vllm-cpu-amxbf16 0.9.1__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 +53 -0
- vllm/_custom_ops.py +1828 -0
- vllm/_ipex_ops.py +244 -0
- vllm/_version.py +34 -0
- vllm/adapter_commons/__init__.py +0 -0
- vllm/adapter_commons/layers.py +16 -0
- vllm/adapter_commons/models.py +106 -0
- vllm/adapter_commons/request.py +26 -0
- vllm/adapter_commons/utils.py +93 -0
- vllm/adapter_commons/worker_manager.py +39 -0
- vllm/assets/__init__.py +0 -0
- vllm/assets/audio.py +45 -0
- vllm/assets/base.py +41 -0
- vllm/assets/image.py +34 -0
- vllm/assets/video.py +115 -0
- vllm/attention/__init__.py +20 -0
- vllm/attention/backends/__init__.py +0 -0
- vllm/attention/backends/abstract.py +308 -0
- vllm/attention/backends/blocksparse_attn.py +461 -0
- vllm/attention/backends/cpu_mla.py +307 -0
- vllm/attention/backends/dual_chunk_flash_attn.py +1498 -0
- vllm/attention/backends/flash_attn.py +1003 -0
- vllm/attention/backends/flashinfer.py +1104 -0
- vllm/attention/backends/flashmla.py +244 -0
- vllm/attention/backends/hpu_attn.py +313 -0
- vllm/attention/backends/ipex_attn.py +398 -0
- vllm/attention/backends/mla/__init__.py +0 -0
- vllm/attention/backends/mla/common.py +1385 -0
- vllm/attention/backends/pallas.py +351 -0
- vllm/attention/backends/placeholder_attn.py +400 -0
- vllm/attention/backends/rocm_aiter_mla.py +435 -0
- vllm/attention/backends/rocm_flash_attn.py +975 -0
- vllm/attention/backends/torch_sdpa.py +703 -0
- vllm/attention/backends/triton_mla.py +115 -0
- vllm/attention/backends/utils.py +610 -0
- vllm/attention/backends/xformers.py +802 -0
- vllm/attention/layer.py +468 -0
- vllm/attention/ops/__init__.py +0 -0
- vllm/attention/ops/blocksparse_attention/__init__.py +0 -0
- vllm/attention/ops/blocksparse_attention/blocksparse_attention_kernel.py +433 -0
- vllm/attention/ops/blocksparse_attention/interface.py +239 -0
- vllm/attention/ops/blocksparse_attention/utils.py +246 -0
- vllm/attention/ops/chunked_prefill_paged_decode.py +368 -0
- vllm/attention/ops/flashmla.py +116 -0
- vllm/attention/ops/hpu_paged_attn.py +88 -0
- vllm/attention/ops/ipex_attn.py +195 -0
- vllm/attention/ops/merge_attn_states.py +43 -0
- vllm/attention/ops/nki_flash_attn.py +906 -0
- vllm/attention/ops/paged_attn.py +256 -0
- vllm/attention/ops/prefix_prefill.py +902 -0
- vllm/attention/ops/rocm_aiter_mla.py +100 -0
- vllm/attention/ops/rocm_aiter_paged_attn.py +102 -0
- vllm/attention/ops/triton_decode_attention.py +674 -0
- vllm/attention/ops/triton_flash_attention.py +979 -0
- vllm/attention/ops/triton_merge_attn_states.py +97 -0
- vllm/attention/ops/triton_unified_attention.py +334 -0
- vllm/attention/selector.py +187 -0
- vllm/attention/utils/fa_utils.py +55 -0
- vllm/beam_search.py +87 -0
- vllm/benchmarks/__init__.py +0 -0
- vllm/benchmarks/datasets.py +1185 -0
- vllm/benchmarks/endpoint_request_func.py +381 -0
- vllm/benchmarks/latency.py +168 -0
- vllm/benchmarks/serve.py +1135 -0
- vllm/benchmarks/throughput.py +609 -0
- vllm/benchmarks/utils.py +70 -0
- vllm/collect_env.py +820 -0
- vllm/compilation/__init__.py +0 -0
- vllm/compilation/activation_quant_fusion.py +89 -0
- vllm/compilation/backends.py +563 -0
- vllm/compilation/base_piecewise_backend.py +72 -0
- vllm/compilation/collective_fusion.py +127 -0
- vllm/compilation/compiler_interface.py +544 -0
- vllm/compilation/counter.py +38 -0
- vllm/compilation/cuda_piecewise_backend.py +214 -0
- vllm/compilation/decorators.py +250 -0
- vllm/compilation/fix_functionalization.py +191 -0
- vllm/compilation/fusion.py +618 -0
- vllm/compilation/fx_utils.py +62 -0
- vllm/compilation/inductor_pass.py +115 -0
- vllm/compilation/monitor.py +39 -0
- vllm/compilation/multi_output_match.py +109 -0
- vllm/compilation/noop_elimination.py +137 -0
- vllm/compilation/pass_manager.py +78 -0
- vllm/compilation/sequence_parallelism.py +268 -0
- vllm/compilation/torch25_custom_graph_pass.py +42 -0
- vllm/compilation/vllm_inductor_pass.py +67 -0
- vllm/compilation/wrapper.py +135 -0
- vllm/config.py +4746 -0
- vllm/connections.py +174 -0
- vllm/core/__init__.py +0 -0
- vllm/core/block/__init__.py +0 -0
- vllm/core/block/block_table.py +399 -0
- vllm/core/block/common.py +371 -0
- vllm/core/block/cpu_gpu_block_allocator.py +441 -0
- vllm/core/block/interfaces.py +319 -0
- vllm/core/block/naive_block.py +466 -0
- vllm/core/block/prefix_caching_block.py +1135 -0
- vllm/core/block/utils.py +28 -0
- vllm/core/block_manager.py +521 -0
- vllm/core/evictor.py +157 -0
- vllm/core/interfaces.py +135 -0
- vllm/core/placeholder_block_space_manager.py +100 -0
- vllm/core/scheduler.py +2093 -0
- vllm/device_allocator/__init__.py +0 -0
- vllm/device_allocator/cumem.py +281 -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 +264 -0
- vllm/distributed/device_communicators/base_device_communicator.py +260 -0
- vllm/distributed/device_communicators/cpu_communicator.py +145 -0
- vllm/distributed/device_communicators/cuda_communicator.py +176 -0
- vllm/distributed/device_communicators/cuda_wrapper.py +180 -0
- vllm/distributed/device_communicators/custom_all_reduce.py +304 -0
- vllm/distributed/device_communicators/custom_all_reduce_utils.py +259 -0
- vllm/distributed/device_communicators/hpu_communicator.py +46 -0
- vllm/distributed/device_communicators/neuron_communicator.py +20 -0
- vllm/distributed/device_communicators/pynccl.py +218 -0
- vllm/distributed/device_communicators/pynccl_wrapper.py +341 -0
- vllm/distributed/device_communicators/shm_broadcast.py +585 -0
- vllm/distributed/device_communicators/tpu_communicator.py +103 -0
- vllm/distributed/device_communicators/xpu_communicator.py +55 -0
- vllm/distributed/kv_events.py +356 -0
- vllm/distributed/kv_transfer/README.md +29 -0
- vllm/distributed/kv_transfer/__init__.py +12 -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 +128 -0
- vllm/distributed/kv_transfer/kv_connector/factory.py +128 -0
- vllm/distributed/kv_transfer/kv_connector/lmcache_connector.py +99 -0
- vllm/distributed/kv_transfer/kv_connector/mooncake_store_connector.py +203 -0
- vllm/distributed/kv_transfer/kv_connector/simple_connector.py +329 -0
- vllm/distributed/kv_transfer/kv_connector/utils.py +108 -0
- vllm/distributed/kv_transfer/kv_connector/v1/__init__.py +6 -0
- vllm/distributed/kv_transfer/kv_connector/v1/base.py +283 -0
- vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py +134 -0
- vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py +201 -0
- vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py +1030 -0
- vllm/distributed/kv_transfer/kv_connector/v1/shared_storage_connector.py +384 -0
- vllm/distributed/kv_transfer/kv_connector_agent.py +77 -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 +280 -0
- vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py +280 -0
- vllm/distributed/kv_transfer/kv_transfer_state.py +71 -0
- vllm/distributed/parallel_state.py +1296 -0
- vllm/distributed/tpu_distributed_utils.py +177 -0
- vllm/distributed/utils.py +536 -0
- vllm/engine/__init__.py +0 -0
- vllm/engine/arg_utils.py +1708 -0
- vllm/engine/async_llm_engine.py +1200 -0
- vllm/engine/async_timeout.py +173 -0
- vllm/engine/llm_engine.py +2097 -0
- vllm/engine/metrics.py +629 -0
- vllm/engine/metrics_types.py +94 -0
- vllm/engine/multiprocessing/__init__.py +148 -0
- vllm/engine/multiprocessing/client.py +681 -0
- vllm/engine/multiprocessing/engine.py +460 -0
- vllm/engine/output_processor/__init__.py +0 -0
- vllm/engine/output_processor/interfaces.py +75 -0
- vllm/engine/output_processor/multi_step.py +216 -0
- vllm/engine/output_processor/single_step.py +145 -0
- vllm/engine/output_processor/stop_checker.py +131 -0
- vllm/engine/output_processor/util.py +28 -0
- vllm/engine/protocol.py +317 -0
- vllm/entrypoints/__init__.py +0 -0
- vllm/entrypoints/api_server.py +178 -0
- vllm/entrypoints/chat_utils.py +1299 -0
- vllm/entrypoints/cli/__init__.py +0 -0
- vllm/entrypoints/cli/benchmark/__init__.py +0 -0
- vllm/entrypoints/cli/benchmark/base.py +39 -0
- vllm/entrypoints/cli/benchmark/latency.py +30 -0
- vllm/entrypoints/cli/benchmark/main.py +54 -0
- vllm/entrypoints/cli/benchmark/serve.py +30 -0
- vllm/entrypoints/cli/benchmark/throughput.py +30 -0
- vllm/entrypoints/cli/collect_env.py +35 -0
- vllm/entrypoints/cli/main.py +65 -0
- vllm/entrypoints/cli/openai.py +205 -0
- vllm/entrypoints/cli/run_batch.py +62 -0
- vllm/entrypoints/cli/serve.py +328 -0
- vllm/entrypoints/cli/types.py +25 -0
- vllm/entrypoints/launcher.py +147 -0
- vllm/entrypoints/llm.py +1544 -0
- vllm/entrypoints/logger.py +50 -0
- vllm/entrypoints/openai/__init__.py +0 -0
- vllm/entrypoints/openai/api_server.py +1387 -0
- vllm/entrypoints/openai/cli_args.py +315 -0
- vllm/entrypoints/openai/logits_processors.py +90 -0
- vllm/entrypoints/openai/protocol.py +1913 -0
- vllm/entrypoints/openai/run_batch.py +463 -0
- vllm/entrypoints/openai/serving_chat.py +1221 -0
- vllm/entrypoints/openai/serving_classification.py +160 -0
- vllm/entrypoints/openai/serving_completion.py +592 -0
- vllm/entrypoints/openai/serving_embedding.py +201 -0
- vllm/entrypoints/openai/serving_engine.py +986 -0
- vllm/entrypoints/openai/serving_models.py +315 -0
- vllm/entrypoints/openai/serving_pooling.py +232 -0
- vllm/entrypoints/openai/serving_score.py +433 -0
- vllm/entrypoints/openai/serving_tokenization.py +157 -0
- vllm/entrypoints/openai/serving_transcription.py +424 -0
- vllm/entrypoints/openai/tool_parsers/__init__.py +23 -0
- vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py +164 -0
- vllm/entrypoints/openai/tool_parsers/deepseekv3_tool_parser.py +370 -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 +371 -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/llama4_pythonic_tool_parser.py +316 -0
- vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py +267 -0
- vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py +369 -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/utils.py +124 -0
- vllm/entrypoints/score_utils.py +50 -0
- vllm/entrypoints/ssl.py +75 -0
- vllm/entrypoints/utils.py +233 -0
- vllm/env_override.py +41 -0
- vllm/envs.py +944 -0
- vllm/executor/__init__.py +0 -0
- vllm/executor/executor_base.py +401 -0
- vllm/executor/mp_distributed_executor.py +244 -0
- vllm/executor/msgspec_utils.py +30 -0
- vllm/executor/multiproc_worker_utils.py +313 -0
- vllm/executor/ray_distributed_executor.py +701 -0
- vllm/executor/ray_utils.py +399 -0
- vllm/executor/uniproc_executor.py +139 -0
- vllm/forward_context.py +179 -0
- vllm/inputs/__init__.py +41 -0
- vllm/inputs/data.py +331 -0
- vllm/inputs/parse.py +151 -0
- vllm/inputs/preprocess.py +909 -0
- vllm/inputs/registry.py +237 -0
- vllm/jsontree.py +80 -0
- vllm/logger.py +212 -0
- vllm/logging_utils/__init__.py +8 -0
- vllm/logging_utils/dump_input.py +85 -0
- vllm/logging_utils/formatter.py +18 -0
- vllm/logits_process.py +119 -0
- vllm/lora/__init__.py +0 -0
- vllm/lora/fully_sharded_layers.py +355 -0
- vllm/lora/layers.py +1285 -0
- vllm/lora/lora.py +199 -0
- vllm/lora/models.py +818 -0
- vllm/lora/ops/__init__.py +0 -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 +290 -0
- vllm/lora/ops/triton_ops/lora_kernel_metadata.py +148 -0
- vllm/lora/ops/triton_ops/lora_shrink_op.py +244 -0
- vllm/lora/ops/triton_ops/utils.py +120 -0
- vllm/lora/ops/xla_ops/__init__.py +7 -0
- vllm/lora/ops/xla_ops/lora_ops.py +145 -0
- vllm/lora/peft_helper.py +136 -0
- vllm/lora/punica_wrapper/__init__.py +10 -0
- vllm/lora/punica_wrapper/punica_base.py +485 -0
- vllm/lora/punica_wrapper/punica_cpu.py +349 -0
- vllm/lora/punica_wrapper/punica_gpu.py +290 -0
- vllm/lora/punica_wrapper/punica_hpu.py +145 -0
- vllm/lora/punica_wrapper/punica_selector.py +20 -0
- vllm/lora/punica_wrapper/punica_tpu.py +405 -0
- vllm/lora/punica_wrapper/utils.py +164 -0
- vllm/lora/request.py +99 -0
- vllm/lora/resolver.py +85 -0
- vllm/lora/utils.py +240 -0
- vllm/lora/worker_manager.py +259 -0
- vllm/model_executor/__init__.py +16 -0
- vllm/model_executor/custom_op.py +152 -0
- vllm/model_executor/guided_decoding/__init__.py +181 -0
- vllm/model_executor/guided_decoding/guidance_decoding.py +63 -0
- vllm/model_executor/guided_decoding/guidance_logits_processors.py +104 -0
- vllm/model_executor/guided_decoding/guided_fields.py +41 -0
- vllm/model_executor/guided_decoding/lm_format_enforcer_decoding.py +67 -0
- vllm/model_executor/guided_decoding/outlines_decoding.py +155 -0
- vllm/model_executor/guided_decoding/outlines_logits_processors.py +284 -0
- vllm/model_executor/guided_decoding/utils.py +242 -0
- vllm/model_executor/guided_decoding/xgrammar_decoding.py +426 -0
- vllm/model_executor/layers/__init__.py +0 -0
- vllm/model_executor/layers/activation.py +369 -0
- vllm/model_executor/layers/fused_moe/__init__.py +54 -0
- vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py +125 -0
- vllm/model_executor/layers/fused_moe/batched_triton_or_deep_gemm_moe.py +117 -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=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=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_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.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=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_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.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_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=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=64,device_name=NVIDIA_A800-SXM4-80GB.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=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=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=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=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=896,device_name=NVIDIA_H20.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.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/cutlass_moe.py +461 -0
- vllm/model_executor/layers/fused_moe/deep_gemm_moe.py +240 -0
- vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py +240 -0
- vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py +186 -0
- vllm/model_executor/layers/fused_moe/fused_batched_moe.py +775 -0
- vllm/model_executor/layers/fused_moe/fused_marlin_moe.py +232 -0
- vllm/model_executor/layers/fused_moe/fused_moe.py +1724 -0
- vllm/model_executor/layers/fused_moe/layer.py +1535 -0
- vllm/model_executor/layers/fused_moe/modular_kernel.py +446 -0
- vllm/model_executor/layers/fused_moe/moe_align_block_size.py +243 -0
- vllm/model_executor/layers/fused_moe/moe_pallas.py +80 -0
- vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py +190 -0
- vllm/model_executor/layers/fused_moe/moe_torch_iterative.py +60 -0
- vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py +159 -0
- vllm/model_executor/layers/fused_moe/prepare_finalize.py +69 -0
- vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py +421 -0
- vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py +117 -0
- vllm/model_executor/layers/fused_moe/utils.py +98 -0
- vllm/model_executor/layers/layernorm.py +288 -0
- vllm/model_executor/layers/lightning_attn.py +652 -0
- vllm/model_executor/layers/linear.py +1524 -0
- vllm/model_executor/layers/logits_processor.py +197 -0
- vllm/model_executor/layers/mamba/__init__.py +0 -0
- vllm/model_executor/layers/mamba/mamba2_metadata.py +125 -0
- vllm/model_executor/layers/mamba/mamba_mixer.py +245 -0
- vllm/model_executor/layers/mamba/mamba_mixer2.py +616 -0
- vllm/model_executor/layers/mamba/ops/__init__.py +0 -0
- vllm/model_executor/layers/mamba/ops/causal_conv1d.py +105 -0
- vllm/model_executor/layers/mamba/ops/mamba_ssm.py +414 -0
- vllm/model_executor/layers/mamba/ops/ssd_bmm.py +262 -0
- vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py +589 -0
- vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py +751 -0
- vllm/model_executor/layers/mamba/ops/ssd_combined.py +232 -0
- vllm/model_executor/layers/mamba/ops/ssd_state_passing.py +206 -0
- vllm/model_executor/layers/pooler.py +350 -0
- vllm/model_executor/layers/quantization/__init__.py +157 -0
- vllm/model_executor/layers/quantization/aqlm.py +376 -0
- vllm/model_executor/layers/quantization/auto_round.py +310 -0
- vllm/model_executor/layers/quantization/awq.py +194 -0
- vllm/model_executor/layers/quantization/awq_marlin.py +519 -0
- vllm/model_executor/layers/quantization/awq_triton.py +320 -0
- vllm/model_executor/layers/quantization/base_config.py +151 -0
- vllm/model_executor/layers/quantization/bitblas.py +461 -0
- vllm/model_executor/layers/quantization/bitsandbytes.py +396 -0
- vllm/model_executor/layers/quantization/compressed_tensors/__init__.py +0 -0
- vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py +668 -0
- vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py +1260 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py +24 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py +358 -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 +93 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py +178 -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 +150 -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/triton_scaled_mm.py +206 -0
- vllm/model_executor/layers/quantization/compressed_tensors/utils.py +216 -0
- vllm/model_executor/layers/quantization/deepspeedfp.py +195 -0
- vllm/model_executor/layers/quantization/experts_int8.py +196 -0
- vllm/model_executor/layers/quantization/fbgemm_fp8.py +172 -0
- vllm/model_executor/layers/quantization/fp8.py +906 -0
- vllm/model_executor/layers/quantization/gguf.py +565 -0
- vllm/model_executor/layers/quantization/gptq.py +278 -0
- vllm/model_executor/layers/quantization/gptq_bitblas.py +445 -0
- vllm/model_executor/layers/quantization/gptq_marlin.py +648 -0
- vllm/model_executor/layers/quantization/gptq_marlin_24.py +297 -0
- vllm/model_executor/layers/quantization/hqq_marlin.py +332 -0
- vllm/model_executor/layers/quantization/ipex_quant.py +250 -0
- vllm/model_executor/layers/quantization/kernels/__init__.py +0 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py +90 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py +83 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py +116 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py +300 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py +143 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py +120 -0
- vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py +131 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py +67 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py +87 -0
- vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py +120 -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 +105 -0
- vllm/model_executor/layers/quantization/kv_cache.py +139 -0
- vllm/model_executor/layers/quantization/marlin.py +261 -0
- vllm/model_executor/layers/quantization/modelopt.py +737 -0
- vllm/model_executor/layers/quantization/moe_wna16.py +449 -0
- vllm/model_executor/layers/quantization/neuron_quant.py +76 -0
- vllm/model_executor/layers/quantization/ptpc_fp8.py +127 -0
- vllm/model_executor/layers/quantization/qqq.py +275 -0
- vllm/model_executor/layers/quantization/quark/__init__.py +0 -0
- vllm/model_executor/layers/quantization/quark/quark.py +441 -0
- vllm/model_executor/layers/quantization/quark/quark_moe.py +237 -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 +126 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py +146 -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/schema.py +86 -0
- vllm/model_executor/layers/quantization/torchao.py +161 -0
- vllm/model_executor/layers/quantization/tpu_int8.py +121 -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 +208 -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=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=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=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/fp8_utils.py +618 -0
- vllm/model_executor/layers/quantization/utils/gptq_utils.py +95 -0
- vllm/model_executor/layers/quantization/utils/int8_utils.py +485 -0
- vllm/model_executor/layers/quantization/utils/layer_utils.py +40 -0
- vllm/model_executor/layers/quantization/utils/machete_utils.py +33 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils.py +476 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py +283 -0
- vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py +325 -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/marlin_utils_test_qqq.py +126 -0
- vllm/model_executor/layers/quantization/utils/mxfp4_utils.py +45 -0
- vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py +104 -0
- vllm/model_executor/layers/quantization/utils/quant_utils.py +573 -0
- vllm/model_executor/layers/quantization/utils/w8a8_utils.py +405 -0
- vllm/model_executor/layers/rejection_sampler.py +406 -0
- vllm/model_executor/layers/resampler.py +270 -0
- vllm/model_executor/layers/rotary_embedding.py +1862 -0
- vllm/model_executor/layers/sampler.py +1204 -0
- vllm/model_executor/layers/spec_decode_base_sampler.py +259 -0
- vllm/model_executor/layers/typical_acceptance_sampler.py +166 -0
- vllm/model_executor/layers/utils.py +95 -0
- vllm/model_executor/layers/vocab_parallel_embedding.py +487 -0
- vllm/model_executor/model_loader/__init__.py +76 -0
- vllm/model_executor/model_loader/base_loader.py +43 -0
- vllm/model_executor/model_loader/bitsandbytes_loader.py +570 -0
- vllm/model_executor/model_loader/default_loader.py +282 -0
- vllm/model_executor/model_loader/dummy_loader.py +27 -0
- vllm/model_executor/model_loader/gguf_loader.py +120 -0
- vllm/model_executor/model_loader/neuron.py +476 -0
- vllm/model_executor/model_loader/neuronx_distributed.py +685 -0
- vllm/model_executor/model_loader/runai_streamer_loader.py +109 -0
- vllm/model_executor/model_loader/sharded_state_loader.py +201 -0
- vllm/model_executor/model_loader/tensorizer.py +600 -0
- vllm/model_executor/model_loader/tensorizer_loader.py +123 -0
- vllm/model_executor/model_loader/tpu.py +112 -0
- vllm/model_executor/model_loader/utils.py +302 -0
- vllm/model_executor/model_loader/weight_utils.py +782 -0
- vllm/model_executor/models/__init__.py +28 -0
- vllm/model_executor/models/adapters.py +248 -0
- vllm/model_executor/models/aimv2.py +246 -0
- vllm/model_executor/models/arctic.py +559 -0
- vllm/model_executor/models/aria.py +657 -0
- vllm/model_executor/models/aya_vision.py +466 -0
- vllm/model_executor/models/baichuan.py +474 -0
- vllm/model_executor/models/bamba.py +543 -0
- vllm/model_executor/models/bart.py +938 -0
- vllm/model_executor/models/bert.py +523 -0
- vllm/model_executor/models/bert_with_rope.py +769 -0
- vllm/model_executor/models/blip.py +339 -0
- vllm/model_executor/models/blip2.py +718 -0
- vllm/model_executor/models/bloom.py +373 -0
- vllm/model_executor/models/chameleon.py +1136 -0
- vllm/model_executor/models/chatglm.py +478 -0
- vllm/model_executor/models/clip.py +407 -0
- vllm/model_executor/models/commandr.py +472 -0
- vllm/model_executor/models/constant_size_cache.py +137 -0
- vllm/model_executor/models/dbrx.py +472 -0
- vllm/model_executor/models/deepseek.py +486 -0
- vllm/model_executor/models/deepseek_mtp.py +269 -0
- vllm/model_executor/models/deepseek_v2.py +843 -0
- vllm/model_executor/models/deepseek_vl2.py +648 -0
- vllm/model_executor/models/eagle.py +260 -0
- vllm/model_executor/models/exaone.py +551 -0
- vllm/model_executor/models/fairseq2_llama.py +154 -0
- vllm/model_executor/models/falcon.py +510 -0
- vllm/model_executor/models/falcon_h1.py +685 -0
- vllm/model_executor/models/florence2.py +1103 -0
- vllm/model_executor/models/fuyu.py +389 -0
- vllm/model_executor/models/gemma.py +425 -0
- vllm/model_executor/models/gemma2.py +425 -0
- vllm/model_executor/models/gemma3.py +533 -0
- vllm/model_executor/models/gemma3_mm.py +709 -0
- vllm/model_executor/models/glm.py +23 -0
- vllm/model_executor/models/glm4.py +305 -0
- vllm/model_executor/models/glm4v.py +648 -0
- vllm/model_executor/models/gpt2.py +328 -0
- vllm/model_executor/models/gpt_bigcode.py +335 -0
- vllm/model_executor/models/gpt_j.py +339 -0
- vllm/model_executor/models/gpt_neox.py +332 -0
- vllm/model_executor/models/granite.py +493 -0
- vllm/model_executor/models/granite_speech.py +779 -0
- vllm/model_executor/models/granitemoe.py +437 -0
- vllm/model_executor/models/granitemoehybrid.py +586 -0
- vllm/model_executor/models/granitemoeshared.py +341 -0
- vllm/model_executor/models/gritlm.py +224 -0
- vllm/model_executor/models/grok1.py +546 -0
- vllm/model_executor/models/h2ovl.py +546 -0
- vllm/model_executor/models/idefics2_vision_model.py +389 -0
- vllm/model_executor/models/idefics3.py +776 -0
- vllm/model_executor/models/interfaces.py +572 -0
- vllm/model_executor/models/interfaces_base.py +164 -0
- vllm/model_executor/models/intern_vit.py +480 -0
- vllm/model_executor/models/internlm2.py +455 -0
- vllm/model_executor/models/internlm2_ve.py +147 -0
- vllm/model_executor/models/internvl.py +1418 -0
- vllm/model_executor/models/jais.py +373 -0
- vllm/model_executor/models/jamba.py +592 -0
- vllm/model_executor/models/kimi_vl.py +577 -0
- vllm/model_executor/models/llama.py +644 -0
- vllm/model_executor/models/llama4.py +532 -0
- vllm/model_executor/models/llama_eagle.py +165 -0
- vllm/model_executor/models/llama_eagle3.py +263 -0
- vllm/model_executor/models/llava.py +866 -0
- vllm/model_executor/models/llava_next.py +586 -0
- vllm/model_executor/models/llava_next_video.py +471 -0
- vllm/model_executor/models/llava_onevision.py +956 -0
- vllm/model_executor/models/mamba.py +273 -0
- vllm/model_executor/models/mamba2.py +308 -0
- vllm/model_executor/models/mamba_cache.py +76 -0
- vllm/model_executor/models/medusa.py +219 -0
- vllm/model_executor/models/mimo.py +192 -0
- vllm/model_executor/models/mimo_mtp.py +285 -0
- vllm/model_executor/models/minicpm.py +592 -0
- vllm/model_executor/models/minicpm3.py +230 -0
- vllm/model_executor/models/minicpm_eagle.py +391 -0
- vllm/model_executor/models/minicpmo.py +759 -0
- vllm/model_executor/models/minicpmv.py +1287 -0
- vllm/model_executor/models/minimax_cache.py +36 -0
- vllm/model_executor/models/minimax_text_01.py +1301 -0
- vllm/model_executor/models/minimax_vl_01.py +364 -0
- vllm/model_executor/models/mistral3.py +604 -0
- vllm/model_executor/models/mixtral.py +488 -0
- vllm/model_executor/models/mixtral_quant.py +453 -0
- vllm/model_executor/models/mllama.py +1624 -0
- vllm/model_executor/models/mllama4.py +938 -0
- vllm/model_executor/models/mlp_speculator.py +206 -0
- vllm/model_executor/models/modernbert.py +331 -0
- vllm/model_executor/models/module_mapping.py +72 -0
- vllm/model_executor/models/molmo.py +1568 -0
- vllm/model_executor/models/moonvit.py +630 -0
- vllm/model_executor/models/mpt.py +331 -0
- vllm/model_executor/models/nemotron.py +508 -0
- vllm/model_executor/models/nemotron_h.py +573 -0
- vllm/model_executor/models/nemotron_nas.py +484 -0
- vllm/model_executor/models/nvlm_d.py +216 -0
- vllm/model_executor/models/olmo.py +389 -0
- vllm/model_executor/models/olmo2.py +414 -0
- vllm/model_executor/models/olmoe.py +468 -0
- vllm/model_executor/models/opt.py +412 -0
- vllm/model_executor/models/orion.py +349 -0
- vllm/model_executor/models/ovis.py +567 -0
- vllm/model_executor/models/paligemma.py +398 -0
- vllm/model_executor/models/persimmon.py +344 -0
- vllm/model_executor/models/phi.py +356 -0
- vllm/model_executor/models/phi3.py +19 -0
- vllm/model_executor/models/phi3_small.py +465 -0
- vllm/model_executor/models/phi3v.py +723 -0
- vllm/model_executor/models/phi4mm.py +1246 -0
- vllm/model_executor/models/phi4mm_audio.py +1233 -0
- vllm/model_executor/models/phi4mm_utils.py +1884 -0
- vllm/model_executor/models/phimoe.py +665 -0
- vllm/model_executor/models/pixtral.py +1316 -0
- vllm/model_executor/models/plamo2.py +738 -0
- vllm/model_executor/models/prithvi_geospatial_mae.py +232 -0
- vllm/model_executor/models/qwen.py +362 -0
- vllm/model_executor/models/qwen2.py +497 -0
- vllm/model_executor/models/qwen2_5_omni_thinker.py +904 -0
- vllm/model_executor/models/qwen2_5_vl.py +1166 -0
- vllm/model_executor/models/qwen2_audio.py +410 -0
- vllm/model_executor/models/qwen2_moe.py +540 -0
- vllm/model_executor/models/qwen2_rm.py +132 -0
- vllm/model_executor/models/qwen2_vl.py +1405 -0
- vllm/model_executor/models/qwen3.py +321 -0
- vllm/model_executor/models/qwen3_moe.py +535 -0
- vllm/model_executor/models/qwen_vl.py +785 -0
- vllm/model_executor/models/registry.py +622 -0
- vllm/model_executor/models/roberta.py +276 -0
- vllm/model_executor/models/siglip.py +524 -0
- vllm/model_executor/models/skyworkr1v.py +951 -0
- vllm/model_executor/models/smolvlm.py +52 -0
- vllm/model_executor/models/solar.py +506 -0
- vllm/model_executor/models/stablelm.py +343 -0
- vllm/model_executor/models/starcoder2.py +356 -0
- vllm/model_executor/models/tarsier.py +643 -0
- vllm/model_executor/models/telechat2.py +140 -0
- vllm/model_executor/models/teleflm.py +79 -0
- vllm/model_executor/models/transformers.py +508 -0
- vllm/model_executor/models/ultravox.py +656 -0
- vllm/model_executor/models/utils.py +731 -0
- vllm/model_executor/models/vision.py +147 -0
- vllm/model_executor/models/whisper.py +747 -0
- vllm/model_executor/models/zamba2.py +1009 -0
- vllm/model_executor/parameter.py +459 -0
- vllm/model_executor/pooling_metadata.py +72 -0
- vllm/model_executor/sampling_metadata.py +597 -0
- vllm/model_executor/utils.py +77 -0
- vllm/multimodal/__init__.py +33 -0
- vllm/multimodal/audio.py +106 -0
- vllm/multimodal/base.py +219 -0
- vllm/multimodal/hasher.py +118 -0
- vllm/multimodal/image.py +97 -0
- vllm/multimodal/inputs.py +876 -0
- vllm/multimodal/parse.py +461 -0
- vllm/multimodal/processing.py +1895 -0
- vllm/multimodal/profiling.py +258 -0
- vllm/multimodal/registry.py +331 -0
- vllm/multimodal/utils.py +436 -0
- vllm/multimodal/video.py +198 -0
- vllm/outputs.py +512 -0
- vllm/platforms/__init__.py +291 -0
- vllm/platforms/cpu.py +266 -0
- vllm/platforms/cuda.py +526 -0
- vllm/platforms/hpu.py +106 -0
- vllm/platforms/interface.py +538 -0
- vllm/platforms/neuron.py +150 -0
- vllm/platforms/rocm.py +435 -0
- vllm/platforms/tpu.py +216 -0
- vllm/platforms/xpu.py +156 -0
- vllm/plugins/__init__.py +94 -0
- vllm/plugins/lora_resolvers/README.md +15 -0
- vllm/plugins/lora_resolvers/__init__.py +0 -0
- vllm/plugins/lora_resolvers/filesystem_resolver.py +50 -0
- vllm/pooling_params.py +54 -0
- vllm/profiler/__init__.py +0 -0
- vllm/profiler/layerwise_profile.py +375 -0
- vllm/profiler/utils.py +148 -0
- vllm/prompt_adapter/__init__.py +0 -0
- vllm/prompt_adapter/layers.py +83 -0
- vllm/prompt_adapter/models.py +358 -0
- vllm/prompt_adapter/request.py +37 -0
- vllm/prompt_adapter/utils.py +98 -0
- vllm/prompt_adapter/worker_manager.py +179 -0
- vllm/py.typed +2 -0
- vllm/reasoning/__init__.py +15 -0
- vllm/reasoning/abs_reasoning_parsers.py +192 -0
- vllm/reasoning/deepseek_r1_reasoning_parser.py +173 -0
- vllm/reasoning/granite_reasoning_parser.py +363 -0
- vllm/reasoning/qwen3_reasoning_parser.py +151 -0
- vllm/sampling_params.py +602 -0
- vllm/scalar_type.py +347 -0
- vllm/scripts.py +15 -0
- vllm/sequence.py +1568 -0
- vllm/spec_decode/__init__.py +0 -0
- vllm/spec_decode/batch_expansion.py +506 -0
- vllm/spec_decode/draft_model_runner.py +349 -0
- vllm/spec_decode/interfaces.py +99 -0
- vllm/spec_decode/medusa_worker.py +138 -0
- vllm/spec_decode/metrics.py +213 -0
- vllm/spec_decode/mlp_speculator_worker.py +94 -0
- vllm/spec_decode/mqa_scorer.py +160 -0
- vllm/spec_decode/multi_step_worker.py +423 -0
- vllm/spec_decode/ngram_worker.py +196 -0
- vllm/spec_decode/proposer_worker_base.py +59 -0
- vllm/spec_decode/smaller_tp_proposer_worker.py +196 -0
- vllm/spec_decode/spec_decode_worker.py +1326 -0
- vllm/spec_decode/target_model_runner.py +45 -0
- vllm/spec_decode/top1_proposer.py +275 -0
- vllm/spec_decode/util.py +277 -0
- vllm/test_utils.py +130 -0
- vllm/third_party/__init__.py +0 -0
- vllm/third_party/pynvml.py +6140 -0
- vllm/tracing.py +131 -0
- vllm/transformers_utils/__init__.py +24 -0
- vllm/transformers_utils/chat_templates/__init__.py +5 -0
- vllm/transformers_utils/chat_templates/registry.py +60 -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/config.py +887 -0
- vllm/transformers_utils/configs/__init__.py +61 -0
- vllm/transformers_utils/configs/arctic.py +207 -0
- vllm/transformers_utils/configs/chatglm.py +72 -0
- vllm/transformers_utils/configs/cohere2.py +195 -0
- vllm/transformers_utils/configs/dbrx.py +280 -0
- vllm/transformers_utils/configs/deepseek_vl2.py +216 -0
- vllm/transformers_utils/configs/eagle.py +85 -0
- vllm/transformers_utils/configs/exaone.py +190 -0
- vllm/transformers_utils/configs/falcon.py +90 -0
- vllm/transformers_utils/configs/h2ovl.py +16 -0
- vllm/transformers_utils/configs/internvl.py +54 -0
- vllm/transformers_utils/configs/jais.py +238 -0
- vllm/transformers_utils/configs/kimi_vl.py +37 -0
- vllm/transformers_utils/configs/medusa.py +63 -0
- vllm/transformers_utils/configs/minimax_text_01.py +70 -0
- vllm/transformers_utils/configs/minimax_vl_01.py +71 -0
- vllm/transformers_utils/configs/mllama.py +31 -0
- vllm/transformers_utils/configs/mlp_speculator.py +68 -0
- vllm/transformers_utils/configs/moonvit.py +33 -0
- vllm/transformers_utils/configs/mpt.py +180 -0
- vllm/transformers_utils/configs/nemotron.py +205 -0
- vllm/transformers_utils/configs/nemotron_h.py +258 -0
- vllm/transformers_utils/configs/nvlm_d.py +15 -0
- vllm/transformers_utils/configs/ovis.py +184 -0
- vllm/transformers_utils/configs/skyworkr1v.py +54 -0
- vllm/transformers_utils/configs/solar.py +247 -0
- vllm/transformers_utils/configs/telechat2.py +64 -0
- vllm/transformers_utils/configs/ultravox.py +108 -0
- vllm/transformers_utils/detokenizer.py +168 -0
- vllm/transformers_utils/detokenizer_utils.py +189 -0
- vllm/transformers_utils/processor.py +221 -0
- vllm/transformers_utils/processors/__init__.py +8 -0
- vllm/transformers_utils/processors/deepseek_vl2.py +363 -0
- vllm/transformers_utils/processors/ovis.py +420 -0
- vllm/transformers_utils/s3_utils.py +162 -0
- vllm/transformers_utils/tokenizer.py +302 -0
- vllm/transformers_utils/tokenizer_base.py +149 -0
- vllm/transformers_utils/tokenizer_group.py +120 -0
- vllm/transformers_utils/tokenizers/__init__.py +10 -0
- vllm/transformers_utils/tokenizers/mistral.py +493 -0
- vllm/transformers_utils/utils.py +99 -0
- vllm/triton_utils/__init__.py +14 -0
- vllm/triton_utils/importing.py +50 -0
- vllm/usage/__init__.py +0 -0
- vllm/usage/usage_lib.py +256 -0
- vllm/utils.py +2910 -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 +163 -0
- vllm/v1/attention/backends/flash_attn.py +869 -0
- vllm/v1/attention/backends/flashinfer.py +651 -0
- vllm/v1/attention/backends/flex_attention.py +477 -0
- vllm/v1/attention/backends/mla/__init__.py +0 -0
- vllm/v1/attention/backends/mla/common.py +931 -0
- vllm/v1/attention/backends/mla/cutlass_mla.py +97 -0
- vllm/v1/attention/backends/mla/flashmla.py +152 -0
- vllm/v1/attention/backends/mla/rocm_aiter_mla.py +220 -0
- vllm/v1/attention/backends/mla/triton_mla.py +120 -0
- vllm/v1/attention/backends/pallas.py +240 -0
- vllm/v1/attention/backends/triton_attn.py +285 -0
- vllm/v1/attention/backends/utils.py +52 -0
- vllm/v1/core/__init__.py +0 -0
- vllm/v1/core/block_pool.py +349 -0
- vllm/v1/core/encoder_cache_manager.py +150 -0
- vllm/v1/core/kv_cache_coordinator.py +363 -0
- vllm/v1/core/kv_cache_manager.py +392 -0
- vllm/v1/core/kv_cache_utils.py +996 -0
- vllm/v1/core/sched/__init__.py +0 -0
- vllm/v1/core/sched/interface.py +150 -0
- vllm/v1/core/sched/output.py +154 -0
- vllm/v1/core/sched/scheduler.py +1044 -0
- vllm/v1/core/sched/utils.py +23 -0
- vllm/v1/core/single_type_kv_cache_manager.py +403 -0
- vllm/v1/engine/__init__.py +173 -0
- vllm/v1/engine/async_llm.py +558 -0
- vllm/v1/engine/coordinator.py +253 -0
- vllm/v1/engine/core.py +961 -0
- vllm/v1/engine/core_client.py +1129 -0
- vllm/v1/engine/detokenizer.py +261 -0
- vllm/v1/engine/exceptions.py +17 -0
- vllm/v1/engine/llm_engine.py +317 -0
- vllm/v1/engine/logprobs.py +199 -0
- vllm/v1/engine/mm_input_cache.py +91 -0
- vllm/v1/engine/output_processor.py +428 -0
- vllm/v1/engine/parallel_sampling.py +133 -0
- vllm/v1/engine/processor.py +407 -0
- vllm/v1/executor/__init__.py +0 -0
- vllm/v1/executor/abstract.py +113 -0
- vllm/v1/executor/multiproc_executor.py +537 -0
- vllm/v1/executor/ray_distributed_executor.py +62 -0
- vllm/v1/kv_cache_interface.py +194 -0
- vllm/v1/metrics/__init__.py +0 -0
- vllm/v1/metrics/loggers.py +523 -0
- vllm/v1/metrics/prometheus.py +82 -0
- vllm/v1/metrics/ray_wrappers.py +131 -0
- vllm/v1/metrics/reader.py +246 -0
- vllm/v1/metrics/stats.py +239 -0
- vllm/v1/outputs.py +116 -0
- vllm/v1/request.py +193 -0
- vllm/v1/sample/__init__.py +0 -0
- vllm/v1/sample/metadata.py +44 -0
- vllm/v1/sample/ops/__init__.py +0 -0
- vllm/v1/sample/ops/bad_words.py +39 -0
- vllm/v1/sample/ops/penalties.py +59 -0
- vllm/v1/sample/ops/topk_topp_sampler.py +293 -0
- vllm/v1/sample/rejection_sampler.py +631 -0
- vllm/v1/sample/sampler.py +286 -0
- vllm/v1/sample/tpu/__init__.py +0 -0
- vllm/v1/sample/tpu/metadata.py +124 -0
- vllm/v1/sample/tpu/sampler.py +145 -0
- vllm/v1/serial_utils.py +315 -0
- vllm/v1/spec_decode/__init__.py +0 -0
- vllm/v1/spec_decode/eagle.py +432 -0
- vllm/v1/spec_decode/medusa.py +62 -0
- vllm/v1/spec_decode/metadata.py +62 -0
- vllm/v1/spec_decode/metrics.py +178 -0
- vllm/v1/spec_decode/ngram_proposer.py +132 -0
- vllm/v1/spec_decode/utils.py +46 -0
- vllm/v1/structured_output/__init__.py +222 -0
- vllm/v1/structured_output/backend_guidance.py +245 -0
- vllm/v1/structured_output/backend_types.py +134 -0
- vllm/v1/structured_output/backend_xgrammar.py +318 -0
- vllm/v1/structured_output/request.py +86 -0
- vllm/v1/structured_output/utils.py +175 -0
- vllm/v1/utils.py +743 -0
- vllm/v1/worker/__init__.py +0 -0
- vllm/v1/worker/block_table.py +142 -0
- vllm/v1/worker/cpu_model_runner.py +86 -0
- vllm/v1/worker/cpu_worker.py +152 -0
- vllm/v1/worker/gpu_input_batch.py +681 -0
- vllm/v1/worker/gpu_model_runner.py +2320 -0
- vllm/v1/worker/gpu_worker.py +393 -0
- vllm/v1/worker/lora_model_runner_mixin.py +173 -0
- vllm/v1/worker/tpu_model_runner.py +1673 -0
- vllm/v1/worker/tpu_worker.py +299 -0
- vllm/v1/worker/utils.py +111 -0
- vllm/v1/worker/worker_base.py +65 -0
- vllm/version.py +41 -0
- vllm/vllm_flash_attn/.gitkeep +0 -0
- vllm/worker/__init__.py +0 -0
- vllm/worker/cache_engine.py +145 -0
- vllm/worker/cpu_enc_dec_model_runner.py +326 -0
- vllm/worker/cpu_model_runner.py +671 -0
- vllm/worker/cpu_pooling_model_runner.py +125 -0
- vllm/worker/cpu_worker.py +450 -0
- vllm/worker/enc_dec_model_runner.py +555 -0
- vllm/worker/hpu_model_runner.py +2320 -0
- vllm/worker/hpu_worker.py +484 -0
- vllm/worker/model_runner.py +2178 -0
- vllm/worker/model_runner_base.py +282 -0
- vllm/worker/multi_step_hpu_worker.py +123 -0
- vllm/worker/multi_step_model_runner.py +911 -0
- vllm/worker/multi_step_neuron_model_runner.py +84 -0
- vllm/worker/multi_step_neuronx_distributed_model_runner.py +63 -0
- vllm/worker/multi_step_tpu_worker.py +108 -0
- vllm/worker/multi_step_worker.py +197 -0
- vllm/worker/neuron_model_runner.py +460 -0
- vllm/worker/neuron_worker.py +193 -0
- vllm/worker/neuronx_distributed_model_runner.py +294 -0
- vllm/worker/pooling_model_runner.py +211 -0
- vllm/worker/tpu_model_runner.py +909 -0
- vllm/worker/tpu_worker.py +337 -0
- vllm/worker/utils.py +53 -0
- vllm/worker/worker.py +577 -0
- vllm/worker/worker_base.py +646 -0
- vllm/worker/xpu_model_runner.py +606 -0
- vllm/worker/xpu_worker.py +186 -0
- vllm_cpu_amxbf16-0.9.1.dist-info/METADATA +305 -0
- vllm_cpu_amxbf16-0.9.1.dist-info/RECORD +1197 -0
- vllm_cpu_amxbf16-0.9.1.dist-info/WHEEL +5 -0
- vllm_cpu_amxbf16-0.9.1.dist-info/entry_points.txt +5 -0
- vllm_cpu_amxbf16-0.9.1.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,1197 @@
|
|
|
1
|
+
vllm/_C.abi3.so,sha256=Opd1cgWqrRGSwVWwdu_j0zYp3L_9di3FQgN5i5DaHqQ,20240976
|
|
2
|
+
vllm/__init__.py,sha256=Kem0adJsL5ncZMaclrWZFD3aQPlyXDpPx7JEM40_zXE,1984
|
|
3
|
+
vllm/_custom_ops.py,sha256=Z2ZcP0Gn-WzcHhhUt8WzQVWj3pIFCqi07tmMDIcjZmU,76683
|
|
4
|
+
vllm/_ipex_ops.py,sha256=Bus71ROUjsvueWC_fGEODjrUZ0aYgfzyNT_kVYXmmqQ,8715
|
|
5
|
+
vllm/_version.py,sha256=LwGndsRSpclYq-j3wgRr2nzOXwUYj0Jtg7Kof7R0BEw,704
|
|
6
|
+
vllm/beam_search.py,sha256=X6PLlBDWaeZNKK4ttym328Rvjnup5wQnIDmSafMNSQI,2639
|
|
7
|
+
vllm/collect_env.py,sha256=Z2dauhcwD50tOczPNrk5Ynqqvckc6N3tJk7scouvms4,28292
|
|
8
|
+
vllm/config.py,sha256=juBa1hTLqWRyhwLt6q8-cE9epvw8spbOhAp_H4fskUY,207019
|
|
9
|
+
vllm/connections.py,sha256=YL5sQpi0vg05ZwNhpnn-7h9oCGjQeKWjTRYPCB_pKGQ,5088
|
|
10
|
+
vllm/env_override.py,sha256=fbUyMmMdoOLUP9aht_CHUPfvG3vkbKoxZHbEMR-T3sA,1698
|
|
11
|
+
vllm/envs.py,sha256=pdiltv1CrrmNlrzgcUiMOmIBWxvLlTqWHf0ez0jgsY8,38271
|
|
12
|
+
vllm/forward_context.py,sha256=PllkGCMC5x00RlodMHBwWeUerZvweoHxWvUUR5mm1pc,7241
|
|
13
|
+
vllm/jsontree.py,sha256=Fl-Ae-1z0GOKsDrdx3ibbXg2IFhbL_B3L3S90In0vQY,2212
|
|
14
|
+
vllm/logger.py,sha256=DI8-5MoH8fubVMAeqDWYQSAS79T2h6pfgErjaP8T7bE,7575
|
|
15
|
+
vllm/logits_process.py,sha256=l7EmiG8n4-zYS1ZHr3jnCJDHSvWUfXdfaIx7y6yYzXw,4440
|
|
16
|
+
vllm/outputs.py,sha256=lG2fRt1bpCYRtAYxEuMn_beWdt3JBhsAofq_EzQwnEw,20029
|
|
17
|
+
vllm/pooling_params.py,sha256=VYOF0KqoseeB5lnjekAOUA_GQfTiSdEqK4MjNeFLD4c,2086
|
|
18
|
+
vllm/py.typed,sha256=F5LUrt0voM87SNuuOky2X9veCVDqJUgRg_VohYqDigY,65
|
|
19
|
+
vllm/sampling_params.py,sha256=sqUvh-RT8aMtr-j7EGzjWjhoUQcy-2PEjLR5oyTNVRw,27008
|
|
20
|
+
vllm/scalar_type.py,sha256=L6WsIC1s15P7cczrNMo4Kp-t0PhJa2N9hooM7sx4RQA,12371
|
|
21
|
+
vllm/scripts.py,sha256=GBLs96wGlHWNj7WDtb-kuwHCR7HCdQIJN-vDoPh2Ud8,501
|
|
22
|
+
vllm/sequence.py,sha256=6Ufm46WIR2LMC0GW1pEEzfXr9yYw7EtuQqIvqEv-Ihw,62319
|
|
23
|
+
vllm/test_utils.py,sha256=kefc-m-RCrSmJFGtlla-jPk6F9uxO7kibBSjIIM-lco,6061
|
|
24
|
+
vllm/tracing.py,sha256=6fIL7vcKohcG2tbilH0UheKvev9N7TCLxWCvfYJOwSI,4845
|
|
25
|
+
vllm/utils.py,sha256=8O-nJAyxq0MRnrTJUPb9F41YZPKDXP5Eqy-lgkSyHqw,98828
|
|
26
|
+
vllm/version.py,sha256=j5_jpV6lcpUIkq56JF2uxJS02TJjG_7nGrzjvf7ptDI,1375
|
|
27
|
+
vllm/adapter_commons/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
28
|
+
vllm/adapter_commons/layers.py,sha256=ahfExqPZiZfRoi8gmzp31Hj3MKGvcalVGGR6w9lhdNA,450
|
|
29
|
+
vllm/adapter_commons/models.py,sha256=5XvXSRMnC8TufQZwf7O01SH83chilebej3Y4LnQKrhU,2870
|
|
30
|
+
vllm/adapter_commons/request.py,sha256=PGKCbvlRywX4PTQgT9hPBGYwkc9scpiic-Hi3K6Uokg,686
|
|
31
|
+
vllm/adapter_commons/utils.py,sha256=eAbRtVVso5fvSLp28k9VjArFUjrbl8BT0NkJPmJIgF4,3329
|
|
32
|
+
vllm/adapter_commons/worker_manager.py,sha256=PKuagBEoFxWzPz9AbUogHGaNJst7mWlAOarcZkUBa7I,992
|
|
33
|
+
vllm/assets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
34
|
+
vllm/assets/audio.py,sha256=03OUK2QRgJDgEucc2HDl3vdrwgiRAuBxzckas015Ces,1254
|
|
35
|
+
vllm/assets/base.py,sha256=Yv1bK5DmfZbWr_1Uqhb-mawh5M6yC1tlFT6gRkHtcgs,1265
|
|
36
|
+
vllm/assets/image.py,sha256=vW3KXy3bM-0UfQ4ZSFZPwOQfIQCIRd-4D8Xp3oY1Ics,1024
|
|
37
|
+
vllm/assets/video.py,sha256=71Tk4-IEQJmpVSoCyLS0Az1HYwQrpjhu1ahomIeu8h0,3481
|
|
38
|
+
vllm/attention/__init__.py,sha256=yfqspQ_l0_9DtVE42eeurvzLLQCyx_TCBV6Uo4_nZK8,679
|
|
39
|
+
vllm/attention/layer.py,sha256=_l3YBKs3F5SYU25uvmlCy0EgzeYgUbWhGYCVoCRPdvs,19268
|
|
40
|
+
vllm/attention/selector.py,sha256=_2J2G9oDqZaIwvz0Md7kJ8K4jpGXFRrUPYT0n2PIBwA,5934
|
|
41
|
+
vllm/attention/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
42
|
+
vllm/attention/backends/abstract.py,sha256=116UUlAFXWKKWhtJTcz6_IEQ4vG-DUlF48xgFCInjOo,9486
|
|
43
|
+
vllm/attention/backends/blocksparse_attn.py,sha256=EQb3Ek_ZyJYBgasxIlCtQt6DkU9gKUe9csx4W5nPwY8,18264
|
|
44
|
+
vllm/attention/backends/cpu_mla.py,sha256=I5vbO4xEMp0kb7IZySOaA1z7qy6bIBysP-4hPKFTiGw,11342
|
|
45
|
+
vllm/attention/backends/dual_chunk_flash_attn.py,sha256=n2Cj2cq4_kWmvzMvdoPLdUhoJQhHjK9h7pkLvTLGS6E,66236
|
|
46
|
+
vllm/attention/backends/flash_attn.py,sha256=2mZqQZiNfxnfFyR4i3hlSu5YUyNDQBFX8eR_5khkg6I,44738
|
|
47
|
+
vllm/attention/backends/flashinfer.py,sha256=resEqV9oL4a2Hwfdgk3rcT8OguStktTyaaMyaBlWYeg,47962
|
|
48
|
+
vllm/attention/backends/flashmla.py,sha256=l0Rf9Jj08GqugdjE38XvDeiVVsG4E7g7fy1WlaQiJp4,9175
|
|
49
|
+
vllm/attention/backends/hpu_attn.py,sha256=bZ74G0qwa-obI_hg4H46yzpJu_MslFRO6oQXTKpj8ms,12535
|
|
50
|
+
vllm/attention/backends/ipex_attn.py,sha256=-s73WbXIrOqtC2f5-r15ncQa5Ts18gQyLrawRz5pZoI,15080
|
|
51
|
+
vllm/attention/backends/pallas.py,sha256=N8Nrk-WKp_FJIJvHJPqKOr9AlTF8IFoImzRpYbIRDZs,13934
|
|
52
|
+
vllm/attention/backends/placeholder_attn.py,sha256=lY1GvhayOg_v04gsJbLHCyF9-Eb3gY9bNGUY8rG3ZZM,16165
|
|
53
|
+
vllm/attention/backends/rocm_aiter_mla.py,sha256=c19DnPe_k5tCOnQ8gTK5H2DU1G1maYjjffbj1BPa7A8,18027
|
|
54
|
+
vllm/attention/backends/rocm_flash_attn.py,sha256=fjnqqUGW052tBbrsHNG3eTsR6lI88AHkaxl0yupPV2g,42770
|
|
55
|
+
vllm/attention/backends/torch_sdpa.py,sha256=lBP2dzsNndin1-9CCR5TO19fTBDTQPe3AkHo70N3vos,27801
|
|
56
|
+
vllm/attention/backends/triton_mla.py,sha256=fwawwKUDQPKQ6ytss1usWLn78F3TBe-V7--pUvADrXk,4099
|
|
57
|
+
vllm/attention/backends/utils.py,sha256=56GrHMcL6g-7MKW_VPzE6b-SNGJIIV-UiWYRmDbnIXk,25995
|
|
58
|
+
vllm/attention/backends/xformers.py,sha256=4bxITBZMb_W3__8ueY3GR1ZCwrnU-6sVSx5kgQTz1Zk,33891
|
|
59
|
+
vllm/attention/backends/mla/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
60
|
+
vllm/attention/backends/mla/common.py,sha256=Hm7B1DYStT5H6UPBIiTeKdvQCGlhayyO1fpOSBSENHA,57866
|
|
61
|
+
vllm/attention/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
62
|
+
vllm/attention/ops/chunked_prefill_paged_decode.py,sha256=T63JOKLYGZErqGFnDGaAbrxKN6czkIKeSG34m-r4Jak,12710
|
|
63
|
+
vllm/attention/ops/flashmla.py,sha256=khmeRslq_BU7yrGhRUzHShRLeALP8OXVNzfdCVhEzkM,3953
|
|
64
|
+
vllm/attention/ops/hpu_paged_attn.py,sha256=h_kMJN7z3JV0ckHOcRRYmCHiA3UIIDxf630B_c5-S6k,2986
|
|
65
|
+
vllm/attention/ops/ipex_attn.py,sha256=7AVjr3jnRivgTgZxVSQYj3EEJ9TuAmKGjW5QF1YYXRs,5719
|
|
66
|
+
vllm/attention/ops/merge_attn_states.py,sha256=1ed_lE3BuH_ahf1PW4d0I6izUasZuKbQdKSeVLu6ESw,1706
|
|
67
|
+
vllm/attention/ops/nki_flash_attn.py,sha256=XIqlLhupMDdX4vGTyoHyTsRT2OWlxzCJoudEE6cTL5Q,32681
|
|
68
|
+
vllm/attention/ops/paged_attn.py,sha256=79sb3nWpOaZF-5YxqhqUSmOnhc209_Kf0l1fkfsaY9w,8388
|
|
69
|
+
vllm/attention/ops/prefix_prefill.py,sha256=ZelX65iQLi91xl7y9DpsfYiEfXjFmTjqHkeLPzY6kas,31106
|
|
70
|
+
vllm/attention/ops/rocm_aiter_mla.py,sha256=6RKmanIe8iZTQAMju9p9PCEXar7Q1oF6DamqmdkIkY0,3580
|
|
71
|
+
vllm/attention/ops/rocm_aiter_paged_attn.py,sha256=NofcR9IMgoqBVT-iyHNNFmJCmq6pv41deXucZcF-WPg,3954
|
|
72
|
+
vllm/attention/ops/triton_decode_attention.py,sha256=Wv9ZicJpuhnruLom2yeN4LMf4_mQOqN5ZXaxqTnaXOw,19190
|
|
73
|
+
vllm/attention/ops/triton_flash_attention.py,sha256=PyUtobu-7ZHIO8Fv-swpx58L6r9FFd-wUP4AILuRhbE,32259
|
|
74
|
+
vllm/attention/ops/triton_merge_attn_states.py,sha256=gKRLVpClXSa4wBO3HkFk4OBKtUPaNOUq7oJkKHQ5X0o,3563
|
|
75
|
+
vllm/attention/ops/triton_unified_attention.py,sha256=hMpRDwYSwaS-Yj-0R6pIazCGzmvOhWxOqpZJJ_VyDSQ,10771
|
|
76
|
+
vllm/attention/ops/blocksparse_attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
77
|
+
vllm/attention/ops/blocksparse_attention/blocksparse_attention_kernel.py,sha256=-l-CrX89lHlSlWKX8oPm1YICFLgJmWOj-yOMrc0mVXA,11603
|
|
78
|
+
vllm/attention/ops/blocksparse_attention/interface.py,sha256=B8Nam87zhetCakxhplBaTrGWgTfx5zYPW562KOIqDVI,9395
|
|
79
|
+
vllm/attention/ops/blocksparse_attention/utils.py,sha256=wS5dY0KCSVr9czfs0co93WuHLFziTIhlePjlD_cs33g,8178
|
|
80
|
+
vllm/attention/utils/fa_utils.py,sha256=H0xd2ONZzoibdctyBAzuOdDA6-jpjP7ntMbhteihyVE,2087
|
|
81
|
+
vllm/benchmarks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
82
|
+
vllm/benchmarks/datasets.py,sha256=9bCaWBNVE8JHeagDNmV-wmAJYx8KjbrziFK-Z-TD8Xk,44157
|
|
83
|
+
vllm/benchmarks/endpoint_request_func.py,sha256=r0fMEXJhQIxsIOyIxcgvR89HqUlKmG4B_CfAPQMZ4eM,14528
|
|
84
|
+
vllm/benchmarks/latency.py,sha256=res4151NBrj9zX_-qBVXGNmihj490wfSq8cdpbpqWsk,6047
|
|
85
|
+
vllm/benchmarks/serve.py,sha256=8TK8gi2Ht7mLOkexn6letAKsD4l8ykqtz-GypB3rW68,44843
|
|
86
|
+
vllm/benchmarks/throughput.py,sha256=9UFSkX4ATBFvIpxHmvkgij3lGU6ES3H08JEGXtDnl9E,24868
|
|
87
|
+
vllm/benchmarks/utils.py,sha256=a1KVuL7NttB3GP_aGBCls90lULsr2ryIA4PEv_92yr0,2247
|
|
88
|
+
vllm/compilation/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
89
|
+
vllm/compilation/activation_quant_fusion.py,sha256=QLg7qfOaIWv8nCslmq_JtMEZAlxaSmB4CSFWyET6a-w,3235
|
|
90
|
+
vllm/compilation/backends.py,sha256=ZLABN3Gva0F08PyU8nFWvNxrPFOy4m0w15zKp698ljg,22489
|
|
91
|
+
vllm/compilation/base_piecewise_backend.py,sha256=upn_akHBpZsFqq6N6b5dKKn0K-6mvEqIAkt1wtnaK5w,2865
|
|
92
|
+
vllm/compilation/collective_fusion.py,sha256=NoJ0fo8hdY9xP7sWsaRSlBA5yZms_G1zJjqA7bFOmLo,4332
|
|
93
|
+
vllm/compilation/compiler_interface.py,sha256=qnlAWsJQcrbA18jGXX-5ae1TgUvjGozPQyChoPEaxWk,22207
|
|
94
|
+
vllm/compilation/counter.py,sha256=3SgHVIe4QBRwnrhTfGYjWwV2em9JGYBCrPUU7d6benY,1141
|
|
95
|
+
vllm/compilation/cuda_piecewise_backend.py,sha256=0syIQ7CEgUn1EATdhlaiyCze6ZoDquWxL3NJy8CCTL8,9058
|
|
96
|
+
vllm/compilation/decorators.py,sha256=SOy5q_vIbYAQUfj2NpTGiOzmiSBODgDtFQ0FRpU0jEo,10303
|
|
97
|
+
vllm/compilation/fix_functionalization.py,sha256=SGqUN-XC3PlEhSQFSfi3SM5hzlPWaadKeujLP1jwF_I,8462
|
|
98
|
+
vllm/compilation/fusion.py,sha256=zgzbD4fhoqO_pr0MdiitG7fKF_msJqjiluzwYZDBRwg,24583
|
|
99
|
+
vllm/compilation/fx_utils.py,sha256=HD0dNMaq6RCx0LJ0R86S9GZ4BVwJgA5dP4zNeY3r6zI,2119
|
|
100
|
+
vllm/compilation/inductor_pass.py,sha256=C3vwg9EQGkqcK32ffo6lxkU1BB400gb3X7NO2mlydJg,3451
|
|
101
|
+
vllm/compilation/monitor.py,sha256=3eICJCWnpV8yFqh1W3Dc2pb5e78-lu_BoiVr5EvE1mU,1415
|
|
102
|
+
vllm/compilation/multi_output_match.py,sha256=uuVLvzaBuEZjOLbrfQVH9tZvaBD2GdNwbidSNaWv9dY,3904
|
|
103
|
+
vllm/compilation/noop_elimination.py,sha256=ABGKVff7gMb0gCkWAj-4Z5_tSqSVyy_LpyKixcPVPZk,5303
|
|
104
|
+
vllm/compilation/pass_manager.py,sha256=KBIYnBgOBiV_H1DBamEYgEwthWc51NH9ZcfkUTIE02U,2971
|
|
105
|
+
vllm/compilation/sequence_parallelism.py,sha256=AVR_vm3BSTJYNEGgyoJvEY-FrkPhbmMDnbpRiLZd5RM,9718
|
|
106
|
+
vllm/compilation/torch25_custom_graph_pass.py,sha256=OTZc1hc3eLlS8LhG4MvHwpglY5_1E_voPW7ShGS5HJs,1430
|
|
107
|
+
vllm/compilation/vllm_inductor_pass.py,sha256=DT6-FafI6GoMsatha-63vGGtJwZ8W6aR39cpd8T8MYg,2473
|
|
108
|
+
vllm/compilation/wrapper.py,sha256=J4zjVIUTfQ5nXO16kG2zUEfoi4J7LHO0H0bWoB0OIrE,5933
|
|
109
|
+
vllm/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
110
|
+
vllm/core/block_manager.py,sha256=0ZUWAiPHfAsP2vHK5o6eid0cI6qmVE4Abbl883ZE4NY,22273
|
|
111
|
+
vllm/core/evictor.py,sha256=FUiGVDiY8cmE59jf6ydo5CtYMEMGWWu6Zg6OLVyyQkw,5515
|
|
112
|
+
vllm/core/interfaces.py,sha256=90Km4Z25RxvUjTZr23sorms3bSyDsqA-viC9g903Ty4,3659
|
|
113
|
+
vllm/core/placeholder_block_space_manager.py,sha256=SXJsXrm2QoTI6vuLrxsBqHTITxyvzAkpO7bgAE1w5T8,3040
|
|
114
|
+
vllm/core/scheduler.py,sha256=YNrXuXDizcQJ4Ocz5ZMB7gbTOB8K-kGMqEvYDUG6AMQ,91778
|
|
115
|
+
vllm/core/block/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
116
|
+
vllm/core/block/block_table.py,sha256=Yokf5KU-onU1gp7dlqfWa0mQlCbtx9vNceGcg1dFDDg,16091
|
|
117
|
+
vllm/core/block/common.py,sha256=nTf2wtA0nWtbGoh5qsN8XmwIP8r9xlP8ry1lInaZTRY,13269
|
|
118
|
+
vllm/core/block/cpu_gpu_block_allocator.py,sha256=SKxpxXRGXLQuY3aFChuGkOnp_Ojpx_rFZJ0CMZY1FLc,17016
|
|
119
|
+
vllm/core/block/interfaces.py,sha256=BLv8rVkTVINbae_-Y5MLKUuZK-9Tix5qxlMRcb1jMRY,8213
|
|
120
|
+
vllm/core/block/naive_block.py,sha256=XPf0jZ5e5fJoXUss_Y6_mXAQ0D5bdYkCXZ2_XxlVoGU,16424
|
|
121
|
+
vllm/core/block/prefix_caching_block.py,sha256=BG_PRgkcH9vv25RhUlEVXPVSHBJw3ysKA-DSLBF2kk0,44251
|
|
122
|
+
vllm/core/block/utils.py,sha256=ecLOYLGeBIeqMCpbUNBoW6hJIHlG5EINgsf2Or1BHyk,997
|
|
123
|
+
vllm/device_allocator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
124
|
+
vllm/device_allocator/cumem.py,sha256=8mgglTfOAPBTO3A-aPswwh3HmGwye7UFoFoyhW49MuY,11018
|
|
125
|
+
vllm/distributed/__init__.py,sha256=l_KMMLMmYq-MqxY5OeTuQjA38RYwdS4TtVy8JafQq3E,191
|
|
126
|
+
vllm/distributed/communication_op.py,sha256=igCBXNoAhJ8eZooR79KhpzgYlVP1TUgnPF5C7BSpSJE,1562
|
|
127
|
+
vllm/distributed/kv_events.py,sha256=3A-SxHLe1Dar2IMHTtTlVHUTRjg1VSTvBUJzMMLmZ18,12357
|
|
128
|
+
vllm/distributed/parallel_state.py,sha256=xlv9jwsT7sVzpq7bX0VdL78WClFUR73MaNsSOxF16ZU,50271
|
|
129
|
+
vllm/distributed/tpu_distributed_utils.py,sha256=8xkJxtqRonnjlFMmbPA8-NeGF3KvjvQTgVr_3mMVQeo,7758
|
|
130
|
+
vllm/distributed/utils.py,sha256=K2CNfdyDZChfy6QWoMx-n6pDzbG8X4SBmdutEnhPNqQ,21012
|
|
131
|
+
vllm/distributed/device_communicators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
132
|
+
vllm/distributed/device_communicators/all2all.py,sha256=Vi-UzA5LJFl497LGOua0xTV8P-YP7uX0raQk6WVBE2I,9819
|
|
133
|
+
vllm/distributed/device_communicators/base_device_communicator.py,sha256=YeqXOmte0UY-kApX7BKBSjZ0TuQyOGGE1nh3OmgPsyY,10312
|
|
134
|
+
vllm/distributed/device_communicators/cpu_communicator.py,sha256=BQEdx2b0lsrjFKzWeCDmsKIMEUyPoUo-rssTiRIoHyk,5593
|
|
135
|
+
vllm/distributed/device_communicators/cuda_communicator.py,sha256=3muBQSx8tzsCSt0yiVxW69wIqTguhFmCgSjwt4ZLy18,7123
|
|
136
|
+
vllm/distributed/device_communicators/cuda_wrapper.py,sha256=1I1OZOc9-St5Zlr4gUmoDm7HxdS-T9ZE1ixOJGJK55s,7185
|
|
137
|
+
vllm/distributed/device_communicators/custom_all_reduce.py,sha256=h-P7nPNq6ZflvXdeqPvceE4aDxe3DVB60okDzVqbGWM,12675
|
|
138
|
+
vllm/distributed/device_communicators/custom_all_reduce_utils.py,sha256=FCWwNPzVLllZLBiK50myd3SlBiLIf0m1Ydpip5SM6OY,10558
|
|
139
|
+
vllm/distributed/device_communicators/hpu_communicator.py,sha256=SCAWX8SxecNzR79UE5AKysm7OP20nw_q-ABkLzqOtpk,1836
|
|
140
|
+
vllm/distributed/device_communicators/neuron_communicator.py,sha256=NF-k7fuSxpLtEatxVzTCt162N9rkRDTsxd82gV6J7VI,693
|
|
141
|
+
vllm/distributed/device_communicators/pynccl.py,sha256=6aOeCmloJqswF8rnfLhyuggNSN2D2SNDi4deLS7wj3E,9211
|
|
142
|
+
vllm/distributed/device_communicators/pynccl_wrapper.py,sha256=xeMmSohTi4kc9vFSnW25ss91HoVOvKNsff7IdIxtrEI,13763
|
|
143
|
+
vllm/distributed/device_communicators/shm_broadcast.py,sha256=x4C6QKStqUotHdkmI5OjcqWR24gA3U07v8V3t8EmC6Q,24959
|
|
144
|
+
vllm/distributed/device_communicators/tpu_communicator.py,sha256=mDqS1cHYs0zeptNKlMjkG667moa68Dc_Anx1iAVrfmY,4159
|
|
145
|
+
vllm/distributed/device_communicators/xpu_communicator.py,sha256=_a34w4noXIZW0099sLO3Z7CdLc-QC_NxKsnxH5wn5zk,2176
|
|
146
|
+
vllm/distributed/kv_transfer/README.md,sha256=B4s4s-6F9FP4wbgmrYJDSpdUu0_Yq4EeWLEyZMNkAyk,2006
|
|
147
|
+
vllm/distributed/kv_transfer/__init__.py,sha256=s4nYYd_WS6iDGPpYMvXnq8-x9vt-776yOsxnnRU2cvU,461
|
|
148
|
+
vllm/distributed/kv_transfer/disagg_prefill_workflow.jpg,sha256=fOFUEx-2Fm1uxHCGopvCREaRqdvR87Z7C0bMqEVH3Iw,142656
|
|
149
|
+
vllm/distributed/kv_transfer/kv_connector_agent.py,sha256=Pg8790EwU7LAYJMVdK8_jWs4V-7SYfQZjdzvSU0nvAE,2489
|
|
150
|
+
vllm/distributed/kv_transfer/kv_transfer_state.py,sha256=aYn9HaM0YH-4S-8V7R4wacCJ4kaYbXuOgZnhA7J2xvE,2335
|
|
151
|
+
vllm/distributed/kv_transfer/kv_connector/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
152
|
+
vllm/distributed/kv_transfer/kv_connector/base.py,sha256=pU3LM2zTdnzLb-GlxUeppL0i9Gl-ZoTew-Qu2U8ZSmQ,4490
|
|
153
|
+
vllm/distributed/kv_transfer/kv_connector/factory.py,sha256=i-kS8KBLQrH6U4YArb99wo6JqKrfXg0nxoHf9RKxXq0,4918
|
|
154
|
+
vllm/distributed/kv_transfer/kv_connector/lmcache_connector.py,sha256=14YN5LyPfFUPOlqXtAGp5t1c6d6AkeA7orahdQ7W2Xs,3739
|
|
155
|
+
vllm/distributed/kv_transfer/kv_connector/mooncake_store_connector.py,sha256=-Dd0D8xfrt6dVXhWy2CL6Dy6-rHaXkoBIFGWcYlOUqY,8679
|
|
156
|
+
vllm/distributed/kv_transfer/kv_connector/simple_connector.py,sha256=n-613lm8SPqXM2_fpJin3lYqePhbir3UpQu2eR48pp4,13926
|
|
157
|
+
vllm/distributed/kv_transfer/kv_connector/utils.py,sha256=aj28w0bLGPpUAc1FRnTNATv-B1TVTTUI77Gvc1XhZWg,4464
|
|
158
|
+
vllm/distributed/kv_transfer/kv_connector/v1/__init__.py,sha256=Vgcn88rEfiLwJ3-YkZKWsvMurr-vsV4_47b9_Mv-vlo,265
|
|
159
|
+
vllm/distributed/kv_transfer/kv_connector/v1/base.py,sha256=92ACWysP74FT4jc-m5A0WKrMj016UbzN2rK7RHiK6DI,10012
|
|
160
|
+
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py,sha256=RGY8QM17-GTg46L2KlZwRsX0qDn-55gFGuVD0uZeV5Q,5185
|
|
161
|
+
vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py,sha256=s9MS6JeW94duB9dw0OKkiUODHprffi6VtZz622s0Xv8,8243
|
|
162
|
+
vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py,sha256=oiGMxVMnH2SQ81HO97I6mtKRpqz2BKDTx84Fy6W19yk,46090
|
|
163
|
+
vllm/distributed/kv_transfer/kv_connector/v1/shared_storage_connector.py,sha256=zJmIJum57R6TRjXojfz1SSO8nLnGt9OXOVj3SR_70ZQ,15780
|
|
164
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
165
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/base.py,sha256=ZZYJZBDDny_StDcmXUFwOtDslRrTCL9iSUcr8XWe08g,6280
|
|
166
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/mooncake_store.py,sha256=atXfrR3n4MZAB88TtNmVAC5Gn9FhyVFcVRO1VjjL4uA,5679
|
|
167
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py,sha256=m8XNP5UiFwq2g33f3fiJeLMu87OhKwSvjWcI2jppztk,9156
|
|
168
|
+
vllm/distributed/kv_transfer/kv_pipe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
169
|
+
vllm/distributed/kv_transfer/kv_pipe/base.py,sha256=FHfg3C53oZjBBZjEWHmxMOPKTvJitfBOXXFzh8j70cU,2156
|
|
170
|
+
vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py,sha256=1agXvCvhn94CCK_0QbIcmOz-omp69UNCc8kCptsjlBc,12111
|
|
171
|
+
vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py,sha256=NjIOnIl2Fv7H7S-SZn2_xroAcZ39Vg2CCi90Q4iSRzw,9720
|
|
172
|
+
vllm/engine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
173
|
+
vllm/engine/arg_utils.py,sha256=DjwVO_y-9b2Ke6u507Fm9n7S5iS1aMoNY5PwyMwCvsE,78328
|
|
174
|
+
vllm/engine/async_llm_engine.py,sha256=8iiLRsYuNDmaqjYMLo--IgRvfDOP3MhWcuzJZvWgI90,49066
|
|
175
|
+
vllm/engine/async_timeout.py,sha256=uxUlhUevs6Ae1VvJ0GTkj23bAkg_w_CWteeXTCAFYvM,6594
|
|
176
|
+
vllm/engine/llm_engine.py,sha256=Rwfx18emhFb08QWllPw7agY-zajXKV-Vfyq65aT8hPA,91931
|
|
177
|
+
vllm/engine/metrics.py,sha256=LG_2wawnok658rpG6ZJFnMod7G8aydjteOYz4WwFMz4,26793
|
|
178
|
+
vllm/engine/metrics_types.py,sha256=8_E0ssV3TKZZr63dInytvsEluXgUvrPhrpnRPISUdso,3248
|
|
179
|
+
vllm/engine/protocol.py,sha256=Zoz-g1CBgk-9staLLGOlOPhdmGqRn8QkECGHRo3bJjo,11294
|
|
180
|
+
vllm/engine/multiprocessing/__init__.py,sha256=DMMFIKmNM1hn6leoQn35h2d5UaTpaHilKJfC2ar9jv4,3747
|
|
181
|
+
vllm/engine/multiprocessing/client.py,sha256=tWa-XGcWzDiwhnHTfnclR_eivmzxSJS7kyJDpa2c31A,28210
|
|
182
|
+
vllm/engine/multiprocessing/engine.py,sha256=27etqUvs7Qdkbo-aa577eZBSOXM545ZiT6B8otT7xXI,18400
|
|
183
|
+
vllm/engine/output_processor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
184
|
+
vllm/engine/output_processor/interfaces.py,sha256=jSj7l8R2YbHeKyDrcOamQAOZPgvarX2lERWMFFBJZd4,3063
|
|
185
|
+
vllm/engine/output_processor/multi_step.py,sha256=aZhtnbioId3KlW6nRc4GPJd_fHubXtaLoCx5ZabIbzA,9507
|
|
186
|
+
vllm/engine/output_processor/single_step.py,sha256=W11dmtv_-7wwuDafhgUdLR_Hf6GHrg56pmQI6LHITj4,6422
|
|
187
|
+
vllm/engine/output_processor/stop_checker.py,sha256=wPsxTqC2x2HkggUrTtnme3DL37gdwVZ37SDspMsdWTo,5137
|
|
188
|
+
vllm/engine/output_processor/util.py,sha256=358XXxAOG9vNO6uRTfINK0B-oCzqbidVpXfV5nrNs2k,1125
|
|
189
|
+
vllm/entrypoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
190
|
+
vllm/entrypoints/api_server.py,sha256=F1c5uZ-WFzmNtrpSH158bOzv6p623tmY7gimPZiwMGY,5818
|
|
191
|
+
vllm/entrypoints/chat_utils.py,sha256=DM-C7nv3WIoTXcZM-wnqd4t46aQu7RaQsFAHZ2wCQ0g,46925
|
|
192
|
+
vllm/entrypoints/launcher.py,sha256=l_VfSBIAVo-xE_HauO8G5GxKPcue16XdITvTxs9oyjM,5281
|
|
193
|
+
vllm/entrypoints/llm.py,sha256=m6bMV4v1XRiMXWtlJmlf-mc7YQzys_odzGGgbKD5JgU,69229
|
|
194
|
+
vllm/entrypoints/logger.py,sha256=fFcBqHM8hitDzkj-pNaFGN7EsJywkV8GXXI_ZsfL9u4,1685
|
|
195
|
+
vllm/entrypoints/score_utils.py,sha256=ZUxphYOqXVj14KbPAvvKgX2derLYMvir1rM2WXjsP3Y,1723
|
|
196
|
+
vllm/entrypoints/ssl.py,sha256=2InxP04Dt_I84ORXewngn5cUdXvRkrK_zZB6o8Ng60k,2805
|
|
197
|
+
vllm/entrypoints/utils.py,sha256=IcKt2N0a8Kk7wfZg0CmjlVci3LwODt1LfKGSPfHyX5I,9555
|
|
198
|
+
vllm/entrypoints/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
199
|
+
vllm/entrypoints/cli/collect_env.py,sha256=4GKIFhL_7kERjTJ0F-K18plm2wuEJolCjPKpTcdfMzk,1098
|
|
200
|
+
vllm/entrypoints/cli/main.py,sha256=9eUFDzgPMjvkyELCvOr4fd0CwMVZYnhkCILfr5jeL98,1795
|
|
201
|
+
vllm/entrypoints/cli/openai.py,sha256=8alMdXJ8Css2D5Xo76jJbmScCmONkr0gm_uKSjQTwdc,6921
|
|
202
|
+
vllm/entrypoints/cli/run_batch.py,sha256=_BwIdVKw9M0ERHhk37PC3C4wLSZdATOlmR9BoEjYWmY,2312
|
|
203
|
+
vllm/entrypoints/cli/serve.py,sha256=LPSKgYJK8CEg_gGpmDr-HtZPEIlCr8uYY7eAOnoON_w,12327
|
|
204
|
+
vllm/entrypoints/cli/types.py,sha256=OPisQT2_vqXvlETiUNd2xjH5Sau3qJhalpNBLrIhfVg,706
|
|
205
|
+
vllm/entrypoints/cli/benchmark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
206
|
+
vllm/entrypoints/cli/benchmark/base.py,sha256=GgBT4_2aIK2RcybeYOB5kbZEZRDpE58mbwvx4bk64-w,1174
|
|
207
|
+
vllm/entrypoints/cli/benchmark/latency.py,sha256=L4OBo9qy3i9d9zLbcezTGWnzygm4YmfBHJ5rbK03LJk,879
|
|
208
|
+
vllm/entrypoints/cli/benchmark/main.py,sha256=BaK1_IrQdE0jzEcCcREpXUfM90DFt6wXDhH8rkhrND0,1849
|
|
209
|
+
vllm/entrypoints/cli/benchmark/serve.py,sha256=-rV0FpX45O0NwPGNX2hKFDYIjajsyoSdQAXt6SCNcWU,861
|
|
210
|
+
vllm/entrypoints/cli/benchmark/throughput.py,sha256=MTK_QPQZUTECAJHcyayN-RsgSo86KYN-tQjb2fsNtGc,881
|
|
211
|
+
vllm/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
212
|
+
vllm/entrypoints/openai/api_server.py,sha256=MyNVvxTZ45dNvFpjdTbNy8xdyQDbeo2tEDsot8V81sI,52595
|
|
213
|
+
vllm/entrypoints/openai/cli_args.py,sha256=Z39HxSdJfIx_e6LCB72bGCjpEcsJdYWCBa2RUKsynYU,12362
|
|
214
|
+
vllm/entrypoints/openai/logits_processors.py,sha256=QAJn3DMAfFySExoA5aaSNVjXwtlOXGCv1DX6Fltj2ZY,3230
|
|
215
|
+
vllm/entrypoints/openai/protocol.py,sha256=nGzaaNrFvrlz-Qo9YN8T9aZ-XwIFduZBUgpqXuc4ziA,70885
|
|
216
|
+
vllm/entrypoints/openai/run_batch.py,sha256=1cj9gUT-tM9gIvivuur5eRvIun8MgLlkM8tdIyGl0es,17740
|
|
217
|
+
vllm/entrypoints/openai/serving_chat.py,sha256=6aIGheQ77SVWQzgThno0zPnh0dedDbwsQv42fJACtcY,57820
|
|
218
|
+
vllm/entrypoints/openai/serving_classification.py,sha256=8bcKvF1Nnp2MjcphEGke8ar6srj-Ef1gkFF5CzgUduA,5335
|
|
219
|
+
vllm/entrypoints/openai/serving_completion.py,sha256=oVirjXifsLsQzf6Mke1f6dfebFVrMRhVL-8PloCOm8s,25584
|
|
220
|
+
vllm/entrypoints/openai/serving_embedding.py,sha256=ejT3CsStaQQFYO3Vms9tsitHkaumFMHr6VxkGq4CWKc,7384
|
|
221
|
+
vllm/entrypoints/openai/serving_engine.py,sha256=inA_0HSBExYAN7XnZqVNE-oAkg__o-EfIkaUEQf6pDo,38711
|
|
222
|
+
vllm/entrypoints/openai/serving_models.py,sha256=GYqPJtMw350_fpm8b0kxjHU1z_omJQTPgptTq0lJgPM,12797
|
|
223
|
+
vllm/entrypoints/openai/serving_pooling.py,sha256=yKTe7YqS_ynztPjYRiUXhkmi1bq5KatLotNzUjkZIPE,8719
|
|
224
|
+
vllm/entrypoints/openai/serving_score.py,sha256=cpZSoRdaIUajrKo7rNWlY-jKODHKHY0Tf9srOMry4Sk,15976
|
|
225
|
+
vllm/entrypoints/openai/serving_tokenization.py,sha256=9SMgGGjM3uLkmXRfzRno57BEX6xOMgSm9pJtET1XCTM,6090
|
|
226
|
+
vllm/entrypoints/openai/serving_transcription.py,sha256=i8zWUiQJklZyD5D2S9EfxvhZWkIHzXBasZn7zAoO-1U,15843
|
|
227
|
+
vllm/entrypoints/openai/tool_parsers/__init__.py,sha256=xbsgwoDLlW3vqIer2iscCEZnb0YWkz1UeAf4DN1lE9w,1104
|
|
228
|
+
vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py,sha256=UyO8engPSTh8Ej8EuQay-mDz9YPzHAsmzJA43-4vmq8,6095
|
|
229
|
+
vllm/entrypoints/openai/tool_parsers/deepseekv3_tool_parser.py,sha256=gKlW7rFyEx6lZJmkKdEuyqz5F7MGJPkk0zwtd9aZ8rY,16678
|
|
230
|
+
vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py,sha256=YqhxroDlNDpZOwbrAHrdpBLKRnahVNQahd2N2z9Lpl4,11502
|
|
231
|
+
vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py,sha256=1LKw06AkMy82c4zXRu41Edthks6Z4xazB4nyhLiRy9g,10723
|
|
232
|
+
vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py,sha256=BTNW2L9BHkqNEmiTkqTZlYrCecr5KNIIvbAB4SIquTY,16891
|
|
233
|
+
vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py,sha256=t5AjAiwJsYdLMurJJROlGPHXiEpMgO9NLGQAT_du2RA,9461
|
|
234
|
+
vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py,sha256=R1uMMM4Vnji28xyHVqB1N2O0CpHaW6NISeoc1NsxjJQ,13947
|
|
235
|
+
vllm/entrypoints/openai/tool_parsers/llama4_pythonic_tool_parser.py,sha256=k6f1xFWCjG1KIyHOQ-bN2nYaPbgW2bNvkMpn8GV2FsM,13258
|
|
236
|
+
vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py,sha256=yY9n9uxy0q5SQ5yI9VGf6dSpOcde-3gY-o-wZjSncPU,12313
|
|
237
|
+
vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py,sha256=ipV3kFRxjoOywvxXfo4bVV9Fyc38QEeQLEZ_vYlv82g,16553
|
|
238
|
+
vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py,sha256=o7RbhWFthf2VKwtuxZfZyVdJAQ_5iOuSLHdsoz2Hf4E,4346
|
|
239
|
+
vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py,sha256=xJELNmJ0_6tHl6OZh_EmY57b5QjGO1yQ3rLI46XoozU,12636
|
|
240
|
+
vllm/entrypoints/openai/tool_parsers/utils.py,sha256=RrvMsSpaYYMPefvM1ktVKzo9Gs5KsHpi21QaP1h4EKU,3874
|
|
241
|
+
vllm/executor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
242
|
+
vllm/executor/executor_base.py,sha256=L9dpD4kIXgn2KJ5XTHvtZ2OpMXM1JEJfZ1-QVIbCcRI,15732
|
|
243
|
+
vllm/executor/mp_distributed_executor.py,sha256=zhyIz7Smu33879dkoQ4FHO0r47BSWjBnFfpwWjqsf-w,9923
|
|
244
|
+
vllm/executor/msgspec_utils.py,sha256=0tCYOinMJxzOI-U8fAY8C9A9seN0f4MdaE9H8PJuuAE,978
|
|
245
|
+
vllm/executor/multiproc_worker_utils.py,sha256=1Ddh8AEFrh6GIWbRqm7I-Kupluw40FPIVijgak_5434,10794
|
|
246
|
+
vllm/executor/ray_distributed_executor.py,sha256=dkxCh1bmW39r0RGgLYqI7eRz7vsqt0owBZrF9AxgIDY,30775
|
|
247
|
+
vllm/executor/ray_utils.py,sha256=rsav_z9cZnKIGz37knp2YUtx3ThtYAdP85smG2y21d4,16883
|
|
248
|
+
vllm/executor/uniproc_executor.py,sha256=23FH6Z3EqfCQEf7IOFFkhKIaycByazM5EkQrUNoZkbM,5548
|
|
249
|
+
vllm/inputs/__init__.py,sha256=8cagQSlaOP05DjPdGL1EPpOOYaYkWlNHzQ25JigzVu4,1329
|
|
250
|
+
vllm/inputs/data.py,sha256=_KoSfLXeSwi4981LvUyMJU22Sjs2oO4KfkRUKcth2RA,10829
|
|
251
|
+
vllm/inputs/parse.py,sha256=_Lbf4PQyczm3OPsLgvyPf3CiKGNP1Ctd4bW_AnuORpk,4499
|
|
252
|
+
vllm/inputs/preprocess.py,sha256=bBfQA5MfOD9UJix2qhuWnCUYCcib847zsEEgP3qjZe4,34416
|
|
253
|
+
vllm/inputs/registry.py,sha256=8aAcHouGBJ2KVvnTzUhwsCbSc2MztfZNOMmbyBIXoL4,7482
|
|
254
|
+
vllm/logging_utils/__init__.py,sha256=lGnFUwOOIQYnuCu-Pf3LKtxPRmx6DgkxlxknU9fO3-Q,205
|
|
255
|
+
vllm/logging_utils/dump_input.py,sha256=mCQrk4AI6K7w0lBbYWVfRf-44Z7WBbZLbnuRbIk9Ioc,3110
|
|
256
|
+
vllm/logging_utils/formatter.py,sha256=kIZNddJTgIcB1RRoJc0fFmDtsVv3X0GGUgblS2PdW48,594
|
|
257
|
+
vllm/lora/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
258
|
+
vllm/lora/fully_sharded_layers.py,sha256=6o8xjkxFJd1A6ESz1KeEDPYWrs0RNjHAJZ8d6IUntc8,12694
|
|
259
|
+
vllm/lora/layers.py,sha256=-iEPCZ9e5oYUQBDdS6RFqyIHh2P7_0GXvFe2aXs49ss,46740
|
|
260
|
+
vllm/lora/lora.py,sha256=AuAxQNXr-6RLCn7Kc28qqbgA715IDb7yfuReHchu10I,6294
|
|
261
|
+
vllm/lora/models.py,sha256=Gb75UF3VRAdwXBRISlCiyfDkywACBvlA0oGTK4SFqV0,36053
|
|
262
|
+
vllm/lora/peft_helper.py,sha256=VBwUFq0hnhQZK8qL90VEjazb4ClFDO2lro_-UVwOYcg,5334
|
|
263
|
+
vllm/lora/request.py,sha256=spYbJvjKyPlu1a1otY3sxI4JBpAzUvLLjhyxFJP2Cg0,3178
|
|
264
|
+
vllm/lora/resolver.py,sha256=6iZpDMfxWGcy8MWlj3nCCcVmgr6nKs8EzzOhaN4TiCs,2881
|
|
265
|
+
vllm/lora/utils.py,sha256=yi5k_4gUwrJv4g_rNrEgUMUBci2xASELsROgOUISC8g,9318
|
|
266
|
+
vllm/lora/worker_manager.py,sha256=-kKrfkTgU16e5QggBmDfUB1DEkvMronp9K4fiUruzMo,11107
|
|
267
|
+
vllm/lora/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
268
|
+
vllm/lora/ops/torch_ops/__init__.py,sha256=ywu1d5miStgp7A9BRAo6kUvuE3AcgOAOJHxYHD4cKvQ,535
|
|
269
|
+
vllm/lora/ops/torch_ops/lora_ops.py,sha256=LOSdfKpQM365cIWVkyElcLpfgn8cF44IVw-KUN2NMKs,4517
|
|
270
|
+
vllm/lora/ops/triton_ops/__init__.py,sha256=arDrNt_kvrDaC4mN3RNbu6-0YACXQRp9Md2cJxXI1ao,384
|
|
271
|
+
vllm/lora/ops/triton_ops/kernel_utils.py,sha256=3P-CWMjNQR2vp3QUNynjXAIaWQy06mEFDTRLRQljDME,8509
|
|
272
|
+
vllm/lora/ops/triton_ops/lora_expand_op.py,sha256=740f2SjW7lP2rtbFIGFl2e-FnCHxGv_tVs9WmbqftBE,8965
|
|
273
|
+
vllm/lora/ops/triton_ops/lora_kernel_metadata.py,sha256=YgL-K9fVeFZebx68DJNvrqsfZI5o0thpa---d4NYlnA,5967
|
|
274
|
+
vllm/lora/ops/triton_ops/lora_shrink_op.py,sha256=WfuQ1-7dtJAQ_Pc7sN8yl7jRkcsYX0MXZ08uwatdEfg,7996
|
|
275
|
+
vllm/lora/ops/triton_ops/utils.py,sha256=zsQcSl0sWdYUefY5IWqVOpjdXySLSSsHgTwNPwKkWJY,4916
|
|
276
|
+
vllm/lora/ops/xla_ops/__init__.py,sha256=2Yh5hqiUt7hGz9SwznSZlj-_G7-SknTauNyHGDcUjBY,304
|
|
277
|
+
vllm/lora/ops/xla_ops/lora_ops.py,sha256=hLERTyHuXcH5J5ePn_3cak2Mi5S8_i0BcXiJmNZHBEk,4400
|
|
278
|
+
vllm/lora/punica_wrapper/__init__.py,sha256=A5cDJmdCPRBN23kwLfemRlWI4YA-t_7qIxeoeimCkT8,313
|
|
279
|
+
vllm/lora/punica_wrapper/punica_base.py,sha256=oR-f11G-ga_JOazy2M3iBoBaRb1D6ifWn7xbkCB3gGI,18500
|
|
280
|
+
vllm/lora/punica_wrapper/punica_cpu.py,sha256=sFBBu_qBEL8LGALamK7hE1ympyipYNT4qpav-V1nllU,12527
|
|
281
|
+
vllm/lora/punica_wrapper/punica_gpu.py,sha256=Wg8n1z8_pdxolBakhIPV8rNi059HnmzK2l1kPS_2LV4,10885
|
|
282
|
+
vllm/lora/punica_wrapper/punica_hpu.py,sha256=qljiMC-THj_SIhaFeHygMQuB13wBKyz7dr-ba_aqpaI,5848
|
|
283
|
+
vllm/lora/punica_wrapper/punica_selector.py,sha256=Of6p5uYMMLnA6g46VK7M3xJT8Xq4q1VFoeOpTIsPf3s,799
|
|
284
|
+
vllm/lora/punica_wrapper/punica_tpu.py,sha256=utenbLEam1-CCYjnXFDC-zKfzp2H8ndBop3XRlCp5YU,16290
|
|
285
|
+
vllm/lora/punica_wrapper/utils.py,sha256=vOSc9EvIlgLbdJq5iZ7LOLdkadvPX18JbZZei2OO2eY,7050
|
|
286
|
+
vllm/model_executor/__init__.py,sha256=vE7mcT8ZyKWc-wlc4pq2-ofRwEDVYT67HSgD-hLut0Y,574
|
|
287
|
+
vllm/model_executor/custom_op.py,sha256=Ugjx_52-NSL7SWVL5Kg0_I5X-Yzpz3Agr_qSictAx9U,5669
|
|
288
|
+
vllm/model_executor/parameter.py,sha256=H_qq9zP0q0QbDaPbDkH9coanlZZVWsTZ_kbvlt7KYEc,16758
|
|
289
|
+
vllm/model_executor/pooling_metadata.py,sha256=bbOjrSCh_8aX9M3oML5oyUzijmJhy9Gb5_7bURoCi6w,2127
|
|
290
|
+
vllm/model_executor/sampling_metadata.py,sha256=6uc7pahkFyei2c-4Mn0jX10MQFQKKKhm7VJUCxRbQ8Q,23013
|
|
291
|
+
vllm/model_executor/utils.py,sha256=yt3QtDHwHpiQJA-vPrVpsG3dTMEAzACaxc0gZ7ie888,2921
|
|
292
|
+
vllm/model_executor/guided_decoding/__init__.py,sha256=XEvEfOGGBuBsKrwc_mOi9XjbzCdr0SK6N0PmyWyhyVs,8332
|
|
293
|
+
vllm/model_executor/guided_decoding/guidance_decoding.py,sha256=-goDVm60krE6RH482nbUTXSeDQ0jnxnWVCW3ep8qoRo,2600
|
|
294
|
+
vllm/model_executor/guided_decoding/guidance_logits_processors.py,sha256=mcy35zX1YHfKoxJZADvLxkP5F8OYiEHO_P-Xg_lQZrA,3344
|
|
295
|
+
vllm/model_executor/guided_decoding/guided_fields.py,sha256=KSAGqffFpedIz4LfgwAodX2eJkyOZ4RTD49ynzSbrTU,1566
|
|
296
|
+
vllm/model_executor/guided_decoding/lm_format_enforcer_decoding.py,sha256=jl5gxFhJkIL2pSOzKhgyHL_1qRszIakyNN6LbrFJXfs,2747
|
|
297
|
+
vllm/model_executor/guided_decoding/outlines_decoding.py,sha256=-MKzmEGn1QuulI2JDU1cAejfo03nHxlQluadMJe27h0,5571
|
|
298
|
+
vllm/model_executor/guided_decoding/outlines_logits_processors.py,sha256=UfCgpaI1KwSFNjtQ-2lmBTYkLszSXQrVZhtvKpeKras,10889
|
|
299
|
+
vllm/model_executor/guided_decoding/utils.py,sha256=n6prXaBa-qiTes5wPhIX6CJg4Chrje_wQNsWxYuiYf8,7966
|
|
300
|
+
vllm/model_executor/guided_decoding/xgrammar_decoding.py,sha256=plEHV0pFHJF06jgMg2w1Tlok2h31D3M6C2GA-Zpx7lU,16833
|
|
301
|
+
vllm/model_executor/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
302
|
+
vllm/model_executor/layers/activation.py,sha256=JkTpc5D05uhREoAs_zk4t64GP-xxefz3VdBBpg0cviE,12584
|
|
303
|
+
vllm/model_executor/layers/layernorm.py,sha256=_tQTYGrfHXNqPc-WXdhqtK1XQzJ-yIpIRwOhDazPqKE,9230
|
|
304
|
+
vllm/model_executor/layers/lightning_attn.py,sha256=KqXTG_XlaAu2K6kT1wSNU5fGAKWEcrZR1CR0RmdpxCM,20962
|
|
305
|
+
vllm/model_executor/layers/linear.py,sha256=GrK_DBoCoMoNCTfj4oNo2aMPdfptz0OqUfo6H3_YFTU,65470
|
|
306
|
+
vllm/model_executor/layers/logits_processor.py,sha256=ehI9fTIQE3eOUxZTl9tzjYSWtq6NtPvPPW_HlzqYBq4,7825
|
|
307
|
+
vllm/model_executor/layers/pooler.py,sha256=T8aG7N0dCDM_ZyIRHdIBbFHjXJMYu_2HGyLVs7Ge4o8,12158
|
|
308
|
+
vllm/model_executor/layers/rejection_sampler.py,sha256=CEugEvE9tmLJqaCGx033TFMQ-_xGAeNKFByYrQFKt-g,16384
|
|
309
|
+
vllm/model_executor/layers/resampler.py,sha256=jDG2clcusNHfxLptLZUbbwxmxC3f_I-KJ8tJIdjyuLM,10506
|
|
310
|
+
vllm/model_executor/layers/rotary_embedding.py,sha256=nGMjpuERRXO1OtuucAQ9E2Ok0CepunDnGhIifdwAyKU,78083
|
|
311
|
+
vllm/model_executor/layers/sampler.py,sha256=gOsxvuWntPAVabVMCKSma_pS6XnmOr80QMAE1iAxdbw,49689
|
|
312
|
+
vllm/model_executor/layers/spec_decode_base_sampler.py,sha256=ZtvhMhd0DYJlYpqkLyIoiUec0gvqVT8IqnotqN60EAE,10253
|
|
313
|
+
vllm/model_executor/layers/typical_acceptance_sampler.py,sha256=AZ-q02vuqxGMQLgBL07uLl67T3Zrw_YtwglJwmyu5UA,7026
|
|
314
|
+
vllm/model_executor/layers/utils.py,sha256=RYUsT7GZniK2seIQGxARh2Uph90KIceza9SmpWCoNaQ,3851
|
|
315
|
+
vllm/model_executor/layers/vocab_parallel_embedding.py,sha256=DWzKb224fam0ctWb769LRHXzh7Nq0YmLyuGeNXvD7AA,22765
|
|
316
|
+
vllm/model_executor/layers/fused_moe/__init__.py,sha256=Yf9Pz1_mAfW6V1Fi6NLGSiqGz00lk0FJaCNnuOMzHUM,1434
|
|
317
|
+
vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py,sha256=zzl3sQxTCF7C40De8xM-nZiBVPEIyLGsddyvvrVbrRE,4637
|
|
318
|
+
vllm/model_executor/layers/fused_moe/batched_triton_or_deep_gemm_moe.py,sha256=-uBk2KEGa6zf1xXuzKyzLdash630CE7nLogqZBlAHrQ,4876
|
|
319
|
+
vllm/model_executor/layers/fused_moe/cutlass_moe.py,sha256=prI3_SnvLsDx8mM74LLFw8uEn5ZkG4KC3X_Bl8yKFJE,18969
|
|
320
|
+
vllm/model_executor/layers/fused_moe/deep_gemm_moe.py,sha256=3YREsVaktZLc_VAxlaI_BH2IZPtsPgayejLhuUsHLN4,8408
|
|
321
|
+
vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py,sha256=oFlutUNnQxAtZEr8ehyJQ5NeioDtC5-6KOwHp28qV8Q,10076
|
|
322
|
+
vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py,sha256=BDCcEym3y79KsQA84SL81zNIazr0XKzZXPVzoTcL46w,7391
|
|
323
|
+
vllm/model_executor/layers/fused_moe/fused_batched_moe.py,sha256=LRHXdmPPiVm27VaIHbhD-G3fS3_als2IDOO1boBXO8o,26614
|
|
324
|
+
vllm/model_executor/layers/fused_moe/fused_marlin_moe.py,sha256=Goxq_TjD7ls01emorNZsGDhGZJmtOYAl-b_Q0UdjDA0,8911
|
|
325
|
+
vllm/model_executor/layers/fused_moe/fused_moe.py,sha256=KGxqU8k3wJPcfTmlYgn-oTgkqFzG8ABklGi3AhIObSw,69329
|
|
326
|
+
vllm/model_executor/layers/fused_moe/layer.py,sha256=YPu4_JQrIV6CRxHdqgz1eI59woX3ni9gcDDmMVNedfg,63828
|
|
327
|
+
vllm/model_executor/layers/fused_moe/modular_kernel.py,sha256=lw0mpzbEMYsip0kZit6ERAispBdELtUfmoNo1lZm-OI,18014
|
|
328
|
+
vllm/model_executor/layers/fused_moe/moe_align_block_size.py,sha256=CHcWjXIHHztUit7b67lvQAFO_IfqO1W5XuhB-LepXf4,8340
|
|
329
|
+
vllm/model_executor/layers/fused_moe/moe_pallas.py,sha256=AynMAg-Va0T9qvSeofHp4ZuRYWN6pQdZPTL5EKHRcps,3158
|
|
330
|
+
vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py,sha256=A8JBstS-8q_zQG_QCcSGrQUpFgajfE-rOxIkrkVRYCA,7973
|
|
331
|
+
vllm/model_executor/layers/fused_moe/moe_torch_iterative.py,sha256=ZSvVVU8rUzENLnHycTypPg2UhO9eF_eu6wm1HEtpl-s,2156
|
|
332
|
+
vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py,sha256=GVhqzJdlFoRlNSamOcs79OStkDaGMxQaXw7YN26GFD8,5780
|
|
333
|
+
vllm/model_executor/layers/fused_moe/prepare_finalize.py,sha256=6Ymie6pXbphT9cH3_NO6DuRJB3QkGBlN8e2l6hjTbDE,2462
|
|
334
|
+
vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py,sha256=V31muuurjEsD8vI8dfxX59HOUITvZ0bOQjsIFE5VcpQ,14558
|
|
335
|
+
vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py,sha256=4jfw4S_iB8koAGkdtYxeb8d720DI7HTDy7tqlx64cUc,4298
|
|
336
|
+
vllm/model_executor/layers/fused_moe/utils.py,sha256=SI2vXr4Q_EAWfMODbSRqpE4OgdYn9M8MZwy5kYiAGA4,3281
|
|
337
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
|
338
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=hH5rRN9Wtyv35azxMzyUMHWtiKgOHev5tNjIG8j6dsE,2751
|
|
339
|
+
"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
|
|
340
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=s47lb8VLnyxMgWlqcIR4BdPBsjKWL4olXF49uZvygzQ,4140
|
|
341
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=gzfjrYDcS0vsACq7ONGVkNA3FqVjr3e89q9fO9kokkg,4133
|
|
342
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Np7yRX9Z7Y7Z5Nutbl02wpKdZRltbt4WqlPlleiYs2E,4146
|
|
343
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=XsNfNXY8v0eatazkLCDiDclI0FnTudUGLYO01e1_4aA,4149
|
|
344
|
+
"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
|
|
345
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=arPqstZMzZjz8BNpY3alKT4vGCJyUj5I2hEeK02aq98,4152
|
|
346
|
+
"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
|
|
347
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=7WHPz_0fxeI3Ed0D9VIpZVoeN9RtJVVARvptfcmQu40,4146
|
|
348
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=2kWS9Qvy5Q3mvUFmbPVures5iZAriAXsy8WrtE5wu00,3727
|
|
349
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=D2dn9vXyN4FCKsZCf7VYgAWLedCx8XpPjbkQVVAvwAA,4737
|
|
350
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=5QqFljwwA8OaPlFnXy1zogl5oi6aE0OqN39xk2IUC64,3245
|
|
351
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I3k416HbXU_rYb8scD8gAI4fuBlElHl06PM347Qa11w,3253
|
|
352
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20-3e.json",sha256=CoC3pMKx0vkjI9T6rqRLTIwbDskxljTj31fCHI34B5w,3232
|
|
353
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20.json",sha256=RgV8C4F1LO09h01YsgF_eqX6GNoBtC7ulPfJRUUbg_g,3241
|
|
354
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H200.json",sha256=nsNEuDNks0tVLfQfIm7xxFwEeptTfQcoa9fJy0NS8xQ,3247
|
|
355
|
+
"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
|
|
356
|
+
"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
|
|
357
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e.json",sha256=gkimxy2r78McckKxx4U4R3xahTI1KMH2pMOdUFOUdu8,3234
|
|
358
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20.json",sha256=vS2DRIDOqWyiBvbG6H746ownfkD1F8Aj2YZ0ET9xll8,3232
|
|
359
|
+
"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
|
|
360
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200.json",sha256=xqhl748it8GV2KXX0XixitE_ywnsKksqK8AGL7tAgT8,3254
|
|
361
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=FsWbV4Q6AzAtgegVuENBDz2ZcSJsqNiwUIVfQbpP7hQ,3244
|
|
362
|
+
"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
|
|
363
|
+
"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
|
|
364
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json",sha256=10Ntu2aVD5vGLonx-jW0qNw-tgZWdZmzMGx7utDVeng,3237
|
|
365
|
+
"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
|
|
366
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200.json",sha256=JraM-Nvbg5V_TJkSl6UPFYZN1zHHoIbr2pAcksenoTY,3248
|
|
367
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=96,device_name=NVIDIA_H20.json",sha256=JtcHRlPz8xQEAqJ9EWI63oYvdmjQFG6VTHqtt85VOSA,3221
|
|
368
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=f3iM3xm8hGUirJ4ilAIPO6Pe9bs4sm3qaRKMswN9SKE,4731
|
|
369
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H100.json",sha256=Bq57MPQXuSib06u6OwiEmSzOr3XvPYoD6ohYDJaBnII,3244
|
|
370
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=pCCKkdUzzuBVtljyk7AEIAbeDf12DUiieXaODZXzm5E,3254
|
|
371
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=trX2-c4N6hTTD6zFNi6A2bT3FkhxKjkM2rPl-o1K9ss,3250
|
|
372
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I4d56uD7E1JMXD9RAxq3FebdPquDsnNEkVaIY9Ctm9w,3246
|
|
373
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ypuAxMQ7JESPXLBltt68wly2wTrJzlnobhUMip6xAmc,2751
|
|
374
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=tUptlureu5QgyAEedtx5sm7CFudXAE6fIXepOb9gfas,2745
|
|
375
|
+
"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
|
|
376
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JmXhUnhX6YOy8RsmT0zFLGyNCpRBPV2q2Db9Y9ctZeE,4144
|
|
377
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=G4PKqWxh0MlBhg7QHKj0m--_fP3Ll0gs7VJaeg-NIDM,3254
|
|
378
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=bKX9AvcxN6k-i3RUmHSchZZ3rjoYRYb4iBqhCI4L3MY,3257
|
|
379
|
+
"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
|
|
380
|
+
"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
|
|
381
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=_9HO7SaR6aQeh6vqCDpo3kjHnGJ9BVKLiMwYYgd3SmQ,2913
|
|
382
|
+
"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
|
|
383
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=Twkm9DVNxijpowfvioJ_4cKwIIlAWdyNWO9TA3gxAHs,4149
|
|
384
|
+
"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
|
|
385
|
+
"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
|
|
386
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=iySqae0zI_PRBLqV-vfSCwDS4Jxcl5QjWa2NnhndL0U,2752
|
|
387
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Uhq0SrWiCrldkWbb0ZZZhWaCZ0SsvpiNL4z30KZUN5g,2747
|
|
388
|
+
"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
|
|
389
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=TtDngG7ljrU5RtWZ7g-xxdBT3uEuawiKhP8EwPr97XM,3254
|
|
390
|
+
"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
|
|
391
|
+
"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
|
|
392
|
+
"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
|
|
393
|
+
"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
|
|
394
|
+
"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
|
|
395
|
+
"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
|
|
396
|
+
"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
|
|
397
|
+
"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
|
|
398
|
+
"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
|
|
399
|
+
"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
|
|
400
|
+
"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
|
|
401
|
+
"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
|
|
402
|
+
"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
|
|
403
|
+
"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
|
|
404
|
+
"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
|
|
405
|
+
"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
|
|
406
|
+
"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
|
|
407
|
+
"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
|
|
408
|
+
"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
|
|
409
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=rVORXxNsxy4WmO5SJR8Sd4k7vozKqhYf50wZNCMeQzs,3239
|
|
410
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json",sha256=4UXbsSNHmrSWnD85SdRMLp4cFGRufndzJjB6hoQPclU,4736
|
|
411
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json",sha256=p6TKUp-KDeLB9E9LqThR1e7J2-ogSXPJojISdHgCxaY,4727
|
|
412
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json",sha256=gHxtmO_uvpueLVlsJgXBVE3_pS1S9EeRxNmHG_ZQszg,4729
|
|
413
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json",sha256=tVdpbIU1scsylx6oz3IADhkcwvZaNqw-_QVb7a6oVX8,4732
|
|
414
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=6QPLhZurIqcMVdy3w0Dd7gLViKxsyJRBz-qd8agpi6Q,3248
|
|
415
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=WPu80-OWyEJBy1hdnewLN1H1neFW8UVJrqyeDGegXc0,3250
|
|
416
|
+
"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
|
|
417
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ozS2ECxk-Dsd4Y9DgCGGwDwJlCf5T20ANf5gnTUMuSc,3252
|
|
418
|
+
"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
|
|
419
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200.json",sha256=w18R3eHB4oUhfbcCXjHyDvp0RiDSeCrfM-VFESim2hQ,3253
|
|
420
|
+
"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
|
|
421
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=dYpKgvuG7Jji0W0zg_E9NfIojStBAdBcKd4B3nhimqk,3263
|
|
422
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200.json",sha256=CXiHlGpea5cEGmFi28Jec34uxEZITF2XldVFcJteZX0,3251
|
|
423
|
+
"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
|
|
424
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tku4-yTbIr0H5TNrm1Pq3tJJFYTXqHpdzJDSEF3bk9A,3238
|
|
425
|
+
"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
|
|
426
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200.json",sha256=bM9g-XpirsThO3Q2x8ChSx3PPtHuHRXLvVMnTWt8jLI,3243
|
|
427
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=oxOKFDrgmw1YmgxTtRa1uoe3p09ylTLrkj_jOTqNh1Q,3249
|
|
428
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=-B6gZAEYLwMJZOnpO81pTxqs-YVKs_144Nn9BSLaMh0,3247
|
|
429
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=GPjPHicomrS7ntHu7nnvgNXcHCoUw9vhyTUewkXpppo,3252
|
|
430
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ObHUCUAgHTnld8Cq9Dy1n3ilmbBzyNC4jZcz6YYhMXA,3264
|
|
431
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=WegYsHl39QVlHu_4EZJSrgA4LQ5fYxSVNWFhoL6W2Rc,3251
|
|
432
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Hrlas0Nt7d3JMr1vTpI3OVgkzxqcRziSMfFf_U5pQ58,3267
|
|
433
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200.json",sha256=J59rmqF8NQWkqmay__ahA3t3IwaPXNu5AVNLnTaDfYA,3252
|
|
434
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=896,device_name=NVIDIA_H20.json",sha256=GNbp4W4MBoHHN4-0sXJovY0lX6rHfZzGyKicrumupGQ,3225
|
|
435
|
+
"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
|
|
436
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json",sha256=FsIv5bqSpkWbxK2dBfg1N6tX9epZ55ZhgkJCD7hENlY,4733
|
|
437
|
+
"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
|
|
438
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json",sha256=fnO-v4YqBz0vUo0UtOTTD0n7VDG_ivczeQ1tR6Qm9f0,4734
|
|
439
|
+
"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
|
|
440
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=QaITFIJU4UsrOBXaGdPYJwTmYJ0nT9kiiqeUiZzvd1k,3270
|
|
441
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200.json",sha256=CC_jsMhXzrYne7eIOroDa0fCBKNnffiaVW2TKd4P-ek,3260
|
|
442
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=LgHbxG1kQV36zZPkJcnurHYzwAjMh04lvEHEsfzS1t0,3732
|
|
443
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json",sha256=_fcdkmWvdMqHiH8ZAGke-zXhH7qVPQx5CmKELW5hRCA,4735
|
|
444
|
+
"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
|
|
445
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json",sha256=JKYW21c0CzR0fgE5ZnYp6C1sY_tVRlm8L_lgak5V5zE,4736
|
|
446
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=yTf2R9cngSf4OafucAYlDDn4-bftaMFKaY7qhaBZPqQ,3739
|
|
447
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json",sha256=_1eVE7ok935L2V43-3D3bVNWSVaoViia19sh0VrXmXM,4735
|
|
448
|
+
"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
|
|
449
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json",sha256=18v6YruKbQ95pXPV8ocV4VdM1zNw3aZFp3WByeUkNSM,4736
|
|
450
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=AffDc0_51ML8HiA3757zbD10TZJdUsUDIYIqO4g0yUw,3250
|
|
451
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=IEYBNjt9HGnzoOVSWvL0A0jUqq926QD0_BvVYR4RA1Y,3252
|
|
452
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=Ns9Y12aZbJnFhcG3nwb67bDqqiQAo9tdTAIe8K2Ajz4,3255
|
|
453
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=uGSLFPZXK_JQ3GTDUAEiIecDor1yjbC3bJvMolF0Xl8,3267
|
|
454
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200.json",sha256=8q6ol5JQBWj6yVfzFOn7Gz5MSXTaW9javL7qQmYVOwg,3245
|
|
455
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=6jRC0oOpVpq5c1xePFKNRy-Xtmb038i4LE9N2zao2W4,3730
|
|
456
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json",sha256=cFWeyNJtEbs-Bfohgzclxo1rcYGU863oV0BzJyQ4T0w,4734
|
|
457
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=SMtsqtQeqcyy8aNwl9hPxRvx_XQdT7I3SBDNJ3OIvwY,3728
|
|
458
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.json",sha256=ZyOFJB6GUgGZsAjjT43XJwG8P-QrZ5yTvmgzQP7ThQY,4734
|
|
459
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=HOxWmCI2ifHmWc0or2y8nEen86jDeLDov1-tuMzuhxo,3256
|
|
460
|
+
"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
|
|
461
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=_5weLBinQCDzyV75hHKIT95Y0ce94KWft2_5BC6EkbQ,3254
|
|
462
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=DlatRLPaSr8HJuO50gRZ2lzXoelx55EP3SDUdgIT2v4,3269
|
|
463
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200.json",sha256=TXSOoqvi-x8H13xPqrB9qz2T3opEGA-2D0v_4n5BEG4,3259
|
|
464
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ro3drDpWAdeXH7IjMvx8wYGhIuDPOl0bpbJaIB5Msns,3732
|
|
465
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json",sha256=w_R2LL8k5jNVUARcqvSgGLvNoQiQC0Mh73ciqSIAz54,4734
|
|
466
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=hjDoTXRmEFLKhhmBFEjPowQus_z23ISonxFljql3c9k,3732
|
|
467
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json",sha256=AdOTy7ASetdAXUhNM8buoU8_rLLjcUYF0m8RGFrLWRo,4733
|
|
468
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=Ru460ZgnUP4U8OsJfwF8n-AI-gfcolNR3_qzoxG6DtY,3254
|
|
469
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=K6BGrKw_oHTAtHjsZldcjp-BUM1dIecKXrrRn9OpRGs,3254
|
|
470
|
+
"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
|
|
471
|
+
"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
|
|
472
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=-5nkLIunjG1ghPoUEtt2AXEQw9oGiilP7K3UvQv9CqE,3252
|
|
473
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WKzddrIXo-KavpuXuouW3aLLAptu5Q4XJUb5K2PLgDM,3262
|
|
474
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200.json",sha256=ad1ZkkSyLJwRGb4Kf24qg5hW_DPmt0BXrKR85oAiV34,3257
|
|
475
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_L40S.json",sha256=qX5_yErBEwDRzhv2FvxrS3pEMa8zn0GHzLp5TUMX90g,3872
|
|
476
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ysRCWmxV20K2BYD9XEUtxwREFGtA3QHI191vHRA0k_Q,3733
|
|
477
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json",sha256=L8VA1sfygHoyLJ-Ybfs8DP5c0YWFmMkwxHT8yJ9PEFM,4732
|
|
478
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=FJWpDLr13XF3hHiHfJykpjbLiP7Ccu2en3U6BL-QwXw,3732
|
|
479
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X.json",sha256=FnVcfzf5gXkQRt0XgsRzIQVbDPaUDOwWJX_9qOlyvRc,4731
|
|
480
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=DxYu8regZOSFu8ugFGA_QbwWK4g8xwQUZF9a_nNY4Cs,3255
|
|
481
|
+
"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
|
|
482
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=qwKy8oaMsd3QrXgQbM_x9xcfYiHK_Ou1CEwDPL5Gbgo,3259
|
|
483
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=qUifbWbE4cOKZbIHWmmLx68VRaslQX69eZHwRIQx-7I,3269
|
|
484
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200.json",sha256=JT-ZMLhAqqzSkqivOW5ATTKRlyyaFQkqQDnaPS4DE10,3262
|
|
485
|
+
"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
|
|
486
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json",sha256=EtVorGY4khTEuimlqZu0AAlPz84PH3ZkDZmVpxLtgQw,4735
|
|
487
|
+
"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
|
|
488
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json",sha256=JPdO0azlh4yUvbpC9dEHYpRT11ELEr5LXBSb5XP4E_4,4735
|
|
489
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=BAJnXTZoewwCtzJLUPJ0oYuALv640MvDuLseGcsYaaw,3252
|
|
490
|
+
"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
|
|
491
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tme0ydWzIxdABZLk4tU8G_X2dJUYGGZNkQzNGcmcvUc,3261
|
|
492
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=g6Ivy4wvadaCAMJ4ZElbUU-CwyTMdbaa49M7IVQhVjk,3273
|
|
493
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200.json",sha256=GstQosPPHUn_I2DV3eMGtn3xXOw6kl1hb8L0EvRsbEU,3261
|
|
494
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=kF4Fx0yHUmiMSLFNXT6xqAEA4AgCaHOoy_3irv4dNss,3732
|
|
495
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json",sha256=uOlVzTdJl_4VrRK4wmxIb8JKfveFZRjO9syjw_oEeL0,4732
|
|
496
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=plnx7r9jkcYXkhvapbeeNvUg3NMGdGsIgIPSrfVy2qU,3733
|
|
497
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X.json",sha256=UC-iTgh8_dUSXRaYHOIhDH31KOiJmcfqM_Bv_UBf3ks,4733
|
|
498
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=sY2nWMPh9lsIkhPCjkHO245wpnfFbrHmzdcZDVFPVww,3265
|
|
499
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WQLKugnKzlQ0avf1N-41lRHtG6wJ56DfVPv_nip6NBc,3273
|
|
500
|
+
vllm/model_executor/layers/fused_moe/configs/README,sha256=W2yIZkP9O8GGlg97We9BJfTtWUtPbuz5ZH3esrrjBX0,572
|
|
501
|
+
vllm/model_executor/layers/mamba/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
502
|
+
vllm/model_executor/layers/mamba/mamba2_metadata.py,sha256=nkO73Gy2bXldUCJsNMptrCwyHvIEL0cdYzNf4zCQn88,5093
|
|
503
|
+
vllm/model_executor/layers/mamba/mamba_mixer.py,sha256=8Ee4TAKRrTICZKJ83XHP56S5-WjFvwN9BNgiFBXUdpc,10210
|
|
504
|
+
vllm/model_executor/layers/mamba/mamba_mixer2.py,sha256=iE78icB4I2GCY6WpLTYYIXoaEQVp_1OhC2TfdpKWtjU,24796
|
|
505
|
+
vllm/model_executor/layers/mamba/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
506
|
+
vllm/model_executor/layers/mamba/ops/causal_conv1d.py,sha256=BF7OI_1NkflshfWnoYGD1hJ-4sjfEpm30od2EpG_HK8,4539
|
|
507
|
+
vllm/model_executor/layers/mamba/ops/mamba_ssm.py,sha256=cqVVlHBLoeVIo_iB4pLveRkBfXS_g6wlI67oUXx13Hw,14234
|
|
508
|
+
vllm/model_executor/layers/mamba/ops/ssd_bmm.py,sha256=_k43ejVu7CTTVnxNNQPQ8_ByedPi9kUDirJpcD0jzhw,8640
|
|
509
|
+
vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py,sha256=HjpasgV0w53ypVrSbOhI7BbuyUhe7_wYxrW46Z0YYtg,20905
|
|
510
|
+
vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py,sha256=J_HGERmSVwkf4Djb8h8RSd6dC2jH5SKlVJewJlsH0GA,25681
|
|
511
|
+
vllm/model_executor/layers/mamba/ops/ssd_combined.py,sha256=vNqBweQEvwdIEl_woyMenhdItwEAXjG1L0B8LmY89sg,9401
|
|
512
|
+
vllm/model_executor/layers/mamba/ops/ssd_state_passing.py,sha256=4jeOPs4utX_CfzkjIgZv6XUjX-wCnYtJNembsov12-o,7438
|
|
513
|
+
vllm/model_executor/layers/quantization/__init__.py,sha256=Fz9aeiFDXM-4BK5b_-xHf6Nz8vzYiF21XRDADHF_P9c,5220
|
|
514
|
+
vllm/model_executor/layers/quantization/aqlm.py,sha256=4djL6YcziiKOPdzOy2ozHN7Bd0Sbro6H-RCFEvHPtJA,13777
|
|
515
|
+
vllm/model_executor/layers/quantization/auto_round.py,sha256=pE1IiSCk4ekyjAlyN4z5L5_ZSvuBAJZ4mNkZK-ODn_M,13421
|
|
516
|
+
vllm/model_executor/layers/quantization/awq.py,sha256=wLndIMx0ZVe-Kc4hArACCc1jvxskz8l3RVcUUrjYTfw,7356
|
|
517
|
+
vllm/model_executor/layers/quantization/awq_marlin.py,sha256=Dbm1laSvoaTMnwqMgo--iiZq2GSGnd2IHevdhHqb5BY,21383
|
|
518
|
+
vllm/model_executor/layers/quantization/awq_triton.py,sha256=SAYgtOiFmM43fsuLICbGpeJzF9Of1dc3iXIQKhczJ80,12483
|
|
519
|
+
vllm/model_executor/layers/quantization/base_config.py,sha256=f3TzbJi69WdFjKOrNSFja_HKr03J_kevFOPRzDW7cJI,5227
|
|
520
|
+
vllm/model_executor/layers/quantization/bitblas.py,sha256=hhp1TW5SQ2lUHhjM8yshaY268Z7aN09SYPwt3YNZfEk,17560
|
|
521
|
+
vllm/model_executor/layers/quantization/bitsandbytes.py,sha256=8kAoJ32nJ91B-9xm8l2JpkjpvflXjsvXjvH6kja34L0,15321
|
|
522
|
+
vllm/model_executor/layers/quantization/deepspeedfp.py,sha256=Q_QmEjovzhMyJjWoF79-myHwOQGzaC9EMXxZm4Ljf3I,7286
|
|
523
|
+
vllm/model_executor/layers/quantization/experts_int8.py,sha256=hDwPyTqtWh6Naj1clCww9DMvZ-KhHun6sE-gzJmTCKs,7689
|
|
524
|
+
vllm/model_executor/layers/quantization/fbgemm_fp8.py,sha256=rGi__Usa7F08TeGFt6i_ezuBC46UrXSNa4dQNmjeygA,6964
|
|
525
|
+
vllm/model_executor/layers/quantization/fp8.py,sha256=pof2FuOi723wtbF3bSErTM81BR2612IZJdKI4VUT-3o,42243
|
|
526
|
+
vllm/model_executor/layers/quantization/gguf.py,sha256=XPW-xo12mCGQir7hAcxv63-1QnsRT9MzgIcd9N5gAr4,21170
|
|
527
|
+
vllm/model_executor/layers/quantization/gptq.py,sha256=J0tyDms8oZj-MIcaOHMNzKpYqZWSe7i9uZQlRPTewQA,10838
|
|
528
|
+
vllm/model_executor/layers/quantization/gptq_bitblas.py,sha256=iZMUYR0ajVvCC1yz-xBMKoJMBHSZ4NxzWBOnVOWq-uE,17018
|
|
529
|
+
vllm/model_executor/layers/quantization/gptq_marlin.py,sha256=Nr86TGx3r_s1sUoA4Mq9K5uuRasW2hGCxtqoRSDDtKY,26125
|
|
530
|
+
vllm/model_executor/layers/quantization/gptq_marlin_24.py,sha256=f72YUgTT0ijIZoALWx4wn6M0L8aYpZxxKrb-cRWmZKU,11018
|
|
531
|
+
vllm/model_executor/layers/quantization/hqq_marlin.py,sha256=aXhrjhWHL8HdRffMzd2ttSLrvMZAthWXbPPXgk_Mh2Q,12912
|
|
532
|
+
vllm/model_executor/layers/quantization/ipex_quant.py,sha256=ef0PGhe-bCWzpKA33HmmUmcjQtSX5xvMVCcwaJHiGd4,9842
|
|
533
|
+
vllm/model_executor/layers/quantization/kv_cache.py,sha256=8e7uCDHW4rPO27FvzNeN5yk46jNSXgRse8lCzYQkTgM,6226
|
|
534
|
+
vllm/model_executor/layers/quantization/marlin.py,sha256=HyohF1Sv0qJhvn7bmVCYfpvOMoCuyYpBd202-_L3FXs,9727
|
|
535
|
+
vllm/model_executor/layers/quantization/modelopt.py,sha256=yiueoSErDDUr0cIqL_yiniGOUT2QZGcV3YikPSWxplY,31132
|
|
536
|
+
vllm/model_executor/layers/quantization/moe_wna16.py,sha256=jshzyWYVZ7M_uQiAa6ms12d550OQp51JDRFxQ9YGpRY,19842
|
|
537
|
+
vllm/model_executor/layers/quantization/neuron_quant.py,sha256=j7px2wDFac330ezDhUxvu6reYcQPRHTHkqHHUwCOdOk,2730
|
|
538
|
+
vllm/model_executor/layers/quantization/ptpc_fp8.py,sha256=UZ7eQtNb0YiXwuVFUSSemq1Xpp0e-Qc3Q_abIW-BOMI,5351
|
|
539
|
+
vllm/model_executor/layers/quantization/qqq.py,sha256=b_Ar5gW6hUXaugMmj4X3Ajzi9k4QchpVeZELNtSaWXU,10083
|
|
540
|
+
vllm/model_executor/layers/quantization/schema.py,sha256=x7y16hNaValmG7etgyK0RwpeBCPapT1_GznqWBQ5kGg,3749
|
|
541
|
+
vllm/model_executor/layers/quantization/torchao.py,sha256=NhnWRnkK6XrZAdXC7lkSyH7Dcc5Mte3BUDWsogx-sCc,5807
|
|
542
|
+
vllm/model_executor/layers/quantization/tpu_int8.py,sha256=NJ4oRWVCxebWqG8vztU22_ntye7te_Nk6YK1z4gh0ms,4581
|
|
543
|
+
vllm/model_executor/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
544
|
+
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=HfRvTUBaP3ht_hAY3GRicKWtxZpQOXW9cjCzCtb93CI,29225
|
|
545
|
+
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=cPvhgHFH3wX2x4HoTqRWAafoHE3TAoeivaYFhVNjSVI,55262
|
|
546
|
+
vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py,sha256=lvGKHzRLtDHkkNAAvoD-PyE8AUt26Rf9YNE29P32iOo,7793
|
|
547
|
+
vllm/model_executor/layers/quantization/compressed_tensors/utils.py,sha256=QIonPI7CuMCJwRYgajuT1ohv6t4zk9-Q165TRe6b53w,7859
|
|
548
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=sqmMJiVttpUjs-SmJrk3jO4VKsNe5dpmf_aKxWBZeU4,1199
|
|
549
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py,sha256=R1W0Q4pEe_WUjR31fTU1bfhPwaA6eiJzpoJBULBQod4,14115
|
|
550
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=phymTDNBBnHfLXhq9vmwklinzKDZKdYrfp59en2VOok,1596
|
|
551
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py,sha256=002voQj76mVNI3xF3d3IDmI5LM3-_eGXs7VJOarOWuU,6270
|
|
552
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py,sha256=h1boI5tsFuddBAjvdEPUXRbvmcv_0gdju5lBSjdHU6s,4042
|
|
553
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py,sha256=Q1MTj9lFTbOMHIKSIde08HIKTvNp1z9NUDA9IqVMLAA,7615
|
|
554
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=Z1-7Bh_1qTwnKkbbj2xO1zn19O76iU-uLWRZwdH08QA,5491
|
|
555
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=pgtg07yokeUP3Cu_CwDrn8fyqPsq1FXWfv79-ADAWR4,6506
|
|
556
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py,sha256=TpqBbRB2j5Jbvo4Gczvjy4vqlIEP-j8fljl_nQ66UtI,4930
|
|
557
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py,sha256=tmixOaeebRl-bVTUwRwZMlqr-vhBXE6BeixzhzAqCdg,8541
|
|
558
|
+
vllm/model_executor/layers/quantization/kernels/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
559
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py,sha256=n6clH1JvR3UZ6TPUKIj4xmnRRliIMaOgM4PM50BrRPs,2941
|
|
560
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py,sha256=i847I8VXbTiXeV2YD_QpkUjQFJLP20UlSDNeErWg6ng,3205
|
|
561
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py,sha256=feWdTXJ4hDpJjQEIQhabjfyZs56JVY-uza8UD81i5MA,4444
|
|
562
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py,sha256=RUeSb5-gb5wsEUy0-1WfgD3g6qCOjRVBONNXKOrC9dw,12036
|
|
563
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py,sha256=rKbWF_TyxXjbkm_a28tge9GhOowg121HECmWJIIAm-o,6213
|
|
564
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py,sha256=JTAvDrLuO_Qnw8RUASGTCZuSt3R2C7XCSKyqK1v-lzc,5043
|
|
565
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py,sha256=L4TpdojuurExORWS-aaPv2gcGFN4yNR0c9XXc0N8WGw,5760
|
|
566
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py,sha256=0cL2WbqxsGFMJMlg4AgAt5_EDOncrIB2z3vlg6FoOk8,2108
|
|
567
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py,sha256=4n01vds_ytbnGQ5jFtEJekgSbum5aZzyT39uwE2bGc4,3507
|
|
568
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py,sha256=EJiwelJCPuryD3f4wYJed52ebxWsGTdGcfTJkD-9O1w,4884
|
|
569
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py,sha256=wc9MAgmQFFcg0_wqGRIeXrdAO-_78MoaKfEvqT6odFw,6064
|
|
570
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py,sha256=CgQydI5ERFdaOzOJNR5SPTYIkAUDI-pWr8BqydEB46A,1345
|
|
571
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py,sha256=KxcEOM3PQnLXqvSRIxb6UnGNZlbuE5qrkGY_cdARgfU,4365
|
|
572
|
+
vllm/model_executor/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
573
|
+
vllm/model_executor/layers/quantization/quark/quark.py,sha256=sKM8z7rZWvizP3jsi7ocsCf8JRqy8JFxhEqEt4xr1Uw,19009
|
|
574
|
+
vllm/model_executor/layers/quantization/quark/quark_moe.py,sha256=T44d54IWP7roR8dC0V6iLaRZi37kjc06kcUilX6LhIQ,10845
|
|
575
|
+
vllm/model_executor/layers/quantization/quark/utils.py,sha256=Y1MHt_RTfPOCSb7_kQHK2CQZCaQvG1A6mMA9s70vbDQ,3658
|
|
576
|
+
vllm/model_executor/layers/quantization/quark/schemes/__init__.py,sha256=TvlHrwGTaJp9nBDtUl4n5xtuuPCR18XQVyYGa11AdMM,353
|
|
577
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py,sha256=YkvgTw1sECoubOhGXMixFd47StURg3bzGiYsur_izzg,1560
|
|
578
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=LXtP0CTKNOMD8v_7r7VxN-m9W71Ngrqtptwl2bh7Egg,4729
|
|
579
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py,sha256=v253YQ-a9q7iQXoCm6pxBWT11RFS2ekaCK0Z4j30L48,6302
|
|
580
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py,sha256=TAZaMWM1lydY9bxKj-mdzRbMcUhSVTIPXvUmt8vll0I,5462
|
|
581
|
+
vllm/model_executor/layers/quantization/utils/__init__.py,sha256=k9dh5aEvZi-6ECfjG_Jq2iijwEfjmdRA9fcHjG9uKd8,235
|
|
582
|
+
vllm/model_executor/layers/quantization/utils/allspark_utils.py,sha256=ejjOMJ4V0UhgYiSvYJf5_x6zJA5iQkAYtzLqaw2AuXE,2260
|
|
583
|
+
vllm/model_executor/layers/quantization/utils/bitblas_utils.py,sha256=BGT0qmMJi66O1PX2HS2nd7bApVpLNm5cJIYqUqsr_5g,8213
|
|
584
|
+
vllm/model_executor/layers/quantization/utils/fp8_utils.py,sha256=eHOjXcSKaRt5GkLhuqnqbkeIl1jN1J988eDGNuB1EEk,20075
|
|
585
|
+
vllm/model_executor/layers/quantization/utils/gptq_utils.py,sha256=e49tTqau8qyu95QN4vLXH-UGA-JU6dtpTY6IYPWa1TU,3874
|
|
586
|
+
vllm/model_executor/layers/quantization/utils/int8_utils.py,sha256=CGlycvdrW_w68qGC0fSOkyWaOvKfIEB4VJiJdNXknyM,15114
|
|
587
|
+
vllm/model_executor/layers/quantization/utils/layer_utils.py,sha256=KwNOkW1XYBIOjb8UJgyEKd6T_chNqE_YVskWMtrOmyo,1631
|
|
588
|
+
vllm/model_executor/layers/quantization/utils/machete_utils.py,sha256=hQYHZiCMJFCeKEbk2E3EQmUpiOgQ0b73AO_PjdxeSco,1130
|
|
589
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils.py,sha256=KCrE0m7TRSFKYvAx_qdq_k9ToNCy8oTuUvf0JOtF3RE,19007
|
|
590
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py,sha256=mlHZqTXRV0aO5TYqywOnYZUh26FOM01buE3s6oKHh6U,11235
|
|
591
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py,sha256=UBXQyCa52ixKbH_kMJZnktbARcmsVy86O8lXuByKkLE,13152
|
|
592
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test.py,sha256=GtmzVpQhQCQ8-ajEADNfzUhZW_Ph0GWs0VoSx8QJJ-o,5374
|
|
593
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py,sha256=3_204vZjqNj1Em7VxymB0CfK3TpoHpaS0xY0p29WyDY,17603
|
|
594
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test_qqq.py,sha256=zbQaHDmhnWSrZUBLPsT4ZQgIwytQUTwD23DWaSYH_RQ,4145
|
|
595
|
+
vllm/model_executor/layers/quantization/utils/mxfp4_utils.py,sha256=xC1klknQQztk1wVla1y2MNHqU-0V0p8GnfPyyD4d1jo,1645
|
|
596
|
+
vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py,sha256=FKYBY3y9pM3O-3h2iom7hkcS7YaB2y0_lMMwwGKpU5U,3788
|
|
597
|
+
vllm/model_executor/layers/quantization/utils/quant_utils.py,sha256=sn5_s-X8ijBsqrT4n-yXK8PPr_OqBkNPFIb3APHVBJU,19541
|
|
598
|
+
vllm/model_executor/layers/quantization/utils/w8a8_utils.py,sha256=TaE_0zKzrIQZT-r72ZrH5qyo-7yLuL9zHp1j3zKXEWY,16766
|
|
599
|
+
"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
|
|
600
|
+
"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
|
|
601
|
+
"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
|
|
602
|
+
"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
|
|
603
|
+
"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
|
|
604
|
+
"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
|
|
605
|
+
"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
|
|
606
|
+
"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
|
|
607
|
+
"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
|
|
608
|
+
"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
|
|
609
|
+
"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
|
|
610
|
+
"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
|
|
611
|
+
"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
|
|
612
|
+
"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
|
|
613
|
+
"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
|
|
614
|
+
"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
|
|
615
|
+
"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
|
|
616
|
+
"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
|
|
617
|
+
"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
|
|
618
|
+
"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
|
|
619
|
+
"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
|
|
620
|
+
"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
|
|
621
|
+
"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
|
|
622
|
+
"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
|
|
623
|
+
"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
|
|
624
|
+
"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
|
|
625
|
+
"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
|
|
626
|
+
"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
|
|
627
|
+
"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
|
|
628
|
+
"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
|
|
629
|
+
"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
|
|
630
|
+
"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
|
|
631
|
+
"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
|
|
632
|
+
"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
|
|
633
|
+
"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
|
|
634
|
+
"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
|
|
635
|
+
"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
|
|
636
|
+
"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
|
|
637
|
+
"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
|
|
638
|
+
"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
|
|
639
|
+
"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
|
|
640
|
+
"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
|
|
641
|
+
"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=I44PvJj758-sw_fCOVROLTpG0NQ5_5PCYyQcpZC1YSY,3259
|
|
642
|
+
"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
|
|
643
|
+
"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
|
|
644
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=-CVHqClROli9FWe_FnlnuAG2LiFivDFK_nghH6t-BWc,3261
|
|
645
|
+
"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
|
|
646
|
+
"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
|
|
647
|
+
"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
|
|
648
|
+
"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
|
|
649
|
+
"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
|
|
650
|
+
"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
|
|
651
|
+
"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
|
|
652
|
+
"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
|
|
653
|
+
"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
|
|
654
|
+
"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
|
|
655
|
+
"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
|
|
656
|
+
"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
|
|
657
|
+
"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
|
|
658
|
+
"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
|
|
659
|
+
"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
|
|
660
|
+
"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
|
|
661
|
+
"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
|
|
662
|
+
"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
|
|
663
|
+
"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
|
|
664
|
+
"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
|
|
665
|
+
"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
|
|
666
|
+
"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
|
|
667
|
+
"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
|
|
668
|
+
"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
|
|
669
|
+
"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
|
|
670
|
+
"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
|
|
671
|
+
"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
|
|
672
|
+
"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
|
|
673
|
+
"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
|
|
674
|
+
"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
|
|
675
|
+
"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
|
|
676
|
+
"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=Mtw7a9BSspj2TzC-aPxE82o1LEvwzgbUuIofwRxUNA0,3263
|
|
677
|
+
"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
|
|
678
|
+
"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
|
|
679
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=NHdx3tZnfLF7NplswMzcTRbQEQFLtChg4rd7GU9lMbM,3262
|
|
680
|
+
"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
|
|
681
|
+
"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
|
|
682
|
+
"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
|
|
683
|
+
"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
|
|
684
|
+
"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
|
|
685
|
+
"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=laYeH4w0iZOj2Yg3vDgtKoroNQnwBEX4GUGLrO9095I,3260
|
|
686
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=TWcPDZ2miQMD6OWDC1FteRs80ND9RC-oJL3PLVmJbtI,3257
|
|
687
|
+
"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
|
|
688
|
+
"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
|
|
689
|
+
"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
|
|
690
|
+
"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
|
|
691
|
+
"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
|
|
692
|
+
"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
|
|
693
|
+
"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
|
|
694
|
+
"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
|
|
695
|
+
"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
|
|
696
|
+
"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
|
|
697
|
+
"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
|
|
698
|
+
"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
|
|
699
|
+
"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
|
|
700
|
+
"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
|
|
701
|
+
"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
|
|
702
|
+
"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
|
|
703
|
+
"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
|
|
704
|
+
"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
|
|
705
|
+
"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
|
|
706
|
+
"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
|
|
707
|
+
"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
|
|
708
|
+
"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
|
|
709
|
+
"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
|
|
710
|
+
"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
|
|
711
|
+
"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
|
|
712
|
+
"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
|
|
713
|
+
"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
|
|
714
|
+
"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
|
|
715
|
+
"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
|
|
716
|
+
"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=EgFTGyW_YuDwyEDUCoGglyI1ETdj9J7AR0UfJ86jMoI,3249
|
|
717
|
+
"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
|
|
718
|
+
"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
|
|
719
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=NiorJgOotxkQcP49ID3z5al1UA4QQDrT8MvbCwAWL5Y,3248
|
|
720
|
+
"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
|
|
721
|
+
"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
|
|
722
|
+
"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
|
|
723
|
+
"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
|
|
724
|
+
"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
|
|
725
|
+
"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
|
|
726
|
+
"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
|
|
727
|
+
"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
|
|
728
|
+
"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
|
|
729
|
+
"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
|
|
730
|
+
"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
|
|
731
|
+
"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
|
|
732
|
+
"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
|
|
733
|
+
"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
|
|
734
|
+
"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
|
|
735
|
+
"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
|
|
736
|
+
"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
|
|
737
|
+
"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
|
|
738
|
+
"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
|
|
739
|
+
"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
|
|
740
|
+
"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
|
|
741
|
+
"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
|
|
742
|
+
"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
|
|
743
|
+
"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
|
|
744
|
+
"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
|
|
745
|
+
"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
|
|
746
|
+
"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
|
|
747
|
+
"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
|
|
748
|
+
"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
|
|
749
|
+
"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
|
|
750
|
+
"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
|
|
751
|
+
"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
|
|
752
|
+
"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
|
|
753
|
+
"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
|
|
754
|
+
"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=YWyByOlKSqp5lbcUa8eu6N2dHRKJqJDbCDSjdDQJngg,3249
|
|
755
|
+
"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
|
|
756
|
+
"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
|
|
757
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=j5PTW0IC4Z2yQIygcdICaOsvb639u6Mv-ZpJYkrBQ2k,3254
|
|
758
|
+
"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
|
|
759
|
+
"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
|
|
760
|
+
"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
|
|
761
|
+
"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
|
|
762
|
+
"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
|
|
763
|
+
"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
|
|
764
|
+
"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
|
|
765
|
+
"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
|
|
766
|
+
"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=Xy4mgZx5iiEvuv2ydO4dFNIT8s0jgBhNHE1vu93fGJM,3250
|
|
767
|
+
"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
|
|
768
|
+
"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
|
|
769
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=x476nFeltB_2iO9_6y-z2P_unAbh7ghLPFi5z2LOTOo,3253
|
|
770
|
+
"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
|
|
771
|
+
"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
|
|
772
|
+
"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
|
|
773
|
+
"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
|
|
774
|
+
"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
|
|
775
|
+
"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
|
|
776
|
+
"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=D0moiKqS73oril32iNj5gRJUWpT2SZ5jf-ZesUZnNv4,3254
|
|
777
|
+
"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
|
|
778
|
+
"vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=N37dUL_J2JVpgLFlnlz__Ck7Z4njROnNAO8V2oiDqr8,3253
|
|
779
|
+
"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
|
|
780
|
+
"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
|
|
781
|
+
"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
|
|
782
|
+
"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
|
|
783
|
+
"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
|
|
784
|
+
"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
|
|
785
|
+
"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
|
|
786
|
+
"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
|
|
787
|
+
"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
|
|
788
|
+
"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
|
|
789
|
+
"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
|
|
790
|
+
"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
|
|
791
|
+
"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
|
|
792
|
+
"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
|
|
793
|
+
"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
|
|
794
|
+
"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
|
|
795
|
+
"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
|
|
796
|
+
"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
|
|
797
|
+
"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
|
|
798
|
+
"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
|
|
799
|
+
"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
|
|
800
|
+
"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
|
|
801
|
+
vllm/model_executor/model_loader/__init__.py,sha256=fDu4hGQAHb614QbKbbpsW8yycr5DYetA8gUwaWeoyTo,2756
|
|
802
|
+
vllm/model_executor/model_loader/base_loader.py,sha256=I6Q-W48VimC49Chd6FJSm4kIWoLe7bGDoF5wy37SuBI,1743
|
|
803
|
+
vllm/model_executor/model_loader/bitsandbytes_loader.py,sha256=K0VLTr3VIS5DQxVdBzvnH_7j2iUawmtGtqbZlhaCbYE,25588
|
|
804
|
+
vllm/model_executor/model_loader/default_loader.py,sha256=heCRhupa4ANn7ssMBOY6unTVIF_HCA-FdWcfDVp0kcU,11409
|
|
805
|
+
vllm/model_executor/model_loader/dummy_loader.py,sha256=QHjsazcUyw6aMTI4wocgtFzDylK6rDT0paw733iOE5A,1098
|
|
806
|
+
vllm/model_executor/model_loader/gguf_loader.py,sha256=uApRTt0Mb9WSaLQp3_kTJmlEUbSIzJMUbCGV9zeqkv4,5490
|
|
807
|
+
vllm/model_executor/model_loader/neuron.py,sha256=S7924o11-QrnIixME0vuyq-yTqqeReKNVkJNIQpDBUk,19869
|
|
808
|
+
vllm/model_executor/model_loader/neuronx_distributed.py,sha256=FaWp1IGJas7zTsh8U-3842Ylmth_DU51QEPXjJrWPGs,31285
|
|
809
|
+
vllm/model_executor/model_loader/runai_streamer_loader.py,sha256=gQg_bRxKOZFOLf7eG24wTp21M_jMLJlzH9hsmZeL5Pw,4415
|
|
810
|
+
vllm/model_executor/model_loader/sharded_state_loader.py,sha256=N4uH8NgaKX7TDatrOLnx3CK5hCmTSiofeZRhY7xn72A,8064
|
|
811
|
+
vllm/model_executor/model_loader/tensorizer.py,sha256=Z6HrzLErYsQpVmQpmRyF-OhTggzGr2oFQgwNN7jUVYE,24293
|
|
812
|
+
vllm/model_executor/model_loader/tensorizer_loader.py,sha256=CtkZz8sOfK8h5CWt0HDZAl_I5AIvYx7I3m9UMdbq7zE,5189
|
|
813
|
+
vllm/model_executor/model_loader/tpu.py,sha256=WxhmPnJhYVKBPL-Z59agvQ7JOVDJIjDBjO-yQhRqoeg,4720
|
|
814
|
+
vllm/model_executor/model_loader/utils.py,sha256=VoCUn_EmYwhisbyvg3-MXozARlPe8JOv1nEc3GC6sPA,13132
|
|
815
|
+
vllm/model_executor/model_loader/weight_utils.py,sha256=VsZgTiLHzh_tIZnQUe6r8orJd8WUnNdvH6yiz6AsIsU,29950
|
|
816
|
+
vllm/model_executor/models/__init__.py,sha256=RazsVxlJOcl7TJEpnm9pkfhXQYz6CaKo5a1OKe-oCzE,932
|
|
817
|
+
vllm/model_executor/models/adapters.py,sha256=ULy-8VzK8Cco0gwYD3PsfaeHb_lYEAnoSA31KYW7uEQ,8326
|
|
818
|
+
vllm/model_executor/models/aimv2.py,sha256=fzq5a8XtmAmoEHnQT0kEqJRb5XX0gXR1E8bANLy3YOc,8661
|
|
819
|
+
vllm/model_executor/models/arctic.py,sha256=PMmXq8JXcLb8gNuwH9I7X4EwC4CvTYY5k5bCIqw2KUo,24472
|
|
820
|
+
vllm/model_executor/models/aria.py,sha256=iU4QaBrH7KAi0wS2N5u0zmb1-BkDaofEhbl6AYrTGTE,25634
|
|
821
|
+
vllm/model_executor/models/aya_vision.py,sha256=Vc3G146-2AERXd36wiljRGasfacvZscOxmFQQDWPe1U,18952
|
|
822
|
+
vllm/model_executor/models/baichuan.py,sha256=JA0soAwsSEjWM88MtkE8ymKKwY6ykS2vF5vzaEgySQw,18947
|
|
823
|
+
vllm/model_executor/models/bamba.py,sha256=jj3pV57ECvgeTXnWdooSbJn-Nv5FKsNJ_3VWMgs2UaA,21376
|
|
824
|
+
vllm/model_executor/models/bart.py,sha256=YBWWU4aL0nOKA0tVHqItdGi3z2piEDg9FYoOZ0std6U,33889
|
|
825
|
+
vllm/model_executor/models/bert.py,sha256=D7JtXlyyQ48r_DlD0EQaC7O5L5uO3E-Ul5oZ7yZXiTw,20664
|
|
826
|
+
vllm/model_executor/models/bert_with_rope.py,sha256=yeypk-MmIGAYNitKyTjBVmEpz8x3svyU4KmosbdBbco,30562
|
|
827
|
+
vllm/model_executor/models/blip.py,sha256=E0Qw2SGxfBPBttkLIqhuIZTmwkS6tAy2-9R48mc3NYM,12402
|
|
828
|
+
vllm/model_executor/models/blip2.py,sha256=-NOhxMXu62S1KMSnHZD7vdnEwRQE3OWo8ZTHU5Bi25E,25926
|
|
829
|
+
vllm/model_executor/models/bloom.py,sha256=JpU-c7z6HdjADppHa57wNyNcRG33Q7HEOo8yYnTaIaI,14523
|
|
830
|
+
vllm/model_executor/models/chameleon.py,sha256=BaJPqY5E2VdMXXWDphCVzhevj9ZWjylkDN-3kBBCHdw,45423
|
|
831
|
+
vllm/model_executor/models/chatglm.py,sha256=yqtyEDROvPTfBJHoIFjO5ytOzujyeZnJtfR_NiC6s-U,18460
|
|
832
|
+
vllm/model_executor/models/clip.py,sha256=rrt1JfGp1KSVWV9ioWgIks6wZEw_WT2HKvGRuf0T0lY,14924
|
|
833
|
+
vllm/model_executor/models/commandr.py,sha256=psHUZXWl-KccoJMZOam0pgBdL1JHVyiWNJRvUbc2110,19380
|
|
834
|
+
vllm/model_executor/models/constant_size_cache.py,sha256=O7tfU9CrkKNIHVc8FIPP4IGOn_naP5Q8r-IagakUYzE,5908
|
|
835
|
+
vllm/model_executor/models/dbrx.py,sha256=u_ITrs1XlLjd0q_p-ohcEBrKRdvq_i6HMfq6wEHyeHg,18433
|
|
836
|
+
vllm/model_executor/models/deepseek.py,sha256=s9WL-LoXexUURKjvwOB9FRYKgoNBmetF378CJu9cV6c,19869
|
|
837
|
+
vllm/model_executor/models/deepseek_mtp.py,sha256=x_dcLh5A2iF0lV95adYsWEiVS3ROfwf0KSrZky3EYjg,11032
|
|
838
|
+
vllm/model_executor/models/deepseek_v2.py,sha256=hiyRDfgg1_2Ybgo_ASMH53rYnFyUZuW36AZZJ4UQcDM,35306
|
|
839
|
+
vllm/model_executor/models/deepseek_vl2.py,sha256=qC4vxp3w3AzZRnP14V1gBh_1qGhrCjiXY-ofameXE6g,25216
|
|
840
|
+
vllm/model_executor/models/eagle.py,sha256=qZDWZbOQ8jQVP_HcQiLAtZSYeZlIZ_wKcftv_g6mFw0,11765
|
|
841
|
+
vllm/model_executor/models/exaone.py,sha256=eW-1d3aj-VNOPFQARNxzq3IYCAobAHgwlourzeUiSFc,21157
|
|
842
|
+
vllm/model_executor/models/fairseq2_llama.py,sha256=62IX9r3OrOKXD-TiNJRx_mI_TMLyqUOvmQxk8aoUZ-g,6555
|
|
843
|
+
vllm/model_executor/models/falcon.py,sha256=rjS9x_rMHNfwdXj-_xZf4FGPc7XorREripli3MRdra8,21383
|
|
844
|
+
vllm/model_executor/models/falcon_h1.py,sha256=hVNRgtOT0lcOKk9OXkt0UhGTP2r3Jg8BwvwkrLy3kd8,26901
|
|
845
|
+
vllm/model_executor/models/florence2.py,sha256=20pcLt4cLfq91a-GQhfPyNQ3U4qsckmk0lb-0hEnerY,39262
|
|
846
|
+
vllm/model_executor/models/fuyu.py,sha256=pUtD9A4L0QQKbwAi91QEYu_QSBPn5OXH-S4aNA_gw5A,14297
|
|
847
|
+
vllm/model_executor/models/gemma.py,sha256=q4BnHMW2qhijDZgIEJF3peJLX82DOqdqddiQbtNl2_s,16308
|
|
848
|
+
vllm/model_executor/models/gemma2.py,sha256=1T2xz68BiLaLvaUlFSnwvQo51OCP0LaoAYjVYxoSedM,17539
|
|
849
|
+
vllm/model_executor/models/gemma3.py,sha256=c9pkT5htdCqaC97SLtfgcd2IG-dEz8gnvD_2_cIRj8I,21750
|
|
850
|
+
vllm/model_executor/models/gemma3_mm.py,sha256=laaXS6x1avCiQ-4yr1YAVHY8VDyR4AqF4BnMRbh7ad4,25673
|
|
851
|
+
vllm/model_executor/models/glm.py,sha256=d2mDle-FA4NVjt8bVZwYQm1ddtp75b8Ji-1aVlYKb28,1059
|
|
852
|
+
vllm/model_executor/models/glm4.py,sha256=J_NOzM6avf9dNJjJkA6XnKaXblh-xEaynmLvPrcShNg,11864
|
|
853
|
+
vllm/model_executor/models/glm4v.py,sha256=P-vNsmV0cJZX1l0V0s3QW-S4lYNcg6YDWgpsDudETco,22175
|
|
854
|
+
vllm/model_executor/models/gpt2.py,sha256=gL4tgfMClO6oFKvO26KnwoDQAbJ-QIPUC20cOcjNnr8,12907
|
|
855
|
+
vllm/model_executor/models/gpt_bigcode.py,sha256=Z8KWyYGY0to0iizR05TsVSXezYAezcJzT1wHj-9MNDk,13179
|
|
856
|
+
vllm/model_executor/models/gpt_j.py,sha256=DXwkPWHvcyfYANh_q9cD4hsF6oDDrB41Qbznupbw2ew,13248
|
|
857
|
+
vllm/model_executor/models/gpt_neox.py,sha256=U4Qta239p3CHLT4haOgzh-ZijHTf1XBS5gfYHcWHi18,13387
|
|
858
|
+
vllm/model_executor/models/granite.py,sha256=0LHRQCxu_4SaKhqb4CRZ1h7saWbjj9MVpoOoLXzQ9zY,20125
|
|
859
|
+
vllm/model_executor/models/granite_speech.py,sha256=R4vq7mkynuzrFyiIr28nCtDdn5LC2hoaLcF2e9ZMKYg,31318
|
|
860
|
+
vllm/model_executor/models/granitemoe.py,sha256=xEo_FLUnplEBWQzwzOSlmXeB-7aKrjZsqkgQP-JHzmA,17976
|
|
861
|
+
vllm/model_executor/models/granitemoehybrid.py,sha256=dTH6y6dJP7cvNzA1zdprOMX1SZE7ZMzS91ZiuDY1JHM,24511
|
|
862
|
+
vllm/model_executor/models/granitemoeshared.py,sha256=aOMNA3QROPISeXBLYNLp9zxVTLcDHeI9mzgA3Wj-Mqg,13763
|
|
863
|
+
vllm/model_executor/models/gritlm.py,sha256=JeCdwTJLg_VHJX0YDDA1msgjDZGA7Ow6O1i6YTyIoek,8165
|
|
864
|
+
vllm/model_executor/models/grok1.py,sha256=htPR-OsKJVdor9c3iwsWcLwZM8wyt9TfZTB2yQeyzRQ,22507
|
|
865
|
+
vllm/model_executor/models/h2ovl.py,sha256=tEJy9W5kFfD-y40mESIZy1jygbYtOfDUUc3IIJI5Nn8,18345
|
|
866
|
+
vllm/model_executor/models/idefics2_vision_model.py,sha256=kIJ7fIH6EqRDz9zyb8aybH28CCntgRODy0Sc-VNi3io,15032
|
|
867
|
+
vllm/model_executor/models/idefics3.py,sha256=wmnVrKsyvSq1xbBAEBLFM4NrUVD3y_GI4OIBI6ofNqY,28073
|
|
868
|
+
vllm/model_executor/models/interfaces.py,sha256=bW_OcBvljObG6Qk8quTDGDvZ-O2YbjFKv6QeMcHD6Vo,16149
|
|
869
|
+
vllm/model_executor/models/interfaces_base.py,sha256=JzOV3tbmnDd7T9ioD-0QhhPfwsTpJYGthSUUov-hfDg,4432
|
|
870
|
+
vllm/model_executor/models/intern_vit.py,sha256=moNji6HTfcM01A74d4g9m5ZUumuMnvxgWnhpse7bh5k,17312
|
|
871
|
+
vllm/model_executor/models/internlm2.py,sha256=zqG49lANNdrA8QdVl6ufUA0ibCQJMDt9UBK4Y7GCycM,17258
|
|
872
|
+
vllm/model_executor/models/internlm2_ve.py,sha256=PBc0lISli_zQWI1KUPFaYGiU0MMqjjB0i48DbjayVrQ,5801
|
|
873
|
+
vllm/model_executor/models/internvl.py,sha256=RJ8GqtGbDCW4ie3AYVQiWkqsC6LsKlo9DA97rBYffRY,51523
|
|
874
|
+
vllm/model_executor/models/jais.py,sha256=g5_UOoxXLe77ynXWP9yiqa40Nvz_bhK6buqdfEubhP0,14615
|
|
875
|
+
vllm/model_executor/models/jamba.py,sha256=jf-HS6Qd2UUZu61dG450kub4Xi3pUMGA4X-EzbrVPEU,24339
|
|
876
|
+
vllm/model_executor/models/kimi_vl.py,sha256=R8fwJ5RNx_6T_lAWkICoXSRMdIKuo96oMbZ9sGjldnU,24433
|
|
877
|
+
vllm/model_executor/models/llama.py,sha256=9F2-D-X6iV4E0Zqly9e4gfi4bf8awz0IKY-9E4-xU7g,25953
|
|
878
|
+
vllm/model_executor/models/llama4.py,sha256=XpEUtu5E_AFzSL1oy48zColZ3sOUwfUbRr-kqVL0xk4,21891
|
|
879
|
+
vllm/model_executor/models/llama_eagle.py,sha256=iwQuxwCvJmkwvgTm0Vda-m5tsMDO7QB92O_rXrEIPT0,5889
|
|
880
|
+
vllm/model_executor/models/llama_eagle3.py,sha256=HDljQQQMno0w4fQrMRuCP2DvQGmjDaF1Yj6udggDtj0,9499
|
|
881
|
+
vllm/model_executor/models/llava.py,sha256=kWIs5WUX3Uc5Dz2ClP6FxiQ8qxcGKpkA-irsOBQsdUM,32306
|
|
882
|
+
vllm/model_executor/models/llava_next.py,sha256=XSfiHc9yXfWeFv4m1wACjOq81923JcLsEbQMGG-8v-g,23806
|
|
883
|
+
vllm/model_executor/models/llava_next_video.py,sha256=QC3uOeIXXrQ89wGRwBhSsp2AQg7wmePwo-bCpJdTCS0,17670
|
|
884
|
+
vllm/model_executor/models/llava_onevision.py,sha256=R3e9BSqTQfn4pkPd4bUnrtgrvXFOrCiu96BC4WOs8CY,37008
|
|
885
|
+
vllm/model_executor/models/mamba.py,sha256=w_gqekW_61yAvd4pTPkQk8ULH1XmgF7uuZWkm2Uh61A,11648
|
|
886
|
+
vllm/model_executor/models/mamba2.py,sha256=mzdfo6ZMC2KaHNYpL-Yg9lg7fus3O8Jwp-Icg2sUdLE,12683
|
|
887
|
+
vllm/model_executor/models/mamba_cache.py,sha256=jeDF4fTtFfhHEFiLqa2nrbOjg11_KS7qVqz5Jp8cMMM,2967
|
|
888
|
+
vllm/model_executor/models/medusa.py,sha256=iR59lwoGI-KtA_rh0O7ABUJiDOWocdbdrAbND6qmqVY,9003
|
|
889
|
+
vllm/model_executor/models/mimo.py,sha256=HhJVShVhvEuyxCTuqQUPUX4tmfbNB2X97CrLLKVUSuY,7916
|
|
890
|
+
vllm/model_executor/models/mimo_mtp.py,sha256=0l_36yBG6UgRiCsQrmV6P3McyeYS6W0XwOkTJFIaPtE,11445
|
|
891
|
+
vllm/model_executor/models/minicpm.py,sha256=HPi3QK4F96zXHH8bwysx83Tq7agKz8-2NcffeTd6S3c,23905
|
|
892
|
+
vllm/model_executor/models/minicpm3.py,sha256=3gR9YhnAHhgoi9hfQupHmNhhAt--aeyMDMerp7sncuw,9429
|
|
893
|
+
vllm/model_executor/models/minicpm_eagle.py,sha256=qOHJH4raDUbtTJYiOWpAUBfYo3dUow4ImkdZfx6K88w,15901
|
|
894
|
+
vllm/model_executor/models/minicpmo.py,sha256=jZMHzka9i-BRCb0viIgXPZKNWhS0MpCabW6A1Q-sxFw,28855
|
|
895
|
+
vllm/model_executor/models/minicpmv.py,sha256=O8fqCdwfbiQha-66zgbZS5DlsqC39BGrG0OjYCP-LhI,47298
|
|
896
|
+
vllm/model_executor/models/minimax_cache.py,sha256=k52vWrBlTlPPEOxeZ4Pn8scFroolWzI5DYXpBtX1fjo,1212
|
|
897
|
+
vllm/model_executor/models/minimax_text_01.py,sha256=4RB805VlehZ_adPiT-yGgt51p-AmKdJu7uV-r1RGX_E,51704
|
|
898
|
+
vllm/model_executor/models/minimax_vl_01.py,sha256=b0l_z-GQzHpW-o8zm17kLuPl7zHCutU3KwpXqXxYQZc,13973
|
|
899
|
+
vllm/model_executor/models/mistral3.py,sha256=lWWE5wqyoAU0E1H2dt7nR6ZCxceLgF0qEkg3EjFo5GU,22968
|
|
900
|
+
vllm/model_executor/models/mixtral.py,sha256=wROyHrIf3ZGywQgvY5Y-RGjo08VyWtYJgSjMKY900X8,20207
|
|
901
|
+
vllm/model_executor/models/mixtral_quant.py,sha256=drRwp7bdlBkSs6_sd51m72ON6KD9wupcsSya2J-KMlI,18527
|
|
902
|
+
vllm/model_executor/models/mllama.py,sha256=cz9LwxP4cIpNRNabdiZCatw0OqfSvrGon-xr56zlAG0,66798
|
|
903
|
+
vllm/model_executor/models/mllama4.py,sha256=N-OCNVQqBB5saJOjEUxg83McbtkXqOWuKH8mOMgHZgM,34539
|
|
904
|
+
vllm/model_executor/models/mlp_speculator.py,sha256=Y7j6_gQPcxM53DHel_hLHdT2Xm1t3V6bv2_Q2e_jgFI,7965
|
|
905
|
+
vllm/model_executor/models/modernbert.py,sha256=Zj8LJcQu5CSUhBVkjldfIm9gbWIJa9ifaapk7F4UeKQ,12741
|
|
906
|
+
vllm/model_executor/models/module_mapping.py,sha256=vNEOOezDnDR5JgMltbviAANLu8CM6tQdr3RX6tZu_i0,1844
|
|
907
|
+
vllm/model_executor/models/molmo.py,sha256=XkpJG8l4spBTBvkAsNgceZOvbwp72dNCbAmgVZjV-DY,54941
|
|
908
|
+
vllm/model_executor/models/moonvit.py,sha256=uIhdvvpCQImQCVXAKFAfM_2BbgvHycdQcGR9q1UA_7U,24120
|
|
909
|
+
vllm/model_executor/models/mpt.py,sha256=OlBtxlKQL-NfEElsrlZwd5G8luQ42-06N7p8ZLFgK8A,12754
|
|
910
|
+
vllm/model_executor/models/nemotron.py,sha256=Ir2Jq2DAypuwWLpda_dyjNeENZfiK4MwlUQsJRgn-r4,20715
|
|
911
|
+
vllm/model_executor/models/nemotron_h.py,sha256=UAfH86GIcUqiFWcHjHJ7cqeEEH-2HdJ8Bm9yLyj0ClU,21198
|
|
912
|
+
vllm/model_executor/models/nemotron_nas.py,sha256=t_uY2L4iPWCun6h6ZGRYqreEucld_1sH87u5Os6QETI,19207
|
|
913
|
+
vllm/model_executor/models/nvlm_d.py,sha256=7AeV--WpvjDOe5sotcAx-8sxjCO-lgz4xZkmduQmvaM,8066
|
|
914
|
+
vllm/model_executor/models/olmo.py,sha256=FklGAz1Q3vGrLQIfTuRUuIRtKMEnMx20tWVgBPp4W8I,14924
|
|
915
|
+
vllm/model_executor/models/olmo2.py,sha256=24LqnlygqCbumLWlCMtF1g2qPaVmZzqxAE39DFkeTag,15984
|
|
916
|
+
vllm/model_executor/models/olmoe.py,sha256=Ha9Kmux5e_EVmyPIywkw0cg74kpXQhEOFGEz8zgOtkI,19416
|
|
917
|
+
vllm/model_executor/models/opt.py,sha256=SRHn5LMjOnO5ECwJxfXjBYq_MINaRD0ynTUwzsIozFo,16572
|
|
918
|
+
vllm/model_executor/models/orion.py,sha256=DeAgZLf8sOiQcJ5dVPjtc1EJ74G4CkjxReF2_5_SpOA,13862
|
|
919
|
+
vllm/model_executor/models/ovis.py,sha256=gKZCZOo97EcugDzUIcbdQ9D2X2GSa1N-APbwb6usuaE,21865
|
|
920
|
+
vllm/model_executor/models/paligemma.py,sha256=dA01kAm5xVlrCKqxI24PoHrmtYd3_OLkQpoLBn7Ho-g,14648
|
|
921
|
+
vllm/model_executor/models/persimmon.py,sha256=zcVATPUTd1A3Jl1TrQXd5KulD1B_AhcPob_N9PvWMUs,14328
|
|
922
|
+
vllm/model_executor/models/phi.py,sha256=1dUL1DRw8swSgChiBgdMB9bgIdMwWefBN746VasstVo,14172
|
|
923
|
+
vllm/model_executor/models/phi3.py,sha256=OdDcrMZ2IYHzg_R_gu89ae3lijNSFlxUXKTw4mmcR8U,457
|
|
924
|
+
vllm/model_executor/models/phi3_small.py,sha256=sr2jvhCsi1Hv2mqSZi3kPUZuDVA23JUr5SwY3s16fyE,18282
|
|
925
|
+
vllm/model_executor/models/phi3v.py,sha256=-X-k0OC3RTV0eiGxRmFqFgwzsCrXVbVARTm_I-0P7Mw,28483
|
|
926
|
+
vllm/model_executor/models/phi4mm.py,sha256=azMxQERDZpYGGUA8YYDQIJFEGcHO406T4mNkp9uG3ow,49383
|
|
927
|
+
vllm/model_executor/models/phi4mm_audio.py,sha256=qOVU4zt58LKSFij9yz2N5_wFM-MBREsQHNzzGqTL2ig,49132
|
|
928
|
+
vllm/model_executor/models/phi4mm_utils.py,sha256=dg5ivyxJCdlyWmKxX4pZOF6I-BTgpUMqY4nmHdZFCEk,66739
|
|
929
|
+
vllm/model_executor/models/phimoe.py,sha256=dpJo_zaxYY57O8yPpF4F0MWc6KbiAYCVX4LxvS91zd4,24738
|
|
930
|
+
vllm/model_executor/models/pixtral.py,sha256=Eb0i_EDik3BLr-9vdann0_EfQHf0bvYrbg6rUl7yIW0,48235
|
|
931
|
+
vllm/model_executor/models/plamo2.py,sha256=_RujxGJdXQnep1ws4g-7cW-1dUYKhuPiUn8YPvpehS4,30125
|
|
932
|
+
vllm/model_executor/models/prithvi_geospatial_mae.py,sha256=aYNorj3NlBmgh3wK3GFdkCmPNArhdY2am0ODPqE17g8,9256
|
|
933
|
+
vllm/model_executor/models/qwen.py,sha256=aRjSXkeI2dwoOhf5yvYu0Nj_-rLezwQQR1UnKpNghJM,13916
|
|
934
|
+
vllm/model_executor/models/qwen2.py,sha256=uEC_blysusUjq0OuC45jqeQEMpD2RWTF-a83xSvBJAY,19770
|
|
935
|
+
vllm/model_executor/models/qwen2_5_omni_thinker.py,sha256=l_fhjc78TyRx8gqSYe2z4550-a4DhJpnUD1sAS_TcmU,37186
|
|
936
|
+
vllm/model_executor/models/qwen2_5_vl.py,sha256=nPSgUgBnUrh7oCW5AcHzQDv8KGmn-66jbATia3ktEnI,47525
|
|
937
|
+
vllm/model_executor/models/qwen2_audio.py,sha256=Jvl8apcyxYQ7jM-XJFboJ2NXbFVi2BNY1ZJDfHr_EZw,16581
|
|
938
|
+
vllm/model_executor/models/qwen2_moe.py,sha256=SYlWCTr5dTpVA0DyTfg7G3TVbpZfwRNY7lRL7bysFh8,23070
|
|
939
|
+
vllm/model_executor/models/qwen2_rm.py,sha256=Rbe_5YLaxELesX7hpxlY9u97tM3MfCLBEatoEIz-YiY,4620
|
|
940
|
+
vllm/model_executor/models/qwen2_vl.py,sha256=OSKWS51pP8scwZdwZKbIXh8wbRU1-CNnCMO4UFPUeS8,53664
|
|
941
|
+
vllm/model_executor/models/qwen3.py,sha256=3aWxRi2BAGRyQE9tTYeWmXsuui52IQ811-FVNOupyzo,12474
|
|
942
|
+
vllm/model_executor/models/qwen3_moe.py,sha256=k8FsAIRdm__9cDv07C9-zfDb2iCZh-XMblDIIhaZSdI,23026
|
|
943
|
+
vllm/model_executor/models/qwen_vl.py,sha256=Rk62-xRwtEVS69pf05ujaQvw_rXHYMIMlsOmJnYe52A,26838
|
|
944
|
+
vllm/model_executor/models/registry.py,sha256=VoCUkg9sz3OA96EVI4WaKjVqazuPdofB5bG0pszMLkc,25796
|
|
945
|
+
vllm/model_executor/models/roberta.py,sha256=CzDGg0QF5eTJViqGfZX3HR5sH5CMsrT1jLOqC7a464U,11511
|
|
946
|
+
vllm/model_executor/models/siglip.py,sha256=zfwSZK8jlQL8B6_C1WvF_sUlacyRNMIDXk_Gp2NPrfM,18720
|
|
947
|
+
vllm/model_executor/models/skyworkr1v.py,sha256=5H3rjeqVXy_rBD22Ee-nQLomSYC8lLax-8JvhSV-3dQ,34039
|
|
948
|
+
vllm/model_executor/models/smolvlm.py,sha256=5Lopc0syQDwQQZ6agYHWi2Ew8c5PdzOLfcLfBFqv27A,1799
|
|
949
|
+
vllm/model_executor/models/solar.py,sha256=HLDduE5re-mJnZEEq6djQTugObzWM6HBYFMs3yhJaXU,19962
|
|
950
|
+
vllm/model_executor/models/stablelm.py,sha256=HOSTK482W_yh2yCoMxH_200DsyTGIRGsd7Ymga0AA5M,15007
|
|
951
|
+
vllm/model_executor/models/starcoder2.py,sha256=fC4Vg6oFZow9GBS1QeyuumChhfv8AuBRZOLkTBhdjMs,14610
|
|
952
|
+
vllm/model_executor/models/tarsier.py,sha256=v9oZCqegdGNiuWAAyeePIcjewEX1t26yRkJIGVxd220,26291
|
|
953
|
+
vllm/model_executor/models/telechat2.py,sha256=s6Xfzd3cBY06n3kT3w8RjID5M5imOYVLWkXSDPeWrkQ,6063
|
|
954
|
+
vllm/model_executor/models/teleflm.py,sha256=8BsSo5Ox4ENo4Y1UKicd2nq41lksPZhW-ippU-498NU,3212
|
|
955
|
+
vllm/model_executor/models/transformers.py,sha256=fK5wtvHTUQR7r_Uhn_9_1PLcYcHjAv_Sq39gKZ6HBHA,20464
|
|
956
|
+
vllm/model_executor/models/ultravox.py,sha256=jxyLoOMhmCeIpFarIPKKFnYS2J6RAzGMg13K1u4mlH8,26960
|
|
957
|
+
vllm/model_executor/models/utils.py,sha256=VutntdonPxq2QEQ_DzlXS47bOzxzll6lTLoDxjam1gk,24970
|
|
958
|
+
vllm/model_executor/models/vision.py,sha256=ocDWi7KE4XXlz9iOZpYxkYg8dD9-z_jHU1hh1pdPZuc,5603
|
|
959
|
+
vllm/model_executor/models/whisper.py,sha256=uxRiZU3776PKxIHv4O03SvMJU3EMSXtBkdPc2UPtm-E,27616
|
|
960
|
+
vllm/model_executor/models/zamba2.py,sha256=TCH1kn4HeNHjFHn3mEfhQeCELij0joKrl_5Lb2wVC00,39668
|
|
961
|
+
vllm/multimodal/__init__.py,sha256=itu8-L_cTTq8GzajfSi4OHsAGe4lqyOyKjOlk6GLlPk,1059
|
|
962
|
+
vllm/multimodal/audio.py,sha256=nXiSIMdzGBZ0T6yf76fUhK03NquqbqQQDi2xAk5de04,3148
|
|
963
|
+
vllm/multimodal/base.py,sha256=7D7GyxhfTkqSOsHtUuKqXWR1znFk71Mq7ByHD45KP60,7002
|
|
964
|
+
vllm/multimodal/hasher.py,sha256=95fhWlh7Ho_ralw56Y8hALCBwLFRfofXIK8cBsH3Oqs,3454
|
|
965
|
+
vllm/multimodal/image.py,sha256=5y4QojUye1SlYB5n8oOfCKyRfPMsZ6Ocjn56bIqs2YU,2995
|
|
966
|
+
vllm/multimodal/inputs.py,sha256=VGIthhXqBqtAy4yTH5T6J_xwz-fUxujLMLA_65BWiD0,28421
|
|
967
|
+
vllm/multimodal/parse.py,sha256=58RZ1XMtOouTEryKAgmGGr7WmUYnVT4dLdeM-dF26D8,14485
|
|
968
|
+
vllm/multimodal/processing.py,sha256=qkeIL3ONvmc87dmy7DXDf4YD8YuP5AG8pBNTwSlpAwg,60996
|
|
969
|
+
vllm/multimodal/profiling.py,sha256=09DUYqSsyhaobl19gMJwEERfdbXgK6c--mBl-NCMSK0,8654
|
|
970
|
+
vllm/multimodal/registry.py,sha256=4OS18qN4_7168jA0o44lwrO77DAeq6Vh2WXv38h6ygs,11254
|
|
971
|
+
vllm/multimodal/utils.py,sha256=Y3wnhgll7_ms_aJUdp9ip-DoR8X_2isbpiEqM8gCjVQ,14061
|
|
972
|
+
vllm/multimodal/video.py,sha256=oc2702Ggy1GqTjLOFPyWjJWJChR-FVNIvoyUhbG9BDA,6148
|
|
973
|
+
vllm/platforms/__init__.py,sha256=_vGc1ySlqBeuEjIE75yobQ0jeuk2TbMP4112uogrXaE,10637
|
|
974
|
+
vllm/platforms/cpu.py,sha256=qg_fTQzs_91LRiNkib7KtBgXZhsDs31uvWAkU0QJKHw,10618
|
|
975
|
+
vllm/platforms/cuda.py,sha256=x-EjRKsEi2fMHLhRsrsE9LIIYh-uEUbF8f0M9uj5M1k,21631
|
|
976
|
+
vllm/platforms/hpu.py,sha256=FLff8i9N1klXT7UORGVGc_EP-6GgFXBfqKPqonJ6p1o,4206
|
|
977
|
+
vllm/platforms/interface.py,sha256=X-MqbRyM9vlPzGda15BN3rZJ-3XFI6VYyJnR5oTHfaM,17720
|
|
978
|
+
vllm/platforms/neuron.py,sha256=4kGXZ7nuMKkIXlGBqCa8UMFKe9308pbZDW41hzAVx8c,5575
|
|
979
|
+
vllm/platforms/rocm.py,sha256=muI-076S_ZQ0S2FRWEYLeiRlgi9BTcSIn-y0HiO8wnA,16987
|
|
980
|
+
vllm/platforms/tpu.py,sha256=YgmI5qIU3wQ9oOJ7-9dsiC0tvsswg2bFO06IxyOaLFU,8278
|
|
981
|
+
vllm/platforms/xpu.py,sha256=9IQvpu9OSqnrGdP5kmeufE5jpNnIpAc4IEIx10nLvYo,6200
|
|
982
|
+
vllm/plugins/__init__.py,sha256=XZWErO0pxklJEsdPQiqL7LWi_JQ1AbvbY2UrZSQ4R6o,3322
|
|
983
|
+
vllm/plugins/lora_resolvers/README.md,sha256=I4lYxAwarJdoR322hv-UQqsvuqjdQIxexWtBVdwyrL0,828
|
|
984
|
+
vllm/plugins/lora_resolvers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
985
|
+
vllm/plugins/lora_resolvers/filesystem_resolver.py,sha256=Ic4o6SWF7DeDhNAAE1dxzaAMb_0L03DNzM0590FC1Fk,2086
|
|
986
|
+
vllm/profiler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
987
|
+
vllm/profiler/layerwise_profile.py,sha256=ePkIStAYP58wRo3WUuy9dvOMvd4t5fRPeUN2QDALW0U,13887
|
|
988
|
+
vllm/profiler/utils.py,sha256=zh9V6T6baIqC_EXfG39TUF2-d0z20JVqxfVtKWFDl6Q,4714
|
|
989
|
+
vllm/prompt_adapter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
990
|
+
vllm/prompt_adapter/layers.py,sha256=qa3iB58VSjE9dZPBVrLwNnBbANgp9KwhBtAd7DLLttc,2795
|
|
991
|
+
vllm/prompt_adapter/models.py,sha256=s3K69Ul2W8GVfM8oJip_Mymz1T4d0FamTQO5U5nyFMQ,13791
|
|
992
|
+
vllm/prompt_adapter/request.py,sha256=ZUEDOsSr938VwW19gh2pv8H7d7TjJbsd97DvfaYB6WI,907
|
|
993
|
+
vllm/prompt_adapter/utils.py,sha256=1iulqD-AWfgrBwwa87FIz_OMb3Zy6aEqmAQQMoEeCaw,3737
|
|
994
|
+
vllm/prompt_adapter/worker_manager.py,sha256=emiWFvvZJew530MDzT3WwbbebvPO9Y1DyvuKQeeviI0,7605
|
|
995
|
+
vllm/reasoning/__init__.py,sha256=4sr5FvUGkzpACLGXKoJu075EFK5Bs4gXsDWKgRxAU8s,528
|
|
996
|
+
vllm/reasoning/abs_reasoning_parsers.py,sha256=jmxq1sBhGLfIQQrLSIhFma5mHOWyQtnpPZwdsvVGdaE,6645
|
|
997
|
+
vllm/reasoning/deepseek_r1_reasoning_parser.py,sha256=fVAV4ZsMfd_6bB3Rf6ucSGnMJLnI1NjcAMA2i2yucwA,7465
|
|
998
|
+
vllm/reasoning/granite_reasoning_parser.py,sha256=1D8ojEdvWm391P8xoovSgLsEk2pESZIeNv3vqwfo-Yo,15899
|
|
999
|
+
vllm/reasoning/qwen3_reasoning_parser.py,sha256=gzC5_aje9dv5Juw5TRXQIOOP4QRPa_BXZkcE6cmrb68,6496
|
|
1000
|
+
vllm/spec_decode/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1001
|
+
vllm/spec_decode/batch_expansion.py,sha256=XXuJzD1RxHYRVA_az4ULrt7bFuWW24dy2eE8y7xvXZE,22809
|
|
1002
|
+
vllm/spec_decode/draft_model_runner.py,sha256=CCT401JFi-5_SmVfqteN98scAGS_eapYX_NH3YdkBKI,15222
|
|
1003
|
+
vllm/spec_decode/interfaces.py,sha256=9BnwWHd0SiMOOInnnjFHyyiidD6uk2HE7avvdgtNdvY,3155
|
|
1004
|
+
vllm/spec_decode/medusa_worker.py,sha256=EtxnCq_wFhOAxx4VYZjdZIp0KK2pSiYq0tukM6TqzdA,4969
|
|
1005
|
+
vllm/spec_decode/metrics.py,sha256=K-g8vi-_RoyMlEThMYcyb36Or5iXHz0Y5-jpnh7KE6o,8152
|
|
1006
|
+
vllm/spec_decode/mlp_speculator_worker.py,sha256=cofbNTCITpuRV8k6QeaIgm5RlDYHMvDavU6Gzsk2CNU,3806
|
|
1007
|
+
vllm/spec_decode/mqa_scorer.py,sha256=QttFp8DNHqVBAI4dGprnKjM_pIorE82jJZeDKk_FSBs,7577
|
|
1008
|
+
vllm/spec_decode/multi_step_worker.py,sha256=tPwGnoIKLuUoQeJprtOvESBvQfSgasJ2R8vbOn6biBk,19673
|
|
1009
|
+
vllm/spec_decode/ngram_worker.py,sha256=lCof1qiVJgLwRs5yuTUDzGca9WuVnHWgsYO5gqs6fh8,7896
|
|
1010
|
+
vllm/spec_decode/proposer_worker_base.py,sha256=rffkFH0N1Z3roRimkMdqTiaZqZ1GLhvn6fBg8bKgNDo,2158
|
|
1011
|
+
vllm/spec_decode/smaller_tp_proposer_worker.py,sha256=8w0TnEbusk49rf3GoTIZq8mklYjYTkxXu093qhmZuz0,6952
|
|
1012
|
+
vllm/spec_decode/spec_decode_worker.py,sha256=Q-hPtClVLfyO-cIJnLo4FWTTeS8fMMjn52Pur8k40ys,63027
|
|
1013
|
+
vllm/spec_decode/target_model_runner.py,sha256=evuaAOQnTwrRsXo-yMOXM-0SICI7gYNpnUrhPKRMQAk,2142
|
|
1014
|
+
vllm/spec_decode/top1_proposer.py,sha256=Cljv7ojLAzqVMPUdKsxISdTo2aF6io47gVsKUpq5F9c,12423
|
|
1015
|
+
vllm/spec_decode/util.py,sha256=H22iXEsK3HPptmui5JldppTXPLN8efrEbaKLj9NCMDU,9957
|
|
1016
|
+
vllm/third_party/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1017
|
+
vllm/third_party/pynvml.py,sha256=p0NkH1xRdvKZlP9F6Wfy5mBzdP4tbKpHc2TsFj0V_pw,234653
|
|
1018
|
+
vllm/transformers_utils/__init__.py,sha256=yVNs7WNM1UWvqmKYPW-R4D9NXhYWEjKYQKlfcpxL5HI,910
|
|
1019
|
+
vllm/transformers_utils/config.py,sha256=fBX8ym5iJ_tvH-_qoiUrB4DvG0ys096_Fsii0zxLWac,32938
|
|
1020
|
+
vllm/transformers_utils/detokenizer.py,sha256=UkxFpYPV-TwBGy9GhnPmSnf-SBslKcw4LQaIYgbEJsI,7299
|
|
1021
|
+
vllm/transformers_utils/detokenizer_utils.py,sha256=UoNBvr9gUNhgDNxMmVIT78HjY_KZZHbad8SgwSI6ltE,7321
|
|
1022
|
+
vllm/transformers_utils/processor.py,sha256=FNOmqYVq2Y-foTJs1xsvjqFhazb9mJh9rcS4iYse-XA,7602
|
|
1023
|
+
vllm/transformers_utils/s3_utils.py,sha256=3j5x2VDqiSsW4YwJRG-3bdbSONiw74cEQpf2Qz0SzLw,4954
|
|
1024
|
+
vllm/transformers_utils/tokenizer.py,sha256=kuzCvWjPiXCEYBlU854jBfVwsE5QyEvo6Av89g9PFXo,10721
|
|
1025
|
+
vllm/transformers_utils/tokenizer_base.py,sha256=_1iqKJZTSQW9ITGpZkC-A1lhYw7ND1ZDzpY3SpDhj_c,4029
|
|
1026
|
+
vllm/transformers_utils/tokenizer_group.py,sha256=RqfnicvJU7xQjcAGF1C6czeDf4xjKZoBcWuTlpQYPTc,5259
|
|
1027
|
+
vllm/transformers_utils/utils.py,sha256=C7fFp4Eyw5dGw9neyADzwExlhK5A0g0efIDVL3PHnzg,2699
|
|
1028
|
+
vllm/transformers_utils/chat_templates/__init__.py,sha256=U1sUyX9swSjxaULlg0B6rSroU5H8upeyInuHsF74SEE,208
|
|
1029
|
+
vllm/transformers_utils/chat_templates/registry.py,sha256=ZmIsEElC787e2vLsWnuyhmnB4nmlGDjGpF_tAYWno5k,1945
|
|
1030
|
+
vllm/transformers_utils/chat_templates/template_basic.jinja,sha256=DMH0156UMA7eoJelXKUMEDzB-SigjbyCOBxIu9OyFJE,78
|
|
1031
|
+
vllm/transformers_utils/chat_templates/template_blip2.jinja,sha256=ltMbjFdK7T4HUcN_OQaX4hj2r0PGlS1EJ9zhSlnTz1c,332
|
|
1032
|
+
vllm/transformers_utils/chat_templates/template_chatml.jinja,sha256=CKxCWf_KemM_DntV70Hf03WNkDvxznolyW-03SJJw54,370
|
|
1033
|
+
vllm/transformers_utils/chat_templates/template_deepseek_vl2.jinja,sha256=WX32uOZ7h8_xqrWvmsI5R-6Ns8ZcXVn74CKB7FJOifA,785
|
|
1034
|
+
vllm/transformers_utils/chat_templates/template_fuyu.jinja,sha256=hzdsPgeUMaZnd5L23QPiz2oC6_wMBy5WgZkXMVs3Dgo,85
|
|
1035
|
+
vllm/transformers_utils/configs/__init__.py,sha256=rYfqq6wGJmSaXooZ0aIED27NPs0CjSrbIjDJ8BREDFk,2638
|
|
1036
|
+
vllm/transformers_utils/configs/arctic.py,sha256=8WAZRegtPG1_qaFIplNemJJLlCLHBYB3p3m8ZR5co88,9053
|
|
1037
|
+
vllm/transformers_utils/configs/chatglm.py,sha256=6jt7jwkyzTBLCYQsNbFwww1-FCgBxfhoV8y-PBqm0-Y,2939
|
|
1038
|
+
vllm/transformers_utils/configs/cohere2.py,sha256=GaulobYCg5yygFpKJKiwT5EeI3VGkZBFZ36Cuv10WEc,10422
|
|
1039
|
+
vllm/transformers_utils/configs/dbrx.py,sha256=7zZOGYrASjYZiiXjHRtx8NcHin3efEz3X5y830qzZUk,10984
|
|
1040
|
+
vllm/transformers_utils/configs/deepseek_vl2.py,sha256=BwZtrbgFNLRHyOu-yMpOS8uGIFamH8_DAWxw8RtzFJA,7296
|
|
1041
|
+
vllm/transformers_utils/configs/eagle.py,sha256=pfj6dlz4ElIMGZykeCp1snCCBB-rapqtBrN_JuH2M84,3217
|
|
1042
|
+
vllm/transformers_utils/configs/exaone.py,sha256=19I7krrE3PayhGglYd0H4zzH0gaFCl0mehaGJkayomM,8927
|
|
1043
|
+
vllm/transformers_utils/configs/falcon.py,sha256=vKXtykJL5NGzcDFfSnE532vBV5KLrQvOKm7v5P58y-Y,2986
|
|
1044
|
+
vllm/transformers_utils/configs/h2ovl.py,sha256=54jsgYNkfr31YxIdkRJdkWkj5Az5Qcl0RjzV-TyryLI,558
|
|
1045
|
+
vllm/transformers_utils/configs/internvl.py,sha256=-Ixey6eygi6vwZ0es-4vNS49a1rjG9fg3WaezAOw8w0,1936
|
|
1046
|
+
vllm/transformers_utils/configs/jais.py,sha256=1jEXh11bRdFpH8ptGPKOZaTOr-Ck_BCgMbXpc959eVg,10432
|
|
1047
|
+
vllm/transformers_utils/configs/kimi_vl.py,sha256=xXtkLgTdOt5ZgSxva36iLzgZqqklIoiHaoJhCNgJyVw,1486
|
|
1048
|
+
vllm/transformers_utils/configs/medusa.py,sha256=ZZcus4c6s4A1iTOPCR2bwzJpSHKsms98dycjVpmoi2E,2012
|
|
1049
|
+
vllm/transformers_utils/configs/minimax_text_01.py,sha256=XcsvDZWzH1KHP9SQiD13yUQ5ox6WJsG9PMgz46ygqC0,2384
|
|
1050
|
+
vllm/transformers_utils/configs/minimax_vl_01.py,sha256=M9PrR1OoyRuRrA2KE2YhTnMCb88hu24QVnfiJ-Uqriw,2617
|
|
1051
|
+
vllm/transformers_utils/configs/mllama.py,sha256=DK3NNVpe70EH-HC8CWjtlhXRvzt95uQnDIOZ3kIOrwI,874
|
|
1052
|
+
vllm/transformers_utils/configs/mlp_speculator.py,sha256=2it7HgAv-ZqGDLoE7q66oxXjk8R_mBdnGw31_TVXI7w,2500
|
|
1053
|
+
vllm/transformers_utils/configs/moonvit.py,sha256=Egyjh8mvpzPlX-RmbfDf8ZmeBe7K9fqimYX-QgK9NrQ,1272
|
|
1054
|
+
vllm/transformers_utils/configs/mpt.py,sha256=8G0gnNNmTousHr6yInzh68_XGmqJkL9vptWpDPe3xUw,7652
|
|
1055
|
+
vllm/transformers_utils/configs/nemotron.py,sha256=8_mTkW7hUq0gLXuyrdQjsJDwQlmn_fkTFz-8xCUi7pI,9043
|
|
1056
|
+
vllm/transformers_utils/configs/nemotron_h.py,sha256=xD74xuTxIr2zraGF0acR5YOcPmRoUN5B57L2vf3hXao,12195
|
|
1057
|
+
vllm/transformers_utils/configs/nvlm_d.py,sha256=vlI3jyLRvc6Yrwy1GPd6XcQUwoBtyGoiYJWKE9LfHOo,527
|
|
1058
|
+
vllm/transformers_utils/configs/ovis.py,sha256=tuFDhwa1tfivFenL6Os1PImwTkfcsVy2ll7nS5aNS40,7724
|
|
1059
|
+
vllm/transformers_utils/configs/skyworkr1v.py,sha256=tFblvu0RGA1yVxAlegYtX_he7vBp5gb4czxDzhXGatU,1938
|
|
1060
|
+
vllm/transformers_utils/configs/solar.py,sha256=2BDfqhbvjutvzoNvqrJ6a1ESouK7YmIAQGJBIgfLTIU,10910
|
|
1061
|
+
vllm/transformers_utils/configs/telechat2.py,sha256=i-VmqZFsMjS2O7-ikd0-9cmFQHxUgM-Hz7cfnWsLuVc,2269
|
|
1062
|
+
vllm/transformers_utils/configs/ultravox.py,sha256=K1hw-jFVbTpOZ1mw7PsHXXNus-W8jf7cqjmS3zslkUY,4528
|
|
1063
|
+
vllm/transformers_utils/processors/__init__.py,sha256=w199hgueQE5uEOCjzPLiU1JKZNzB-1XAl4Asz_LdmYA,317
|
|
1064
|
+
vllm/transformers_utils/processors/deepseek_vl2.py,sha256=jhVoBgnvziilKiZjGoePzrIcDJM0lYluQGTkcJ-8El8,14639
|
|
1065
|
+
vllm/transformers_utils/processors/ovis.py,sha256=trrJofhlstXFklZKj_IhS18ct6sSXFM7IX0ldv_XqbE,18928
|
|
1066
|
+
vllm/transformers_utils/tokenizers/__init__.py,sha256=dN6RDCTGacE-3exN7VSZHlEcHhu__4dQM6Ry0lQ43w8,372
|
|
1067
|
+
vllm/transformers_utils/tokenizers/mistral.py,sha256=YxvurhrAcpEiGPs6u-_KpgTsm2_ZgIwlMEMe-3WCZNw,19107
|
|
1068
|
+
vllm/triton_utils/__init__.py,sha256=QuRhc0qyR8n2bM64Mv4VqhR3lIcWl77dQO8XX8d9prI,433
|
|
1069
|
+
vllm/triton_utils/importing.py,sha256=hZoqcRv-TyOBXB9B1kykL4cEPERLYYjBnGAkdIBwHKQ,1430
|
|
1070
|
+
vllm/usage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1071
|
+
vllm/usage/usage_lib.py,sha256=JmS8NnHHf0XBlt8rUJi8HD8CiV-KRU_tAGZW5oMOYyY,8903
|
|
1072
|
+
vllm/v1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1073
|
+
vllm/v1/kv_cache_interface.py,sha256=9wCva7ngubsybUZh-iVbgPBTobdsmbSnJecJx0rNepk,6400
|
|
1074
|
+
vllm/v1/outputs.py,sha256=bhO2rIKofypa6yMgz0zFulX1OLN8dGqmpyFdK_eTZvE,3780
|
|
1075
|
+
vllm/v1/request.py,sha256=kYw5aWSU0RpK6z271gp5_n4Sto6c5vvAptTaZ4PgBsE,7282
|
|
1076
|
+
vllm/v1/serial_utils.py,sha256=V3_YCe5ZntdHJ1_fSgeY29KbIDzGz1gyJnolpIvZ-OY,13219
|
|
1077
|
+
vllm/v1/utils.py,sha256=61oFrABtvMLFgbP3Y5XaHzcjU8y4eFkq1zKbvX8Eixs,27563
|
|
1078
|
+
vllm/v1/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1079
|
+
vllm/v1/attention/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1080
|
+
vllm/v1/attention/backends/cpu_attn.py,sha256=17GK9hhin-jdcSIy0T5XvIscyhz0fhsH2-yEjRwzwUI,6522
|
|
1081
|
+
vllm/v1/attention/backends/flash_attn.py,sha256=LXiZJlp7GAaK4rxEHt-Gt4k7vgBQxcU7Y9hh7XU2bD0,37547
|
|
1082
|
+
vllm/v1/attention/backends/flashinfer.py,sha256=Nw1U54uAYkr-zQ3AazesVGub5EeUYnazDquruXfv2Uo,27220
|
|
1083
|
+
vllm/v1/attention/backends/flex_attention.py,sha256=77TnZn9BycWVRGO5nhLyKuhxBxiIW3n-Wr9XHToOaiU,18266
|
|
1084
|
+
vllm/v1/attention/backends/pallas.py,sha256=WM1g3Cm3D0psAkkxiJ8F0bDMm3-oVVNT8CkpcbFTLF4,9028
|
|
1085
|
+
vllm/v1/attention/backends/triton_attn.py,sha256=vGCHZ3j4-omritdvaCpJ2j3YZJ7gp4knmLwQy9IuhU4,11559
|
|
1086
|
+
vllm/v1/attention/backends/utils.py,sha256=YDXJoydgj_viMMm4inrJuDg8zI75PoM0aa5OY9Sdx-U,2202
|
|
1087
|
+
vllm/v1/attention/backends/mla/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1088
|
+
vllm/v1/attention/backends/mla/common.py,sha256=xeZydrTJpbTgldI9Bf20RLrebOqs2WBbdGmzzF5xkG4,36419
|
|
1089
|
+
vllm/v1/attention/backends/mla/cutlass_mla.py,sha256=WohRgTRutHzfit1mjAmvivs4ESA-0dDJEPrDS403UVQ,3479
|
|
1090
|
+
vllm/v1/attention/backends/mla/flashmla.py,sha256=izT4ktr5VZWuM2vPTJSdFle2njAr2eWZEjSa8f4U4vw,5395
|
|
1091
|
+
vllm/v1/attention/backends/mla/rocm_aiter_mla.py,sha256=aR6AMwHqyrZlePsoyFtO1lxQQaIh7XNAG7CDdnilSxE,7947
|
|
1092
|
+
vllm/v1/attention/backends/mla/triton_mla.py,sha256=iK-qVDbWSRCtBFNzduxI4uYgkTgaDIVWaXxdhQ0WEds,4261
|
|
1093
|
+
vllm/v1/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1094
|
+
vllm/v1/core/block_pool.py,sha256=hFU1r4q220ZrAne94YPOBt4fbGB-URNjgeM7BCO0kXU,14645
|
|
1095
|
+
vllm/v1/core/encoder_cache_manager.py,sha256=t--JCTlsjg9nBUVdb97eGAIY3SkfnV-0RU3rweCucGI,5326
|
|
1096
|
+
vllm/v1/core/kv_cache_coordinator.py,sha256=BYLGMU3YawXXH4Hn6K1fU8EELqFEwSYqr1M2z27AcGM,15229
|
|
1097
|
+
vllm/v1/core/kv_cache_manager.py,sha256=CQG1S4qI-VLWM_loProtOKsC0xrTpwvRtSXc6C531xU,16599
|
|
1098
|
+
vllm/v1/core/kv_cache_utils.py,sha256=VXXxF2elU6X9kT423c7egQkPmqhiNqJuUaEkFC6rBV8,40669
|
|
1099
|
+
vllm/v1/core/single_type_kv_cache_manager.py,sha256=AtSo04ar6dDwM9iioeRQaUfY0ag67zAZVosDTR9lgvg,16418
|
|
1100
|
+
vllm/v1/core/sched/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1101
|
+
vllm/v1/core/sched/interface.py,sha256=mKU1I1yEhcSf5PFUt7TSkVtRd8Lliqdh8lpy3w9oB58,5860
|
|
1102
|
+
vllm/v1/core/sched/output.py,sha256=HizhOfXORVqvgHacIOUP7Nuiqwf8LpEnnD4NWPcTinE,5762
|
|
1103
|
+
vllm/v1/core/sched/scheduler.py,sha256=2qQ38RBvKDGlA8sOHxGBfv-POOl6vbbzGgTbNAl-mXY,48533
|
|
1104
|
+
vllm/v1/core/sched/utils.py,sha256=DwiO7yhp1odUeQhCU0u7O83JQPEVC3I8VUO5CZXx_d4,882
|
|
1105
|
+
vllm/v1/engine/__init__.py,sha256=TqVOiaFD3Y2GKs3psDIgbBusFe0kWdT4VK2ok0Gkja4,5281
|
|
1106
|
+
vllm/v1/engine/async_llm.py,sha256=pgEdf_CZy4REc37onJvY2Qp_XRDgZo4qf__RJsGI_NQ,22187
|
|
1107
|
+
vllm/v1/engine/coordinator.py,sha256=rawACUpcbEocwE0zQo8KbWn-avB08PL4gujBVM4SK2U,10755
|
|
1108
|
+
vllm/v1/engine/core.py,sha256=4lAeeq7j8yT5i4lNDESmHs-GKcGx22datY2pgdQD1kw,39625
|
|
1109
|
+
vllm/v1/engine/core_client.py,sha256=0MWQJo2eggvcId7lXrJ_lCnHOx6LB30N4CPx-n34570,44725
|
|
1110
|
+
vllm/v1/engine/detokenizer.py,sha256=19zOB6hJZrSzt1GKKsFLkABYzExse8ATr2bFKNhnflM,9618
|
|
1111
|
+
vllm/v1/engine/exceptions.py,sha256=OurXOSPqCuoLWzIZ2vi5ahe9NnyGESnO-HZqlvSB-Xs,731
|
|
1112
|
+
vllm/v1/engine/llm_engine.py,sha256=Rlg84c2Xj5zmT7P5F1JQAHgcpM_9ZkmIGVLicw1CvPA,12560
|
|
1113
|
+
vllm/v1/engine/logprobs.py,sha256=iaVMIsZWBRZNZSGaziWQ19qZIjGS9h8KKPwZfiWuDGo,7128
|
|
1114
|
+
vllm/v1/engine/mm_input_cache.py,sha256=FxnAXtNQqtrWGLSY1Qz60LGJd0kEEnuI75zNsO31c4U,3217
|
|
1115
|
+
vllm/v1/engine/output_processor.py,sha256=1hAqG7tzX6umOY6_8_VsGeyAfKueYXiqROkhYGzTEfo,16368
|
|
1116
|
+
vllm/v1/engine/parallel_sampling.py,sha256=uViFaH5NFxMQfWBz8rOdRZ5eIb_ZHMlJu3aCuhq2TIM,4834
|
|
1117
|
+
vllm/v1/engine/processor.py,sha256=WLOPgs1jjcVTa4Op6sWfi84ZL4TAWh6sdZ3Kwgz3qek,17940
|
|
1118
|
+
vllm/v1/executor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1119
|
+
vllm/v1/executor/abstract.py,sha256=PT8RwkVRgGjwuXeVZUU-h0_Vk5ywGolNU5iu-l8vbQY,4533
|
|
1120
|
+
vllm/v1/executor/multiproc_executor.py,sha256=73O4gsOsau0M13p30LJo47QwbsXuZlN8Uz3YIuRwtmg,20780
|
|
1121
|
+
vllm/v1/executor/ray_distributed_executor.py,sha256=JM3NMLxS_fzbtnK7bq-k5v-VB4h2uSCm29hG7pgpZVY,2061
|
|
1122
|
+
vllm/v1/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1123
|
+
vllm/v1/metrics/loggers.py,sha256=xWpU8YyPOXnC5OUKuI48a1uh5WitZh0YVx6ZGpFjvdA,21267
|
|
1124
|
+
vllm/v1/metrics/prometheus.py,sha256=RMS41lcHWzKGRrS8l92sbxfMfM0NIPiy8bSJKkKSAak,2821
|
|
1125
|
+
vllm/v1/metrics/ray_wrappers.py,sha256=1MzBlfON0nxqrc-QXK3SncCyvX6owJPJPtGmxwvGzW0,4475
|
|
1126
|
+
vllm/v1/metrics/reader.py,sha256=9rx29TV3t8P49Hx4a_F1LB2WHTwFDHkVc5v3utoEOFg,8702
|
|
1127
|
+
vllm/v1/metrics/stats.py,sha256=upnyyyJKJESiC71QQdjlBnFkzkiMQA0Dn70oE3sg9xQ,9455
|
|
1128
|
+
vllm/v1/sample/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1129
|
+
vllm/v1/sample/metadata.py,sha256=T8sjcAIz2rlGznHepGGcnBg86WcxlYoshf05gG3C_GY,1163
|
|
1130
|
+
vllm/v1/sample/rejection_sampler.py,sha256=wHdMkjv8E__M75iD5N2B5QFNfFcFworhKqSNCQHUZes,23006
|
|
1131
|
+
vllm/v1/sample/sampler.py,sha256=SKLgi0VyrimJ-iDNvmDrXsG9mvIexcNnMjW2amVl7QI,10948
|
|
1132
|
+
vllm/v1/sample/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1133
|
+
vllm/v1/sample/ops/bad_words.py,sha256=JOnrJXq2RD45cA7cmePX2ktRjBg_1uJQsPqCc0gf2Vw,1191
|
|
1134
|
+
vllm/v1/sample/ops/penalties.py,sha256=wpBU2bBU9jUc_P6DOWolprtf9Jm37nOMUvett-wqRf0,2218
|
|
1135
|
+
vllm/v1/sample/ops/topk_topp_sampler.py,sha256=zF29jKbtTEZCPGJqgfWbI6zRqyxeu02YU73Uf8FvpPg,11084
|
|
1136
|
+
vllm/v1/sample/tpu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1137
|
+
vllm/v1/sample/tpu/metadata.py,sha256=IEGdj_wnsf2oSwVlYVGwmi6gtac6lnOCf-B1GdCvRHc,4695
|
|
1138
|
+
vllm/v1/sample/tpu/sampler.py,sha256=fcT-k807VTSnOOgwg9fDFb_FloHZ4ghLq-GpjdKhFzw,5098
|
|
1139
|
+
vllm/v1/spec_decode/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1140
|
+
vllm/v1/spec_decode/eagle.py,sha256=NIOwf_n4YS1GaT-CmHw_dD3FYieeVUZzFFNrkXgCQIw,19124
|
|
1141
|
+
vllm/v1/spec_decode/medusa.py,sha256=baRvI3XjeP-GXDyMwjFuTOI6nYOJSMERO1ZfsQCXxD0,2148
|
|
1142
|
+
vllm/v1/spec_decode/metadata.py,sha256=I3rD5wVyLs5ID9LnIN3E5hy0lu5Eetz5DGcxstQMeR0,2257
|
|
1143
|
+
vllm/v1/spec_decode/metrics.py,sha256=_Ql1shXH0DurEm1MRuB1SIv8j0VOZywNnBPEonKOU4I,6735
|
|
1144
|
+
vllm/v1/spec_decode/ngram_proposer.py,sha256=l5tmQWxkdg8brzW-KA39GX6s8RjUUQS3VpV54k-hndY,4293
|
|
1145
|
+
vllm/v1/spec_decode/utils.py,sha256=OTgi53oPrx4-LQssrds8uTUu1LxdAVnAg-Uw_znSHXI,1444
|
|
1146
|
+
vllm/v1/structured_output/__init__.py,sha256=eZ2QCnfTcnXSmjN5ouPm9RxSrpQh6zqhThVC4jjwl1Y,9761
|
|
1147
|
+
vllm/v1/structured_output/backend_guidance.py,sha256=X_5Ajlp2t1twy10Oit1OVU3t4pWQelu5Q-N8JXOTzpc,8784
|
|
1148
|
+
vllm/v1/structured_output/backend_types.py,sha256=AvBbM-6oA7KcX60ecRLTa3geFnc4Dbgwa5HPcyax6D0,3806
|
|
1149
|
+
vllm/v1/structured_output/backend_xgrammar.py,sha256=Nkdy9bh7vZxvuATE8T3c3GK4hyH6zCxw1V20QOuGqPE,12249
|
|
1150
|
+
vllm/v1/structured_output/request.py,sha256=qEeKTd0vL27BJ4cPvnlF8O9bVzfALoxekG-fNA3Sr8o,3220
|
|
1151
|
+
vllm/v1/structured_output/utils.py,sha256=KYQOcqpl3TGmWkYXpFFqAyZE4IwiSHa8uqjyHrmKD1g,5866
|
|
1152
|
+
vllm/v1/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1153
|
+
vllm/v1/worker/block_table.py,sha256=e51jo43IYbk1JpR5DzdXBKhL6Fd76Rs5EfmLidOGPeo,5112
|
|
1154
|
+
vllm/v1/worker/cpu_model_runner.py,sha256=kFQyQXKPbQLCgaTMN2gbzFnDVsW6dJG79D9JybyRxSQ,3275
|
|
1155
|
+
vllm/v1/worker/cpu_worker.py,sha256=0I7JIE1G34aoFCFWCVzGHrLrwV2ZnObDs7pqV_3H_3I,6204
|
|
1156
|
+
vllm/v1/worker/gpu_input_batch.py,sha256=hYDMcddniRJXNFjleSLwpBBUy4MWlyPx3WzihHkWKpM,29981
|
|
1157
|
+
vllm/v1/worker/gpu_model_runner.py,sha256=8n7UiFzmJsr0zP5SdUduKFeetXmfPuor-LCdhzol32c,107863
|
|
1158
|
+
vllm/v1/worker/gpu_worker.py,sha256=rDiJr3rTKa28GsRa25TMZGgHznQahFdztupBJ-6MOOw,16617
|
|
1159
|
+
vllm/v1/worker/lora_model_runner_mixin.py,sha256=UBdOPm4snKiiW9_vCtVGW3pq5PrGlUQ9XWMLcjuz5As,6761
|
|
1160
|
+
vllm/v1/worker/tpu_model_runner.py,sha256=cb_kXQrmiwcs0wOhQiiPbKOFbPuqXhoiuLg-aU3y4_g,78182
|
|
1161
|
+
vllm/v1/worker/tpu_worker.py,sha256=S_iQ0kZ1jdk_sobRKTpPqmn7B9Hp4tMG8mKnYkpDlEg,12787
|
|
1162
|
+
vllm/v1/worker/utils.py,sha256=snDvL4WCRN16DoEoRtGWycSQ1vefSLQ2JEY4PuiYXi8,4342
|
|
1163
|
+
vllm/v1/worker/worker_base.py,sha256=VXzA1tCiP-UfXxQ_h-WeP41KSC_8JidGW4j0-S4nKIk,2045
|
|
1164
|
+
vllm/vllm_flash_attn/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1165
|
+
vllm/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1166
|
+
vllm/worker/cache_engine.py,sha256=CsyWo93EoS2h6VKrn-LfgGMlEq_X8B5Mu4j_og6qhaY,6075
|
|
1167
|
+
vllm/worker/cpu_enc_dec_model_runner.py,sha256=0TvNYphZ6xL2AZ7VWR__jySDkE_jqJ68kNRvF2SOjGk,13089
|
|
1168
|
+
vllm/worker/cpu_model_runner.py,sha256=Y5Hp-IFdTq4OQM4RvD-tL0VcOk9EbNOX0ALvFqGqwO8,28375
|
|
1169
|
+
vllm/worker/cpu_pooling_model_runner.py,sha256=IDZqfWjSTwGQho4H5Mcq2gmfdwuniUz15bwv0BzcO14,4830
|
|
1170
|
+
vllm/worker/cpu_worker.py,sha256=QmUtzODL3lBVBLBMJbt1eaaA96W2STkQjFq-vHHgYX8,18407
|
|
1171
|
+
vllm/worker/enc_dec_model_runner.py,sha256=9n8QPo1z5hc7Ab08MEWyalOrbidIBBkNsz8umv4Yd58,24066
|
|
1172
|
+
vllm/worker/hpu_model_runner.py,sha256=B3GdV74Eni9Hd4HOxEWSdPwYw9tP5mvifMkytTPLCnk,104410
|
|
1173
|
+
vllm/worker/hpu_worker.py,sha256=0iWcTgXJqtrNFYeA_Wv_5TplTA2L82H99xPbUGdb_3Y,21648
|
|
1174
|
+
vllm/worker/model_runner.py,sha256=4Jz7uXeAlUDLGmjVK9Ho2IAOHvgRavU1mTfxdQ3QhT0,97895
|
|
1175
|
+
vllm/worker/model_runner_base.py,sha256=yzPjB5vhVYBMQGK0fMAWz4mwnv0pW9Y5F_mpxopwh_8,9439
|
|
1176
|
+
vllm/worker/multi_step_hpu_worker.py,sha256=HYUA_dkgxGDjNDt0WoIdiD6hfH4qej3YVrYGVJMgdxo,5365
|
|
1177
|
+
vllm/worker/multi_step_model_runner.py,sha256=GbZaqrmAm2mkM5_nQER5DmaFYC2QRvloF4cBmBbWczU,39409
|
|
1178
|
+
vllm/worker/multi_step_neuron_model_runner.py,sha256=8m851aQ_GEeVRXBdp5xVJSmk8jabYA3MKqpO2R-0ENY,3292
|
|
1179
|
+
vllm/worker/multi_step_neuronx_distributed_model_runner.py,sha256=GhGSxnwC8B5gAoby7BsunFszu1xJL9iHL_bX_3PJ8pk,2199
|
|
1180
|
+
vllm/worker/multi_step_tpu_worker.py,sha256=YExBBMoOldMmgqhh0H80nZm9h4Q1EwGLAjLRs5iK1DE,4519
|
|
1181
|
+
vllm/worker/multi_step_worker.py,sha256=-OyCJfuXibg_qsLQfNkdNt4giuySR96Vkz5TsKHik-U,9485
|
|
1182
|
+
vllm/worker/neuron_model_runner.py,sha256=81JUkKFU9jVEQo3GHOfDnojUOxHGNlIVh7IxVU_874Y,19651
|
|
1183
|
+
vllm/worker/neuron_worker.py,sha256=aA-rK2XcrcbHvo6MMXE3O3oFEMM-vfg_yaMVBRRAVpY,7486
|
|
1184
|
+
vllm/worker/neuronx_distributed_model_runner.py,sha256=hdEN_hzfk_opVKM7VwfHuGaJ7sn30QTJU0S8Fvz5vz8,12667
|
|
1185
|
+
vllm/worker/pooling_model_runner.py,sha256=24D8B5IYzMX-Mz9pUk4MeNyV6HdyD1smMH4xv87qK0g,9193
|
|
1186
|
+
vllm/worker/tpu_model_runner.py,sha256=Fm7XpWJqs4Eejrzy9trqht2dRvo1lFiRrty0-hNJQpo,40848
|
|
1187
|
+
vllm/worker/tpu_worker.py,sha256=CEmhDsd-7f0JX0uyBbmQDMap8YHGIaYounYywKloe0M,14861
|
|
1188
|
+
vllm/worker/utils.py,sha256=BTNX3J84abaAQBEYkYbfv474Ye36KqkZqTK61IqJ_OQ,1980
|
|
1189
|
+
vllm/worker/worker.py,sha256=h946LI_ca1r1g-abtAlM82S19T4K8j_7QPkIlItYZgU,25551
|
|
1190
|
+
vllm/worker/worker_base.py,sha256=zArLuwSeYCUERQHK8vD5ep81tNs2WH9uejXUkp05XXY,26193
|
|
1191
|
+
vllm/worker/xpu_model_runner.py,sha256=_4-ioHBnFw4hx0WecoqGdudAjr5lUoqeowPuTbYme3s,24547
|
|
1192
|
+
vllm/worker/xpu_worker.py,sha256=NQ6h-2gjTmjEHUP2gPvOSaQFk3uOkRc2KFcz08ZpEhA,7990
|
|
1193
|
+
vllm_cpu_amxbf16-0.9.1.dist-info/METADATA,sha256=8oJt4JhueIflnahsNT4snnQKliL0eIlKsKOmynkwRMM,14504
|
|
1194
|
+
vllm_cpu_amxbf16-0.9.1.dist-info/WHEEL,sha256=IoFti0xAvoDtAxuPJyI4RJkGn0ThylEbxytRcNSoLaU,113
|
|
1195
|
+
vllm_cpu_amxbf16-0.9.1.dist-info/entry_points.txt,sha256=ErfiCUEEMrGDD3jBwf8c54AolBCFv7qrc8Ix9iqzzfs,184
|
|
1196
|
+
vllm_cpu_amxbf16-0.9.1.dist-info/top_level.txt,sha256=fAgb8Pt4zQoKTUA3ZnKEIgcjh0L97_dwEjYDTL5MEEo,5
|
|
1197
|
+
vllm_cpu_amxbf16-0.9.1.dist-info/RECORD,,
|