1/metrics/prometheus.py,sha256=7OX8teYEAtWHc0w2I61fhm6RZ5zYTIzsxj_5SZYUAMY,2842
|
|
1335
|
+
vllm/v1/metrics/ray_wrappers.py,sha256=vGaoDwXmRLE4dFCgI_GOpSRwOIs0uWWOAlslwN2nPfo,5471
|
|
1336
|
+
vllm/v1/metrics/reader.py,sha256=9rx29TV3t8P49Hx4a_F1LB2WHTwFDHkVc5v3utoEOFg,8702
|
|
1337
|
+
vllm/v1/metrics/stats.py,sha256=mEagAaSNXqSzxdqWCizXD4ppAo0wZf881zuPCItdvDU,10182
|
|
1338
|
+
vllm/v1/pool/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1339
|
+
vllm/v1/pool/metadata.py,sha256=uTC6kmLYY0FS8VACsdxgO5XOr-VR5GZq-P3hzjXqkg8,2919
|
|
1340
|
+
vllm/v1/sample/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1341
|
+
vllm/v1/sample/metadata.py,sha256=H6Wj5GnL_vxFqq__NMYoTM2BEFb2fnsHBpuJ42D8wiM,1110
|
|
1342
|
+
vllm/v1/sample/rejection_sampler.py,sha256=Vugp7DztUQgE6NaLP4b1nbxhbYr_SFRObsw5gzy9rIw,22728
|
|
1343
|
+
vllm/v1/sample/sampler.py,sha256=NyD7_VnB8GSmK44EiewENkaBiLafi464TS1i66MfORI,11400
|
|
1344
|
+
vllm/v1/sample/logits_processor/__init__.py,sha256=oPT6ur7KSM_zeBec_h0c7LUdwXCfBcMjGrUvynDsg3w,10935
|
|
1345
|
+
vllm/v1/sample/logits_processor/builtin.py,sha256=KYr2Yt3pZ3cdgNyuSvAwOlzhQ_nvf85mDXgVtP-HRXM,11080
|
|
1346
|
+
vllm/v1/sample/logits_processor/interface.py,sha256=N3t2wMxWaNcoVeWxWbIQG7WzuUYdzFlBntNEznSRJQY,3004
|
|
1347
|
+
vllm/v1/sample/logits_processor/state.py,sha256=tvM6iffbJRCxnTLjPmLn4Wi-uLwVYbcde8AH6RV5ggg,5819
|
|
1348
|
+
vllm/v1/sample/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1349
|
+
vllm/v1/sample/ops/bad_words.py,sha256=JOnrJXq2RD45cA7cmePX2ktRjBg_1uJQsPqCc0gf2Vw,1191
|
|
1350
|
+
vllm/v1/sample/ops/logprobs.py,sha256=E5pKlavblNL2n9CNhodL34_F4iAVaXA4f6SfRSWzd9w,973
|
|
1351
|
+
vllm/v1/sample/ops/penalties.py,sha256=B3IZcrvPBxl2jzTVYlIh3Ty2VSI5y4CD6he1B3Nlkx8,1534
|
|
1352
|
+
vllm/v1/sample/ops/topk_topp_sampler.py,sha256=U27QXky_Lu-IF9V8BP0OQkRB9LBe5Sgs8HJyLSWSsgM,11625
|
|
1353
|
+
vllm/v1/sample/tpu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1354
|
+
vllm/v1/sample/tpu/metadata.py,sha256=4UVHpx8QO2lNOnMON7ZY9oSfVzhjRemOa0_w3C05OeI,4695
|
|
1355
|
+
vllm/v1/sample/tpu/sampler.py,sha256=wQnkNmxnZn6vIY1PMSL2CQwYeOWd2eF-IWTLjjWcyH4,7702
|
|
1356
|
+
vllm/v1/spec_decode/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1357
|
+
vllm/v1/spec_decode/eagle.py,sha256=ooV_06OmwmGJKzslZVtRNCg5mg06dj13_L1S1xBbbr8,47298
|
|
1358
|
+
vllm/v1/spec_decode/medusa.py,sha256=NK38TGMCRGMW04kD7O9NtkHh8K4UwSmTi92y7B2pYY4,2359
|
|
1359
|
+
vllm/v1/spec_decode/metadata.py,sha256=I3rD5wVyLs5ID9LnIN3E5hy0lu5Eetz5DGcxstQMeR0,2257
|
|
1360
|
+
vllm/v1/spec_decode/metrics.py,sha256=7EXCrHqbBsHZC_r8YTl46O0ohjJtQmS801Gy_P6B50U,7878
|
|
1361
|
+
vllm/v1/spec_decode/ngram_proposer.py,sha256=GaIrqg_bXr_2wy7-JgZPur9XAzipzai8Kq6-24aOTgE,11412
|
|
1362
|
+
vllm/v1/spec_decode/utils.py,sha256=EgqNXyhwHkoaxklEttaN4sPh53LVXcpstD1T0yjjnos,591
|
|
1363
|
+
vllm/v1/structured_output/__init__.py,sha256=pXlJvK1A_MOwD4osUEsnkIXx5q9TsbwbTH-cZVsEUu8,12945
|
|
1364
|
+
vllm/v1/structured_output/backend_guidance.py,sha256=ctxDCozseo_zFdjxmz5yuRBHXt2-Zmljc6hwVBSe-rk,8804
|
|
1365
|
+
vllm/v1/structured_output/backend_lm_format_enforcer.py,sha256=6-7pL5RTTB6uGtu5Nd4cyXsEs0S07e9sdHJmq775IJE,6433
|
|
1366
|
+
vllm/v1/structured_output/backend_outlines.py,sha256=8dcSFNzQVeb5sskcihxUUeuH8ycIKlBLk2GM0pOussc,12226
|
|
1367
|
+
vllm/v1/structured_output/backend_types.py,sha256=WSSoKU5aqW2CkRVJ4AKRUpFbMLbei1-U1jS7ioITEsA,3810
|
|
1368
|
+
vllm/v1/structured_output/backend_xgrammar.py,sha256=dgw6SIAnRk_1MMOc0cV4QKYvnvm1FWyCmV9Aol86AT8,12717
|
|
1369
|
+
vllm/v1/structured_output/request.py,sha256=ro2LinC3tkaVzyhx7JqJq_Qk6bnL8s6TERphQrSy0R0,3223
|
|
1370
|
+
vllm/v1/structured_output/utils.py,sha256=VwG2nhAJzGye2BRDiDoHQbDm9Ug-a9dh2cGDYo7K66U,16548
|
|
1371
|
+
vllm/v1/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1372
|
+
vllm/v1/worker/block_table.py,sha256=lrUP7WF7rYOXWx16qeEWMRcZDxUPEZh7y5SFTZy7iaQ,8550
|
|
1373
|
+
vllm/v1/worker/cpu_model_runner.py,sha256=v1yAC81-ZXLwxxlVHSb-MRFBVJN7O-LJf_-4yLXuOeM,6494
|
|
1374
|
+
vllm/v1/worker/cpu_worker.py,sha256=3f2MEP4Ez6clTvbRWiwQt9fQ6x6obxnIvWIiBL-U0uY,6829
|
|
1375
|
+
vllm/v1/worker/gpu_input_batch.py,sha256=rkx12-5qbXaM55ob8fFIqiWQyr1RDQ4B5Ib62EU5Or0,38119
|
|
1376
|
+
vllm/v1/worker/gpu_model_runner.py,sha256=6mt7_kCCNJ6ABC30gBx--eGMgNHDh57rasbpxHYwNXQ,195684
|
|
1377
|
+
vllm/v1/worker/gpu_ubatch_wrapper.py,sha256=bU4awilQqbtBiasdcc4GGpdYXW6RS384SGwmUZj68u4,17263
|
|
1378
|
+
vllm/v1/worker/gpu_worker.py,sha256=4Ggz6KUkfepIjwZweLn2ThKEypyXskiyeYUrBG6BUlY,31864
|
|
1379
|
+
vllm/v1/worker/kv_connector_model_runner_mixin.py,sha256=XRwxPLoLGMaYXFLCycv61IYZU9XrkukT7QuVAqrLO3I,5425
|
|
1380
|
+
vllm/v1/worker/lora_model_runner_mixin.py,sha256=UUr_zxHCHUAunARFPbw6njpOTlSAOH6snS3TeZhppv0,6972
|
|
1381
|
+
vllm/v1/worker/tpu_input_batch.py,sha256=rOxQ0yOZqXs-wjHFX2Mz5E6AFe_HkagpTaV6KrkFqAs,26160
|
|
1382
|
+
vllm/v1/worker/tpu_model_runner.py,sha256=P68PLDvAt8Y1MkzZcjvSZnVlMEsO5OuUQQZ4OHAdc0c,91863
|
|
1383
|
+
vllm/v1/worker/tpu_worker.py,sha256=ZAmrLk7TBQITU5qP-qHq4B5UpGdgri-SFq0rqV5YUvA,14792
|
|
1384
|
+
vllm/v1/worker/ubatch_splitting.py,sha256=5KDDrBIsHGKohhiCxM7ih5Q193XgowctVTmGgu_1InU,7528
|
|
1385
|
+
vllm/v1/worker/ubatch_utils.py,sha256=V4mSQifZVXWKelMQYk2u7LG6JyqrmhhuWcWEvYFNQ-M,790
|
|
1386
|
+
vllm/v1/worker/ubatching.py,sha256=Ib47dgMqNnf1_y83-Fz5QKoYuC1t8Qx3WV1cvlMmx0k,7902
|
|
1387
|
+
vllm/v1/worker/utils.py,sha256=LG8_1YacZhZsh1H2om2qtDUWSWXjdUdx_iBRHp2wZDQ,13148
|
|
1388
|
+
vllm/v1/worker/worker_base.py,sha256=X-XvcP0lzixzgizEv9p4yn2m9Fex4Efl39OlOuFg8A4,2048
|
|
1389
|
+
vllm/v1/worker/xpu_model_runner.py,sha256=Xcaevr_4eUUV6lp8Dc1MIMwId27XIBSm4qdm8qRggi8,1561
|
|
1390
|
+
vllm/v1/worker/xpu_worker.py,sha256=Rli9bmjJdk81qmF5PVfLl21onWsnHVKP_RJfqIEAmDI,8151
|
|
1391
|
+
vllm/vllm_flash_attn/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1392
|
+
vllm/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1393
|
+
vllm/worker/worker_base.py,sha256=JMG2-YTJ1ZhSKxTVpvadrTnX-iPW2UGLwtoF8vmbcSM,11808
|
|
1394
|
+
vllm_cpu-0.11.0.post2.dist-info/METADATA,sha256=S6wrjZlHPQP1tpadftt0Ps8tiC1mTGMbq1K9ML9i1nQ,16581
|
|
1395
|
+
vllm_cpu-0.11.0.post2.dist-info/WHEEL,sha256=IoFti0xAvoDtAxuPJyI4RJkGn0ThylEbxytRcNSoLaU,113
|
|
1396
|
+
vllm_cpu-0.11.0.post2.dist-info/entry_points.txt,sha256=ErfiCUEEMrGDD3jBwf8c54AolBCFv7qrc8Ix9iqzzfs,184
|
|
1397
|
+
vllm_cpu-0.11.0.post2.dist-info/top_level.txt,sha256=fAgb8Pt4zQoKTUA3ZnKEIgcjh0L97_dwEjYDTL5MEEo,5
|
|
1398
|
+
vllm_cpu-0.11.0.post2.dist-info/RECORD,,
|