vllm-cpu 0.9.2.post2__cp311-cp311-manylinux_2_17_aarch64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- vllm/_C.abi3.so +0 -0
- vllm/__init__.py +214 -0
- vllm/_custom_ops.py +1915 -0
- vllm/_ipex_ops.py +350 -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 +139 -0
- vllm/attention/__init__.py +20 -0
- vllm/attention/backends/__init__.py +0 -0
- vllm/attention/backends/abstract.py +325 -0
- vllm/attention/backends/blocksparse_attn.py +465 -0
- vllm/attention/backends/cpu_mla.py +307 -0
- vllm/attention/backends/dual_chunk_flash_attn.py +1506 -0
- vllm/attention/backends/flash_attn.py +1008 -0
- vllm/attention/backends/flashinfer.py +1107 -0
- vllm/attention/backends/flashmla.py +244 -0
- vllm/attention/backends/hpu_attn.py +318 -0
- vllm/attention/backends/ipex_attn.py +403 -0
- vllm/attention/backends/mla/__init__.py +0 -0
- vllm/attention/backends/mla/common.py +1391 -0
- vllm/attention/backends/pallas.py +356 -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 +1015 -0
- vllm/attention/backends/torch_sdpa.py +707 -0
- vllm/attention/backends/triton_mla.py +115 -0
- vllm/attention/backends/utils.py +610 -0
- vllm/attention/backends/xformers.py +807 -0
- vllm/attention/layer.py +481 -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 +903 -0
- vllm/attention/ops/paged_attn.py +256 -0
- vllm/attention/ops/pallas_kv_cache_update.py +120 -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 +984 -0
- vllm/attention/ops/triton_merge_attn_states.py +97 -0
- vllm/attention/ops/triton_unified_attention.py +738 -0
- vllm/attention/selector.py +214 -0
- vllm/attention/utils/fa_utils.py +72 -0
- vllm/beam_search.py +87 -0
- vllm/benchmarks/__init__.py +0 -0
- vllm/benchmarks/datasets.py +1441 -0
- vllm/benchmarks/endpoint_request_func.py +393 -0
- vllm/benchmarks/latency.py +168 -0
- vllm/benchmarks/serve.py +1063 -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 +610 -0
- vllm/compilation/base_piecewise_backend.py +72 -0
- vllm/compilation/collective_fusion.py +127 -0
- vllm/compilation/compiler_interface.py +564 -0
- vllm/compilation/counter.py +41 -0
- vllm/compilation/cuda_piecewise_backend.py +218 -0
- vllm/compilation/decorators.py +250 -0
- vllm/compilation/fix_functionalization.py +191 -0
- vllm/compilation/fusion.py +645 -0
- vllm/compilation/fusion_attn.py +166 -0
- vllm/compilation/fx_utils.py +84 -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 +165 -0
- vllm/compilation/pass_manager.py +82 -0
- vllm/compilation/sequence_parallelism.py +482 -0
- vllm/compilation/torch25_custom_graph_pass.py +42 -0
- vllm/compilation/vllm_inductor_pass.py +70 -0
- vllm/compilation/wrapper.py +135 -0
- vllm/config.py +4913 -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 +525 -0
- vllm/core/evictor.py +157 -0
- vllm/core/interfaces.py +139 -0
- vllm/core/placeholder_block_space_manager.py +103 -0
- vllm/core/scheduler.py +2126 -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 +194 -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 +349 -0
- vllm/distributed/device_communicators/quick_all_reduce.py +278 -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/eplb/__init__.py +8 -0
- vllm/distributed/eplb/eplb_state.py +432 -0
- vllm/distributed/eplb/rebalance_algo.py +234 -0
- vllm/distributed/eplb/rebalance_execute.py +307 -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 +133 -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 +109 -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 +167 -0
- vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py +201 -0
- vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py +1103 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/__init__.py +0 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py +485 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py +533 -0
- vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py +265 -0
- vllm/distributed/kv_transfer/kv_connector/v1/shared_storage_connector.py +389 -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 +290 -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 +1385 -0
- vllm/distributed/tpu_distributed_utils.py +178 -0
- vllm/distributed/utils.py +536 -0
- vllm/engine/__init__.py +0 -0
- vllm/engine/arg_utils.py +1801 -0
- vllm/engine/async_llm_engine.py +1200 -0
- vllm/engine/async_timeout.py +173 -0
- vllm/engine/llm_engine.py +2101 -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 +326 -0
- vllm/entrypoints/__init__.py +0 -0
- vllm/entrypoints/api_server.py +178 -0
- vllm/entrypoints/chat_utils.py +1278 -0
- vllm/entrypoints/cli/__init__.py +12 -0
- vllm/entrypoints/cli/benchmark/__init__.py +0 -0
- vllm/entrypoints/cli/benchmark/base.py +25 -0
- vllm/entrypoints/cli/benchmark/latency.py +21 -0
- vllm/entrypoints/cli/benchmark/main.py +58 -0
- vllm/entrypoints/cli/benchmark/serve.py +21 -0
- vllm/entrypoints/cli/benchmark/throughput.py +21 -0
- vllm/entrypoints/cli/collect_env.py +36 -0
- vllm/entrypoints/cli/main.py +71 -0
- vllm/entrypoints/cli/openai.py +201 -0
- vllm/entrypoints/cli/run_batch.py +69 -0
- vllm/entrypoints/cli/serve.py +265 -0
- vllm/entrypoints/cli/types.py +29 -0
- vllm/entrypoints/launcher.py +147 -0
- vllm/entrypoints/llm.py +1599 -0
- vllm/entrypoints/logger.py +50 -0
- vllm/entrypoints/openai/__init__.py +0 -0
- vllm/entrypoints/openai/api_server.py +1495 -0
- vllm/entrypoints/openai/cli_args.py +331 -0
- vllm/entrypoints/openai/logits_processors.py +90 -0
- vllm/entrypoints/openai/protocol.py +2096 -0
- vllm/entrypoints/openai/run_batch.py +473 -0
- vllm/entrypoints/openai/serving_chat.py +1258 -0
- vllm/entrypoints/openai/serving_classification.py +160 -0
- vllm/entrypoints/openai/serving_completion.py +618 -0
- vllm/entrypoints/openai/serving_embedding.py +201 -0
- vllm/entrypoints/openai/serving_engine.py +988 -0
- vllm/entrypoints/openai/serving_models.py +315 -0
- vllm/entrypoints/openai/serving_pooling.py +234 -0
- vllm/entrypoints/openai/serving_score.py +431 -0
- vllm/entrypoints/openai/serving_tokenization.py +157 -0
- vllm/entrypoints/openai/serving_transcription.py +132 -0
- vllm/entrypoints/openai/speech_to_text.py +395 -0
- vllm/entrypoints/openai/tool_parsers/__init__.py +25 -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/minimax_tool_parser.py +369 -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/openai/tool_parsers/xlam_tool_parser.py +466 -0
- vllm/entrypoints/score_utils.py +50 -0
- vllm/entrypoints/ssl.py +75 -0
- vllm/entrypoints/utils.py +262 -0
- vllm/env_override.py +41 -0
- vllm/envs.py +1029 -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 +185 -0
- vllm/inputs/__init__.py +41 -0
- vllm/inputs/data.py +331 -0
- vllm/inputs/parse.py +151 -0
- vllm/inputs/preprocess.py +924 -0
- vllm/inputs/registry.py +245 -0
- vllm/jsontree.py +80 -0
- vllm/logger.py +212 -0
- vllm/logging_utils/__init__.py +8 -0
- vllm/logging_utils/dump_input.py +81 -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 +256 -0
- vllm/model_executor/__init__.py +16 -0
- vllm/model_executor/custom_op.py +208 -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 +420 -0
- vllm/model_executor/layers/fused_moe/__init__.py +78 -0
- vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py +298 -0
- vllm/model_executor/layers/fused_moe/batched_triton_or_deep_gemm_moe.py +140 -0
- vllm/model_executor/layers/fused_moe/config.py +456 -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,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_B200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=128,N=96,device_name=NVIDIA_H20.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=AMD_Instinct_MI300X.json +200 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200,dtype=fp8_w8a8.json +147 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H100.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json +218 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json +130 -0
- vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json +146 -0
- vllm/model_executor/layers/fused_moe/configs/E=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/cpu_fused_moe.py +215 -0
- vllm/model_executor/layers/fused_moe/cutlass_moe.py +645 -0
- vllm/model_executor/layers/fused_moe/deep_gemm_moe.py +250 -0
- vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py +231 -0
- vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py +183 -0
- vllm/model_executor/layers/fused_moe/fused_batched_moe.py +1021 -0
- vllm/model_executor/layers/fused_moe/fused_marlin_moe.py +234 -0
- vllm/model_executor/layers/fused_moe/fused_moe.py +1734 -0
- vllm/model_executor/layers/fused_moe/layer.py +1528 -0
- vllm/model_executor/layers/fused_moe/modular_kernel.py +598 -0
- vllm/model_executor/layers/fused_moe/moe_align_block_size.py +224 -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 +233 -0
- vllm/model_executor/layers/fused_moe/prepare_finalize.py +66 -0
- vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py +429 -0
- vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py +136 -0
- vllm/model_executor/layers/fused_moe/utils.py +144 -0
- vllm/model_executor/layers/layernorm.py +287 -0
- vllm/model_executor/layers/lightning_attn.py +652 -0
- vllm/model_executor/layers/linear.py +1547 -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 +731 -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 +473 -0
- vllm/model_executor/layers/quantization/__init__.py +160 -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 +228 -0
- vllm/model_executor/layers/quantization/awq_marlin.py +523 -0
- vllm/model_executor/layers/quantization/awq_triton.py +320 -0
- vllm/model_executor/layers/quantization/base_config.py +164 -0
- vllm/model_executor/layers/quantization/bitblas.py +462 -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 +694 -0
- vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py +1613 -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 +105 -0
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py +149 -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/deepgemm.py +83 -0
- vllm/model_executor/layers/quantization/deepspeedfp.py +195 -0
- vllm/model_executor/layers/quantization/experts_int8.py +204 -0
- vllm/model_executor/layers/quantization/fbgemm_fp8.py +172 -0
- vllm/model_executor/layers/quantization/fp8.py +950 -0
- vllm/model_executor/layers/quantization/gguf.py +577 -0
- vllm/model_executor/layers/quantization/gptq.py +278 -0
- vllm/model_executor/layers/quantization/gptq_bitblas.py +446 -0
- vllm/model_executor/layers/quantization/gptq_marlin.py +679 -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 +132 -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 +263 -0
- vllm/model_executor/layers/quantization/modelopt.py +747 -0
- vllm/model_executor/layers/quantization/moe_wna16.py +457 -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 +437 -0
- vllm/model_executor/layers/quantization/quark/quark_moe.py +245 -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 +157 -0
- vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py +122 -0
- vllm/model_executor/layers/quantization/quark/utils.py +105 -0
- vllm/model_executor/layers/quantization/rtn.py +289 -0
- vllm/model_executor/layers/quantization/schema.py +86 -0
- vllm/model_executor/layers/quantization/torchao.py +212 -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 +653 -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 +50 -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 +146 -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 +2025 -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 +116 -0
- vllm/model_executor/layers/vocab_parallel_embedding.py +487 -0
- vllm/model_executor/model_loader/__init__.py +77 -0
- vllm/model_executor/model_loader/base_loader.py +43 -0
- vllm/model_executor/model_loader/bitsandbytes_loader.py +613 -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 +602 -0
- vllm/model_executor/model_loader/tensorizer_loader.py +127 -0
- vllm/model_executor/model_loader/tpu.py +113 -0
- vllm/model_executor/model_loader/utils.py +315 -0
- vllm/model_executor/model_loader/weight_utils.py +782 -0
- vllm/model_executor/models/__init__.py +30 -0
- vllm/model_executor/models/adapters.py +375 -0
- vllm/model_executor/models/aimv2.py +246 -0
- vllm/model_executor/models/arctic.py +559 -0
- vllm/model_executor/models/aria.py +670 -0
- vllm/model_executor/models/aya_vision.py +486 -0
- vllm/model_executor/models/baichuan.py +474 -0
- vllm/model_executor/models/bamba.py +558 -0
- vllm/model_executor/models/bart.py +938 -0
- vllm/model_executor/models/bert.py +513 -0
- vllm/model_executor/models/bert_with_rope.py +617 -0
- vllm/model_executor/models/blip.py +339 -0
- vllm/model_executor/models/blip2.py +728 -0
- vllm/model_executor/models/bloom.py +373 -0
- vllm/model_executor/models/chameleon.py +1146 -0
- vllm/model_executor/models/chatglm.py +478 -0
- vllm/model_executor/models/clip.py +407 -0
- vllm/model_executor/models/commandr.py +471 -0
- vllm/model_executor/models/config.py +200 -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 +281 -0
- vllm/model_executor/models/deepseek_v2.py +935 -0
- vllm/model_executor/models/deepseek_vl2.py +660 -0
- vllm/model_executor/models/dots1.py +536 -0
- vllm/model_executor/models/eagle.py +261 -0
- vllm/model_executor/models/ernie45.py +43 -0
- vllm/model_executor/models/ernie45_moe.py +583 -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 +708 -0
- vllm/model_executor/models/florence2.py +1113 -0
- vllm/model_executor/models/fuyu.py +406 -0
- vllm/model_executor/models/gemma.py +427 -0
- vllm/model_executor/models/gemma2.py +427 -0
- vllm/model_executor/models/gemma3.py +535 -0
- vllm/model_executor/models/gemma3_mm.py +729 -0
- vllm/model_executor/models/gemma3n.py +811 -0
- vllm/model_executor/models/glm.py +23 -0
- vllm/model_executor/models/glm4.py +305 -0
- vllm/model_executor/models/glm4_1v.py +1590 -0
- vllm/model_executor/models/glm4v.py +657 -0
- vllm/model_executor/models/gpt2.py +382 -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 +790 -0
- vllm/model_executor/models/granitemoe.py +437 -0
- vllm/model_executor/models/granitemoehybrid.py +653 -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 +549 -0
- vllm/model_executor/models/hunyuan_v1_moe.py +897 -0
- vllm/model_executor/models/idefics2_vision_model.py +389 -0
- vllm/model_executor/models/idefics3.py +786 -0
- vllm/model_executor/models/interfaces.py +681 -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 +1432 -0
- vllm/model_executor/models/jais.py +373 -0
- vllm/model_executor/models/jamba.py +592 -0
- vllm/model_executor/models/keye.py +1736 -0
- vllm/model_executor/models/kimi_vl.py +585 -0
- vllm/model_executor/models/llama.py +644 -0
- vllm/model_executor/models/llama4.py +531 -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 +887 -0
- vllm/model_executor/models/llava_next.py +604 -0
- vllm/model_executor/models/llava_next_video.py +492 -0
- vllm/model_executor/models/llava_onevision.py +985 -0
- vllm/model_executor/models/mamba.py +273 -0
- vllm/model_executor/models/mamba2.py +320 -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 +772 -0
- vllm/model_executor/models/minicpmv.py +1307 -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 +374 -0
- vllm/model_executor/models/mistral3.py +624 -0
- vllm/model_executor/models/mixtral.py +488 -0
- vllm/model_executor/models/mixtral_quant.py +453 -0
- vllm/model_executor/models/mllama.py +1682 -0
- vllm/model_executor/models/mllama4.py +947 -0
- vllm/model_executor/models/mlp_speculator.py +206 -0
- vllm/model_executor/models/modernbert.py +339 -0
- vllm/model_executor/models/module_mapping.py +72 -0
- vllm/model_executor/models/molmo.py +1576 -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 +588 -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 +577 -0
- vllm/model_executor/models/paligemma.py +419 -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 +733 -0
- vllm/model_executor/models/phi4mm.py +1258 -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 +674 -0
- vllm/model_executor/models/pixtral.py +1329 -0
- vllm/model_executor/models/plamo2.py +738 -0
- vllm/model_executor/models/prithvi_geospatial_mae.py +240 -0
- vllm/model_executor/models/qwen.py +362 -0
- vllm/model_executor/models/qwen2.py +501 -0
- vllm/model_executor/models/qwen2_5_omni_thinker.py +923 -0
- vllm/model_executor/models/qwen2_5_vl.py +1175 -0
- vllm/model_executor/models/qwen2_audio.py +420 -0
- vllm/model_executor/models/qwen2_moe.py +540 -0
- vllm/model_executor/models/qwen2_rm.py +122 -0
- vllm/model_executor/models/qwen2_vl.py +1513 -0
- vllm/model_executor/models/qwen3.py +325 -0
- vllm/model_executor/models/qwen3_moe.py +541 -0
- vllm/model_executor/models/qwen_vl.py +796 -0
- vllm/model_executor/models/registry.py +634 -0
- vllm/model_executor/models/roberta.py +271 -0
- vllm/model_executor/models/siglip.py +524 -0
- vllm/model_executor/models/skyworkr1v.py +961 -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 +652 -0
- vllm/model_executor/models/telechat2.py +140 -0
- vllm/model_executor/models/teleflm.py +79 -0
- vllm/model_executor/models/transformers.py +509 -0
- vllm/model_executor/models/ultravox.py +670 -0
- vllm/model_executor/models/utils.py +744 -0
- vllm/model_executor/models/vision.py +147 -0
- vllm/model_executor/models/whisper.py +886 -0
- vllm/model_executor/models/zamba2.py +1036 -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 +80 -0
- vllm/multimodal/__init__.py +33 -0
- vllm/multimodal/audio.py +116 -0
- vllm/multimodal/base.py +219 -0
- vllm/multimodal/hasher.py +91 -0
- vllm/multimodal/image.py +103 -0
- vllm/multimodal/inputs.py +878 -0
- vllm/multimodal/parse.py +499 -0
- vllm/multimodal/processing.py +1948 -0
- vllm/multimodal/profiling.py +283 -0
- vllm/multimodal/registry.py +331 -0
- vllm/multimodal/utils.py +492 -0
- vllm/multimodal/video.py +227 -0
- vllm/outputs.py +516 -0
- vllm/platforms/__init__.py +291 -0
- vllm/platforms/cpu.py +281 -0
- vllm/platforms/cuda.py +568 -0
- vllm/platforms/hpu.py +106 -0
- vllm/platforms/interface.py +551 -0
- vllm/platforms/neuron.py +150 -0
- vllm/platforms/rocm.py +453 -0
- vllm/platforms/tpu.py +206 -0
- vllm/platforms/xpu.py +192 -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 +64 -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 +922 -0
- vllm/transformers_utils/configs/__init__.py +57 -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/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 +259 -0
- vllm/transformers_utils/configs/nvlm_d.py +31 -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 +94 -0
- vllm/usage/__init__.py +0 -0
- vllm/usage/usage_lib.py +259 -0
- vllm/utils/__init__.py +3008 -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 +184 -0
- vllm/v1/attention/backends/flash_attn.py +757 -0
- vllm/v1/attention/backends/flashinfer.py +680 -0
- vllm/v1/attention/backends/flex_attention.py +491 -0
- vllm/v1/attention/backends/mamba_attn.py +192 -0
- vllm/v1/attention/backends/mla/__init__.py +0 -0
- vllm/v1/attention/backends/mla/common.py +978 -0
- vllm/v1/attention/backends/mla/cutlass_mla.py +98 -0
- vllm/v1/attention/backends/mla/flashmla.py +180 -0
- vllm/v1/attention/backends/mla/rocm_aiter_mla.py +241 -0
- vllm/v1/attention/backends/mla/triton_mla.py +177 -0
- vllm/v1/attention/backends/pallas.py +320 -0
- vllm/v1/attention/backends/rocm_aiter_fa.py +609 -0
- vllm/v1/attention/backends/triton_attn.py +449 -0
- vllm/v1/attention/backends/utils.py +310 -0
- vllm/v1/core/__init__.py +0 -0
- vllm/v1/core/block_pool.py +349 -0
- vllm/v1/core/encoder_cache_manager.py +254 -0
- vllm/v1/core/kv_cache_coordinator.py +369 -0
- vllm/v1/core/kv_cache_manager.py +398 -0
- vllm/v1/core/kv_cache_utils.py +999 -0
- vllm/v1/core/sched/__init__.py +0 -0
- vllm/v1/core/sched/interface.py +150 -0
- vllm/v1/core/sched/output.py +157 -0
- vllm/v1/core/sched/request_queue.py +224 -0
- vllm/v1/core/sched/scheduler.py +1115 -0
- vllm/v1/core/sched/utils.py +36 -0
- vllm/v1/core/single_type_kv_cache_manager.py +444 -0
- vllm/v1/engine/__init__.py +179 -0
- vllm/v1/engine/async_llm.py +626 -0
- vllm/v1/engine/coordinator.py +278 -0
- vllm/v1/engine/core.py +1046 -0
- vllm/v1/engine/core_client.py +1049 -0
- vllm/v1/engine/detokenizer.py +292 -0
- vllm/v1/engine/exceptions.py +17 -0
- vllm/v1/engine/llm_engine.py +322 -0
- vllm/v1/engine/logprobs.py +200 -0
- vllm/v1/engine/mm_input_cache.py +91 -0
- vllm/v1/engine/output_processor.py +477 -0
- vllm/v1/engine/parallel_sampling.py +133 -0
- vllm/v1/engine/processor.py +422 -0
- vllm/v1/engine/utils.py +546 -0
- vllm/v1/executor/__init__.py +0 -0
- vllm/v1/executor/abstract.py +113 -0
- vllm/v1/executor/multiproc_executor.py +532 -0
- vllm/v1/executor/ray_distributed_executor.py +62 -0
- vllm/v1/kv_cache_interface.py +223 -0
- vllm/v1/metrics/__init__.py +0 -0
- vllm/v1/metrics/loggers.py +557 -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 +240 -0
- vllm/v1/outputs.py +124 -0
- vllm/v1/pool/__init__.py +0 -0
- vllm/v1/pool/metadata.py +17 -0
- vllm/v1/request.py +229 -0
- vllm/v1/sample/__init__.py +0 -0
- vllm/v1/sample/logits_processor.py +517 -0
- vllm/v1/sample/metadata.py +43 -0
- vllm/v1/sample/ops/__init__.py +0 -0
- vllm/v1/sample/ops/bad_words.py +39 -0
- vllm/v1/sample/ops/penalties.py +43 -0
- vllm/v1/sample/ops/topk_topp_sampler.py +296 -0
- vllm/v1/sample/rejection_sampler.py +631 -0
- vllm/v1/sample/sampler.py +226 -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 +441 -0
- vllm/v1/spec_decode/medusa.py +64 -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 +41 -0
- vllm/v1/structured_output/__init__.py +227 -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 +377 -0
- vllm/v1/worker/__init__.py +0 -0
- vllm/v1/worker/block_table.py +142 -0
- vllm/v1/worker/cpu_model_runner.py +91 -0
- vllm/v1/worker/cpu_worker.py +153 -0
- vllm/v1/worker/gpu_input_batch.py +757 -0
- vllm/v1/worker/gpu_model_runner.py +2739 -0
- vllm/v1/worker/gpu_worker.py +408 -0
- vllm/v1/worker/lora_model_runner_mixin.py +177 -0
- vllm/v1/worker/tpu_input_batch.py +585 -0
- vllm/v1/worker/tpu_model_runner.py +1849 -0
- vllm/v1/worker/tpu_worker.py +315 -0
- vllm/v1/worker/utils.py +112 -0
- vllm/v1/worker/worker_base.py +65 -0
- vllm/v1/worker/xpu_model_runner.py +33 -0
- vllm/v1/worker/xpu_worker.py +165 -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 +452 -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-0.9.2.post2.dist-info/METADATA +339 -0
- vllm_cpu-0.9.2.post2.dist-info/RECORD +1236 -0
- vllm_cpu-0.9.2.post2.dist-info/WHEEL +5 -0
- vllm_cpu-0.9.2.post2.dist-info/entry_points.txt +5 -0
- vllm_cpu-0.9.2.post2.dist-info/top_level.txt +1 -0
|
@@ -0,0 +1,1236 @@
|
|
|
1
|
+
vllm/_C.abi3.so,sha256=jEY9jPPrPE9OK-lj0a2d73azQWfHDDff4Ip9GteV9lc,20013088
|
|
2
|
+
vllm/__init__.py,sha256=a6VATPoj0VV1lHoEJ3AcEfquewWSzZ9IAVosJESa33w,8402
|
|
3
|
+
vllm/_custom_ops.py,sha256=ax7h46UGOkKWGlWAAhS9noyYWIP7rTeiU-1iKZ1Mieo,79190
|
|
4
|
+
vllm/_ipex_ops.py,sha256=q55lSPojhPY4BXGvjbT853PEPkMnTsqQraaZjSU5YGQ,12349
|
|
5
|
+
vllm/_version.py,sha256=vhqUoR5grvBOD2rM8zguSb28PK2pESJhYcCJ8PFhlvE,719
|
|
6
|
+
vllm/beam_search.py,sha256=X6PLlBDWaeZNKK4ttym328Rvjnup5wQnIDmSafMNSQI,2639
|
|
7
|
+
vllm/collect_env.py,sha256=Z2dauhcwD50tOczPNrk5Ynqqvckc6N3tJk7scouvms4,28292
|
|
8
|
+
vllm/config.py,sha256=pW7kxyS9ab5dJI-eSUXPoMbZcjavnzdmwnk9LTyo4Dc,214786
|
|
9
|
+
vllm/connections.py,sha256=YL5sQpi0vg05ZwNhpnn-7h9oCGjQeKWjTRYPCB_pKGQ,5088
|
|
10
|
+
vllm/env_override.py,sha256=egsakCgvQCyL9q5CAnG42z8v_eVbNKbuF7OuD7RGipw,1712
|
|
11
|
+
vllm/envs.py,sha256=1zi2HF4vR2sYll3fkQFj4m9EssuMLbw49q4gWTqnjrs,42064
|
|
12
|
+
vllm/forward_context.py,sha256=sSUOg-bgYNqsgnEOpmroqg5W5_fpF3bc1yXXri3JKjo,7288
|
|
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=hUwrPzeCRC-MfNOS1stGeSMElmiA1tatktw_y-5ATTg,20214
|
|
17
|
+
vllm/pooling_params.py,sha256=1Obdem0hArVwJihjHtSmeWjPvHbjAZqytVZ0pCRzlMo,2538
|
|
18
|
+
vllm/py.typed,sha256=F5LUrt0voM87SNuuOky2X9veCVDqJUgRg_VohYqDigY,65
|
|
19
|
+
vllm/sampling_params.py,sha256=1yfpSyTv_1Zv6UZluNilOwFbL8R0zWo4fWfS62JROnw,27022
|
|
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/version.py,sha256=j5_jpV6lcpUIkq56JF2uxJS02TJjG_7nGrzjvf7ptDI,1375
|
|
26
|
+
vllm/adapter_commons/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
27
|
+
vllm/adapter_commons/layers.py,sha256=ahfExqPZiZfRoi8gmzp31Hj3MKGvcalVGGR6w9lhdNA,450
|
|
28
|
+
vllm/adapter_commons/models.py,sha256=5XvXSRMnC8TufQZwf7O01SH83chilebej3Y4LnQKrhU,2870
|
|
29
|
+
vllm/adapter_commons/request.py,sha256=PGKCbvlRywX4PTQgT9hPBGYwkc9scpiic-Hi3K6Uokg,686
|
|
30
|
+
vllm/adapter_commons/utils.py,sha256=eAbRtVVso5fvSLp28k9VjArFUjrbl8BT0NkJPmJIgF4,3329
|
|
31
|
+
vllm/adapter_commons/worker_manager.py,sha256=PKuagBEoFxWzPz9AbUogHGaNJst7mWlAOarcZkUBa7I,992
|
|
32
|
+
vllm/assets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
33
|
+
vllm/assets/audio.py,sha256=03OUK2QRgJDgEucc2HDl3vdrwgiRAuBxzckas015Ces,1254
|
|
34
|
+
vllm/assets/base.py,sha256=Yv1bK5DmfZbWr_1Uqhb-mawh5M6yC1tlFT6gRkHtcgs,1265
|
|
35
|
+
vllm/assets/image.py,sha256=vW3KXy3bM-0UfQ4ZSFZPwOQfIQCIRd-4D8Xp3oY1Ics,1024
|
|
36
|
+
vllm/assets/video.py,sha256=HKBjoU2zUCeH_Yao2bTOIU_ykcHwtT_w0thXop8LlZY,4158
|
|
37
|
+
vllm/attention/__init__.py,sha256=yfqspQ_l0_9DtVE42eeurvzLLQCyx_TCBV6Uo4_nZK8,679
|
|
38
|
+
vllm/attention/layer.py,sha256=Kn6Saayd6yx9XItMhQBjjWjwr8ZCjx8Bo4-cd0rTvqQ,19929
|
|
39
|
+
vllm/attention/selector.py,sha256=o-o-S7wBQeXU2xeYJkrVQYVEBYSa156DK3KGj-RCK2U,6841
|
|
40
|
+
vllm/attention/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
41
|
+
vllm/attention/backends/abstract.py,sha256=jzVrcqvxZ28_3nkKzInrzdGYNRKpGDAionsvueqj4dg,10272
|
|
42
|
+
vllm/attention/backends/blocksparse_attn.py,sha256=r__CMA-9xaiABXE4U2NJTW-3F4kVZeFAxngjsWyOv_k,18364
|
|
43
|
+
vllm/attention/backends/cpu_mla.py,sha256=I5vbO4xEMp0kb7IZySOaA1z7qy6bIBysP-4hPKFTiGw,11342
|
|
44
|
+
vllm/attention/backends/dual_chunk_flash_attn.py,sha256=MZ0YYB-m66ZQXsj85oBuIPbfKIk7sS2M92pHDaiMc-M,66542
|
|
45
|
+
vllm/attention/backends/flash_attn.py,sha256=KGDpFsmfwxnO6rOvjMEafWG66jZ5zgkHJOWAh9Ma4LI,44921
|
|
46
|
+
vllm/attention/backends/flashinfer.py,sha256=-1ZTPg3j7kW-_L5ASc_4LgMuzLQCriGXbuT8oQWj9GE,48067
|
|
47
|
+
vllm/attention/backends/flashmla.py,sha256=l0Rf9Jj08GqugdjE38XvDeiVVsG4E7g7fy1WlaQiJp4,9175
|
|
48
|
+
vllm/attention/backends/hpu_attn.py,sha256=ARi0f_Zl9A0h4TtQSoA2oD5n0huOcoBEFbxyJIf6RJc,12716
|
|
49
|
+
vllm/attention/backends/ipex_attn.py,sha256=Ija3AvJ_l54hBs2NumPusEGMGJccPkzwMap3rExAnKw,15262
|
|
50
|
+
vllm/attention/backends/pallas.py,sha256=J0c1i8dkSkQm3k90IFGikmBj9WdbpcWGtwTgKqSqbmc,14079
|
|
51
|
+
vllm/attention/backends/placeholder_attn.py,sha256=lY1GvhayOg_v04gsJbLHCyF9-Eb3gY9bNGUY8rG3ZZM,16165
|
|
52
|
+
vllm/attention/backends/rocm_aiter_mla.py,sha256=c19DnPe_k5tCOnQ8gTK5H2DU1G1maYjjffbj1BPa7A8,18027
|
|
53
|
+
vllm/attention/backends/rocm_flash_attn.py,sha256=zaIV-5J77U0U3wp9mF5QecSbLTftgTr8mkyI34ucKs8,44531
|
|
54
|
+
vllm/attention/backends/torch_sdpa.py,sha256=4oAOlcNDEpBo5-tkzfi8IwpODnRjDYm65URbRYu2_J4,27990
|
|
55
|
+
vllm/attention/backends/triton_mla.py,sha256=fwawwKUDQPKQ6ytss1usWLn78F3TBe-V7--pUvADrXk,4099
|
|
56
|
+
vllm/attention/backends/utils.py,sha256=gJ7Poi8vjCBLlToVuV_yfR3jIBgT9rnYA-AGIYVrrDk,25997
|
|
57
|
+
vllm/attention/backends/xformers.py,sha256=bkDSdOfVx4-Ixj1qyNElSt_If6nzJM9vi6qf6sOWsxU,34068
|
|
58
|
+
vllm/attention/backends/mla/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
59
|
+
vllm/attention/backends/mla/common.py,sha256=Kn9b-6EEFdJORr3174iHY-HvVaOKbt98Y_7OCrQjPxo,58097
|
|
60
|
+
vllm/attention/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
61
|
+
vllm/attention/ops/chunked_prefill_paged_decode.py,sha256=T63JOKLYGZErqGFnDGaAbrxKN6czkIKeSG34m-r4Jak,12710
|
|
62
|
+
vllm/attention/ops/flashmla.py,sha256=khmeRslq_BU7yrGhRUzHShRLeALP8OXVNzfdCVhEzkM,3953
|
|
63
|
+
vllm/attention/ops/hpu_paged_attn.py,sha256=h_kMJN7z3JV0ckHOcRRYmCHiA3UIIDxf630B_c5-S6k,2986
|
|
64
|
+
vllm/attention/ops/ipex_attn.py,sha256=WHYA0sFj2ZVbIHsfiC1-tuTIshjF72HoKYOGaNikgDI,5703
|
|
65
|
+
vllm/attention/ops/merge_attn_states.py,sha256=1ed_lE3BuH_ahf1PW4d0I6izUasZuKbQdKSeVLu6ESw,1706
|
|
66
|
+
vllm/attention/ops/nki_flash_attn.py,sha256=-fWa50C7dnpRB7ZZOSFXubFWEfGCuY-k5_RvXrdd0Xg,32622
|
|
67
|
+
vllm/attention/ops/paged_attn.py,sha256=79sb3nWpOaZF-5YxqhqUSmOnhc209_Kf0l1fkfsaY9w,8388
|
|
68
|
+
vllm/attention/ops/pallas_kv_cache_update.py,sha256=0yuZoGD3Byiz3ZND93_CYjteNf_Iw-qWiuYnHpgbKrM,3900
|
|
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=qt0ss9DjryWVXSdAIdxoDK-KiqKso3yd_CzSnhHT5aY,32379
|
|
74
|
+
vllm/attention/ops/triton_merge_attn_states.py,sha256=gKRLVpClXSa4wBO3HkFk4OBKtUPaNOUq7oJkKHQ5X0o,3563
|
|
75
|
+
vllm/attention/ops/triton_unified_attention.py,sha256=Kz46YYWf9WA89hY-LlCo4o21qCeaG1onapkQPxOwnrY,26253
|
|
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=_30lBn5XlxeTgGNEiVOfLJbTIR89IMsa-PDUfi7jb_E,2757
|
|
81
|
+
vllm/benchmarks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
82
|
+
vllm/benchmarks/datasets.py,sha256=eqZw77HzULl2WTfD8tgeaPs0S5-a61f5b0QNzjEmRPE,53967
|
|
83
|
+
vllm/benchmarks/endpoint_request_func.py,sha256=Olu5YmEEb74JbGkJR0Ka3SLJgzfAYTio-vv6XYtunPw,15146
|
|
84
|
+
vllm/benchmarks/latency.py,sha256=res4151NBrj9zX_-qBVXGNmihj490wfSq8cdpbpqWsk,6047
|
|
85
|
+
vllm/benchmarks/serve.py,sha256=eBWO4ib57tXGTyVWX-vJ-GyWgweYKZtA0ZD2lxZgztc,42374
|
|
86
|
+
vllm/benchmarks/throughput.py,sha256=ziVFvYTyce3XsXX2i9M3EaTuaAWjyao6bCksrJWnUS4,24885
|
|
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=A5JNdOOFtQjHV4o8fJ6Vh_nk3HXfv_mYqkN1oSAMwzw,23948
|
|
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=xSlwW-zA071wSi1MGqQ7BHbQs1fxe53yA1ApYgWcPsc,23051
|
|
94
|
+
vllm/compilation/counter.py,sha256=OfGcezReWsQpsRwLeLajEhrepd4ORt9HxGczXFBICJM,1294
|
|
95
|
+
vllm/compilation/cuda_piecewise_backend.py,sha256=BhUXxvrlmWEv9Ka9P0qdEWlBfd6MF7JoZNmDXczYttI,9308
|
|
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=zseAI1PMprGMxLngZ4vcnyRulHqRCkg5SP0uSNJjaJI,25302
|
|
99
|
+
vllm/compilation/fusion_attn.py,sha256=WJgP2_O3mFenC4gLafTP-vtzJmDjA3rCjmd4v8Wm2Ws,7014
|
|
100
|
+
vllm/compilation/fx_utils.py,sha256=NTw_6bSgwkGsBuCyWfNU-KC8kzd2BOueEQNpD_s69bI,2931
|
|
101
|
+
vllm/compilation/inductor_pass.py,sha256=C3vwg9EQGkqcK32ffo6lxkU1BB400gb3X7NO2mlydJg,3451
|
|
102
|
+
vllm/compilation/monitor.py,sha256=3eICJCWnpV8yFqh1W3Dc2pb5e78-lu_BoiVr5EvE1mU,1415
|
|
103
|
+
vllm/compilation/multi_output_match.py,sha256=uuVLvzaBuEZjOLbrfQVH9tZvaBD2GdNwbidSNaWv9dY,3904
|
|
104
|
+
vllm/compilation/noop_elimination.py,sha256=vwhCcnl4LKwBAg70Au9gA24I__tA5EiGGpa18C6JVMw,6579
|
|
105
|
+
vllm/compilation/pass_manager.py,sha256=urJ-wZXOIWOPBqNIm0WqFu2p3ASkj9ATpZwRQ8rwQIc,3112
|
|
106
|
+
vllm/compilation/sequence_parallelism.py,sha256=FyLOn47ab3NyVf7D0oOaqJFVaTsfrXwQxIB5ZoQXxUg,18753
|
|
107
|
+
vllm/compilation/torch25_custom_graph_pass.py,sha256=OTZc1hc3eLlS8LhG4MvHwpglY5_1E_voPW7ShGS5HJs,1430
|
|
108
|
+
vllm/compilation/vllm_inductor_pass.py,sha256=UWjN_9vG43JyigxFbxfEyCeCENfLZS0YcXk9b9Yn-KI,2588
|
|
109
|
+
vllm/compilation/wrapper.py,sha256=J4zjVIUTfQ5nXO16kG2zUEfoi4J7LHO0H0bWoB0OIrE,5933
|
|
110
|
+
vllm/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
111
|
+
vllm/core/block_manager.py,sha256=hoy2z3wSg1cYQZ5SawdSXvmznslKU6o-bNrR6qvlOao,22437
|
|
112
|
+
vllm/core/evictor.py,sha256=FUiGVDiY8cmE59jf6ydo5CtYMEMGWWu6Zg6OLVyyQkw,5515
|
|
113
|
+
vllm/core/interfaces.py,sha256=ONM6fWByKR3Kbl37MIfZLYxQA5RHbnOt8BomFeDIs0M,3770
|
|
114
|
+
vllm/core/placeholder_block_space_manager.py,sha256=ORG0voTO36PriADYHn08Tvl24USqY4tOEp3mQ-SD4Ac,3134
|
|
115
|
+
vllm/core/scheduler.py,sha256=VyzcuT4a8nQ5zzFTSn0Xd-r3D0tzQyq9FPCN38_pppE,93429
|
|
116
|
+
vllm/core/block/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
117
|
+
vllm/core/block/block_table.py,sha256=Yokf5KU-onU1gp7dlqfWa0mQlCbtx9vNceGcg1dFDDg,16091
|
|
118
|
+
vllm/core/block/common.py,sha256=nTf2wtA0nWtbGoh5qsN8XmwIP8r9xlP8ry1lInaZTRY,13269
|
|
119
|
+
vllm/core/block/cpu_gpu_block_allocator.py,sha256=SKxpxXRGXLQuY3aFChuGkOnp_Ojpx_rFZJ0CMZY1FLc,17016
|
|
120
|
+
vllm/core/block/interfaces.py,sha256=BLv8rVkTVINbae_-Y5MLKUuZK-9Tix5qxlMRcb1jMRY,8213
|
|
121
|
+
vllm/core/block/naive_block.py,sha256=XPf0jZ5e5fJoXUss_Y6_mXAQ0D5bdYkCXZ2_XxlVoGU,16424
|
|
122
|
+
vllm/core/block/prefix_caching_block.py,sha256=BG_PRgkcH9vv25RhUlEVXPVSHBJw3ysKA-DSLBF2kk0,44251
|
|
123
|
+
vllm/core/block/utils.py,sha256=ecLOYLGeBIeqMCpbUNBoW6hJIHlG5EINgsf2Or1BHyk,997
|
|
124
|
+
vllm/device_allocator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
125
|
+
vllm/device_allocator/cumem.py,sha256=8mgglTfOAPBTO3A-aPswwh3HmGwye7UFoFoyhW49MuY,11018
|
|
126
|
+
vllm/distributed/__init__.py,sha256=l_KMMLMmYq-MqxY5OeTuQjA38RYwdS4TtVy8JafQq3E,191
|
|
127
|
+
vllm/distributed/communication_op.py,sha256=igCBXNoAhJ8eZooR79KhpzgYlVP1TUgnPF5C7BSpSJE,1562
|
|
128
|
+
vllm/distributed/kv_events.py,sha256=3A-SxHLe1Dar2IMHTtTlVHUTRjg1VSTvBUJzMMLmZ18,12357
|
|
129
|
+
vllm/distributed/parallel_state.py,sha256=HJtB42vSdKQwi12WbnlUO83TMU8ccBYRng4fHoLG8Ks,53330
|
|
130
|
+
vllm/distributed/tpu_distributed_utils.py,sha256=OOCkNrzouRGPCot0UMVeQPKSbBhXZnNaaRz1c6VKimE,7827
|
|
131
|
+
vllm/distributed/utils.py,sha256=K2CNfdyDZChfy6QWoMx-n6pDzbG8X4SBmdutEnhPNqQ,21012
|
|
132
|
+
vllm/distributed/device_communicators/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
133
|
+
vllm/distributed/device_communicators/all2all.py,sha256=qaut7oz8X0umUx5MBcN7dlu38syzNhYaZmHubQQgqzY,9724
|
|
134
|
+
vllm/distributed/device_communicators/base_device_communicator.py,sha256=YeqXOmte0UY-kApX7BKBSjZ0TuQyOGGE1nh3OmgPsyY,10312
|
|
135
|
+
vllm/distributed/device_communicators/cpu_communicator.py,sha256=BQEdx2b0lsrjFKzWeCDmsKIMEUyPoUo-rssTiRIoHyk,5593
|
|
136
|
+
vllm/distributed/device_communicators/cuda_communicator.py,sha256=i4Hrrmx57JKxFjb6LJ3yhRbJL7fRzemdtkZKT4YTSl0,8179
|
|
137
|
+
vllm/distributed/device_communicators/cuda_wrapper.py,sha256=1I1OZOc9-St5Zlr4gUmoDm7HxdS-T9ZE1ixOJGJK55s,7185
|
|
138
|
+
vllm/distributed/device_communicators/custom_all_reduce.py,sha256=h-P7nPNq6ZflvXdeqPvceE4aDxe3DVB60okDzVqbGWM,12675
|
|
139
|
+
vllm/distributed/device_communicators/custom_all_reduce_utils.py,sha256=FCWwNPzVLllZLBiK50myd3SlBiLIf0m1Ydpip5SM6OY,10558
|
|
140
|
+
vllm/distributed/device_communicators/hpu_communicator.py,sha256=SCAWX8SxecNzR79UE5AKysm7OP20nw_q-ABkLzqOtpk,1836
|
|
141
|
+
vllm/distributed/device_communicators/neuron_communicator.py,sha256=NF-k7fuSxpLtEatxVzTCt162N9rkRDTsxd82gV6J7VI,693
|
|
142
|
+
vllm/distributed/device_communicators/pynccl.py,sha256=6aOeCmloJqswF8rnfLhyuggNSN2D2SNDi4deLS7wj3E,9211
|
|
143
|
+
vllm/distributed/device_communicators/pynccl_wrapper.py,sha256=cZfkdFnL98QOQEdk4u8mzkFi4e0lYWp1n3ypHCL39j4,14099
|
|
144
|
+
vllm/distributed/device_communicators/quick_all_reduce.py,sha256=wOPHST5kQTcUECipz0Xr3wNx9eoMrrpm3z6QnOXVlKo,10885
|
|
145
|
+
vllm/distributed/device_communicators/shm_broadcast.py,sha256=x4C6QKStqUotHdkmI5OjcqWR24gA3U07v8V3t8EmC6Q,24959
|
|
146
|
+
vllm/distributed/device_communicators/tpu_communicator.py,sha256=mDqS1cHYs0zeptNKlMjkG667moa68Dc_Anx1iAVrfmY,4159
|
|
147
|
+
vllm/distributed/device_communicators/xpu_communicator.py,sha256=_a34w4noXIZW0099sLO3Z7CdLc-QC_NxKsnxH5wn5zk,2176
|
|
148
|
+
vllm/distributed/eplb/__init__.py,sha256=iDRi-3lUn2DaLMC9aCQ1xdvvLrRNpT1YFieBjVnYKr8,213
|
|
149
|
+
vllm/distributed/eplb/eplb_state.py,sha256=2dUSXy49xdbnifJvN1B-EB3WXnv0cQ7oZ4r0VZ0Dlek,15222
|
|
150
|
+
vllm/distributed/eplb/rebalance_algo.py,sha256=eqMleLcYqoXWL_WZDqAVhWU3tO-1NPVwicu45wwDpRQ,8952
|
|
151
|
+
vllm/distributed/eplb/rebalance_execute.py,sha256=bbkwMu3OWS2GksWlXkLz7JoahQdFfNh3ooMhRhuxC64,10502
|
|
152
|
+
vllm/distributed/kv_transfer/README.md,sha256=B4s4s-6F9FP4wbgmrYJDSpdUu0_Yq4EeWLEyZMNkAyk,2006
|
|
153
|
+
vllm/distributed/kv_transfer/__init__.py,sha256=s4nYYd_WS6iDGPpYMvXnq8-x9vt-776yOsxnnRU2cvU,461
|
|
154
|
+
vllm/distributed/kv_transfer/disagg_prefill_workflow.jpg,sha256=fOFUEx-2Fm1uxHCGopvCREaRqdvR87Z7C0bMqEVH3Iw,142656
|
|
155
|
+
vllm/distributed/kv_transfer/kv_connector_agent.py,sha256=Pg8790EwU7LAYJMVdK8_jWs4V-7SYfQZjdzvSU0nvAE,2489
|
|
156
|
+
vllm/distributed/kv_transfer/kv_transfer_state.py,sha256=aYn9HaM0YH-4S-8V7R4wacCJ4kaYbXuOgZnhA7J2xvE,2335
|
|
157
|
+
vllm/distributed/kv_transfer/kv_connector/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
158
|
+
vllm/distributed/kv_transfer/kv_connector/base.py,sha256=pU3LM2zTdnzLb-GlxUeppL0i9Gl-ZoTew-Qu2U8ZSmQ,4490
|
|
159
|
+
vllm/distributed/kv_transfer/kv_connector/factory.py,sha256=6R0hlOFGedS5O2YgM0lMuUBwSL0llgspFP-bHNXbf7M,5081
|
|
160
|
+
vllm/distributed/kv_transfer/kv_connector/lmcache_connector.py,sha256=14YN5LyPfFUPOlqXtAGp5t1c6d6AkeA7orahdQ7W2Xs,3739
|
|
161
|
+
vllm/distributed/kv_transfer/kv_connector/mooncake_store_connector.py,sha256=-Dd0D8xfrt6dVXhWy2CL6Dy6-rHaXkoBIFGWcYlOUqY,8679
|
|
162
|
+
vllm/distributed/kv_transfer/kv_connector/simple_connector.py,sha256=n-613lm8SPqXM2_fpJin3lYqePhbir3UpQu2eR48pp4,13926
|
|
163
|
+
vllm/distributed/kv_transfer/kv_connector/utils.py,sha256=CXDh-Hz8B9hcPw9KDjeeRFmPqM8jXsuGkLoeK4RwqbY,4632
|
|
164
|
+
vllm/distributed/kv_transfer/kv_connector/v1/__init__.py,sha256=Vgcn88rEfiLwJ3-YkZKWsvMurr-vsV4_47b9_Mv-vlo,265
|
|
165
|
+
vllm/distributed/kv_transfer/kv_connector/v1/base.py,sha256=92ACWysP74FT4jc-m5A0WKrMj016UbzN2rK7RHiK6DI,10012
|
|
166
|
+
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py,sha256=sB7ghOX2tfCvqdmHx7jFROLwGva7_p-VdLUiG6X6JJw,6504
|
|
167
|
+
vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py,sha256=s9MS6JeW94duB9dw0OKkiUODHprffi6VtZz622s0Xv8,8243
|
|
168
|
+
vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py,sha256=LSqV71mSjLZeGolsI3Qcrz0iRLRNQ1ABeZK7VB3WcNY,49828
|
|
169
|
+
vllm/distributed/kv_transfer/kv_connector/v1/shared_storage_connector.py,sha256=3PQFsKr15sMaihrXGq2MdTtdJ86Glao5U-wn6iygvrE,16007
|
|
170
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
171
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py,sha256=lUI37JeumbRMUycLS8AobawsHpiJ-fMIKK6SJRLcau8,19496
|
|
172
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py,sha256=A43Rq0liuRgAQsnbHhrC4kKe5R7e3ySkb8soTxYIN7s,22216
|
|
173
|
+
vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py,sha256=72pW3MousT9HFG_lDRpjsyQFnaL0a500Ux4hv1Vgjm4,9365
|
|
174
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
175
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/base.py,sha256=ZZYJZBDDny_StDcmXUFwOtDslRrTCL9iSUcr8XWe08g,6280
|
|
176
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/mooncake_store.py,sha256=atXfrR3n4MZAB88TtNmVAC5Gn9FhyVFcVRO1VjjL4uA,5679
|
|
177
|
+
vllm/distributed/kv_transfer/kv_lookup_buffer/simple_buffer.py,sha256=m8XNP5UiFwq2g33f3fiJeLMu87OhKwSvjWcI2jppztk,9156
|
|
178
|
+
vllm/distributed/kv_transfer/kv_pipe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
179
|
+
vllm/distributed/kv_transfer/kv_pipe/base.py,sha256=FHfg3C53oZjBBZjEWHmxMOPKTvJitfBOXXFzh8j70cU,2156
|
|
180
|
+
vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py,sha256=2EvJDsONyP3zDJwWDik-pGsZoE5Qsre1DAmBQAUFJeQ,12390
|
|
181
|
+
vllm/distributed/kv_transfer/kv_pipe/pynccl_pipe.py,sha256=NjIOnIl2Fv7H7S-SZn2_xroAcZ39Vg2CCi90Q4iSRzw,9720
|
|
182
|
+
vllm/engine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
183
|
+
vllm/engine/arg_utils.py,sha256=eye4YaCzv4-kAXEDpMfY61PcP--cVQdg9eubpeiHn_4,82910
|
|
184
|
+
vllm/engine/async_llm_engine.py,sha256=8iiLRsYuNDmaqjYMLo--IgRvfDOP3MhWcuzJZvWgI90,49066
|
|
185
|
+
vllm/engine/async_timeout.py,sha256=uxUlhUevs6Ae1VvJ0GTkj23bAkg_w_CWteeXTCAFYvM,6594
|
|
186
|
+
vllm/engine/llm_engine.py,sha256=W53-gCSzVP3PfgRlJzXIbTe6jXpNY0ebC7WsxPpX2_0,92077
|
|
187
|
+
vllm/engine/metrics.py,sha256=LG_2wawnok658rpG6ZJFnMod7G8aydjteOYz4WwFMz4,26793
|
|
188
|
+
vllm/engine/metrics_types.py,sha256=8_E0ssV3TKZZr63dInytvsEluXgUvrPhrpnRPISUdso,3248
|
|
189
|
+
vllm/engine/protocol.py,sha256=cKcx2R4wR4l513cfnxs8L7Dv68XZ75IZnw8GuKvzYaY,11738
|
|
190
|
+
vllm/engine/multiprocessing/__init__.py,sha256=DMMFIKmNM1hn6leoQn35h2d5UaTpaHilKJfC2ar9jv4,3747
|
|
191
|
+
vllm/engine/multiprocessing/client.py,sha256=tWa-XGcWzDiwhnHTfnclR_eivmzxSJS7kyJDpa2c31A,28210
|
|
192
|
+
vllm/engine/multiprocessing/engine.py,sha256=27etqUvs7Qdkbo-aa577eZBSOXM545ZiT6B8otT7xXI,18400
|
|
193
|
+
vllm/engine/output_processor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
194
|
+
vllm/engine/output_processor/interfaces.py,sha256=jSj7l8R2YbHeKyDrcOamQAOZPgvarX2lERWMFFBJZd4,3063
|
|
195
|
+
vllm/engine/output_processor/multi_step.py,sha256=aZhtnbioId3KlW6nRc4GPJd_fHubXtaLoCx5ZabIbzA,9507
|
|
196
|
+
vllm/engine/output_processor/single_step.py,sha256=W11dmtv_-7wwuDafhgUdLR_Hf6GHrg56pmQI6LHITj4,6422
|
|
197
|
+
vllm/engine/output_processor/stop_checker.py,sha256=wPsxTqC2x2HkggUrTtnme3DL37gdwVZ37SDspMsdWTo,5137
|
|
198
|
+
vllm/engine/output_processor/util.py,sha256=358XXxAOG9vNO6uRTfINK0B-oCzqbidVpXfV5nrNs2k,1125
|
|
199
|
+
vllm/entrypoints/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
200
|
+
vllm/entrypoints/api_server.py,sha256=F1c5uZ-WFzmNtrpSH158bOzv6p623tmY7gimPZiwMGY,5818
|
|
201
|
+
vllm/entrypoints/chat_utils.py,sha256=wlkOSrF2t7Xk-EM74U2ZctDErj8DHsX8aDU7LuKIHSQ,45134
|
|
202
|
+
vllm/entrypoints/launcher.py,sha256=l_VfSBIAVo-xE_HauO8G5GxKPcue16XdITvTxs9oyjM,5281
|
|
203
|
+
vllm/entrypoints/llm.py,sha256=OU7RU1Z0dlfYolc5wqEYBCp7HyUKWXB7r6kDT4dngiA,72014
|
|
204
|
+
vllm/entrypoints/logger.py,sha256=fFcBqHM8hitDzkj-pNaFGN7EsJywkV8GXXI_ZsfL9u4,1685
|
|
205
|
+
vllm/entrypoints/score_utils.py,sha256=ZUxphYOqXVj14KbPAvvKgX2derLYMvir1rM2WXjsP3Y,1723
|
|
206
|
+
vllm/entrypoints/ssl.py,sha256=2InxP04Dt_I84ORXewngn5cUdXvRkrK_zZB6o8Ng60k,2805
|
|
207
|
+
vllm/entrypoints/utils.py,sha256=tTi_r6LIttzhI0AZZtOAdg23Iys7r8SQHkYzZEMnAZY,10918
|
|
208
|
+
vllm/entrypoints/cli/__init__.py,sha256=GRsSDBSSOHMLZfY8jjf-h5gFMOaOaicDAgcIGCVZdI8,482
|
|
209
|
+
vllm/entrypoints/cli/collect_env.py,sha256=GebDsiNF6qvxWrzz8RaQdOnHZtFeoDnNGCMrSvq5krA,1069
|
|
210
|
+
vllm/entrypoints/cli/main.py,sha256=_EZdMQzKYUjKg4yhZ_YTIuifzD82hTSy1Oq8NxXpfuU,1977
|
|
211
|
+
vllm/entrypoints/cli/openai.py,sha256=0XiQTTBsbtjPXOoHpWKXGTtjuJwWUnflN9fkuIItEqQ,6795
|
|
212
|
+
vllm/entrypoints/cli/run_batch.py,sha256=mMDDXRcW7PAxX06bNL908Mi2LwFH8Lv6q0DEKd_8jLs,2403
|
|
213
|
+
vllm/entrypoints/cli/serve.py,sha256=EBQ_DG20bw2ccSrKZAN6LkbEQYWY4QSrpLNR9KvOYyo,10334
|
|
214
|
+
vllm/entrypoints/cli/types.py,sha256=horNt6_2wEsuLNQ1-zoQ3BWsMkvMxJAxcTC-eQS4O1E,785
|
|
215
|
+
vllm/entrypoints/cli/benchmark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
216
|
+
vllm/entrypoints/cli/benchmark/base.py,sha256=r1QkRTjaUCcjO78Zw9zuDeRhMdaGw22N3hqO8kgrOsI,674
|
|
217
|
+
vllm/entrypoints/cli/benchmark/latency.py,sha256=MYxv7pF4kq6StJN5uZYxOm51lIHfNyvMIvXU--szia4,653
|
|
218
|
+
vllm/entrypoints/cli/benchmark/main.py,sha256=IWYHShB_3jDLgk8cFj64xaqpXhPSjSuiYHEw6C8TwNk,2036
|
|
219
|
+
vllm/entrypoints/cli/benchmark/serve.py,sha256=izuara3nwC64MtoealX_FzR9cB6u4YQv0fDikj-VdNI,635
|
|
220
|
+
vllm/entrypoints/cli/benchmark/throughput.py,sha256=YN5PAz4aDjxXkao1a_RjrR8hLGzzjYPecO_OIp1TVwQ,652
|
|
221
|
+
vllm/entrypoints/openai/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
222
|
+
vllm/entrypoints/openai/api_server.py,sha256=eDG2W0gr_qLEp7mU3nPOGDeyYoj3npcv6eGYw6_EAik,56897
|
|
223
|
+
vllm/entrypoints/openai/cli_args.py,sha256=GXd1_6c4JjOlVuZurcDbn-4afrUY7Fl6nSJVrhOL2qw,13012
|
|
224
|
+
vllm/entrypoints/openai/logits_processors.py,sha256=QAJn3DMAfFySExoA5aaSNVjXwtlOXGCv1DX6Fltj2ZY,3230
|
|
225
|
+
vllm/entrypoints/openai/protocol.py,sha256=jT-wY4cezRYpKhOZaI6Nbabg0gQWxLRSS0Om5q1V6sw,76455
|
|
226
|
+
vllm/entrypoints/openai/run_batch.py,sha256=xce9ofsHNsxAkdpvUqfCsUitk-o_ak8sbGjnkBU8NbQ,18031
|
|
227
|
+
vllm/entrypoints/openai/serving_chat.py,sha256=S2kvtLv_NUvr4yKGFUqUIB9dS4rP7duZ9PeNzBtub9M,59708
|
|
228
|
+
vllm/entrypoints/openai/serving_classification.py,sha256=8bcKvF1Nnp2MjcphEGke8ar6srj-Ef1gkFF5CzgUduA,5335
|
|
229
|
+
vllm/entrypoints/openai/serving_completion.py,sha256=98S-lJtx4xyiXzur8ri578OyO4-YXz-6TKzG7pp0B-U,26797
|
|
230
|
+
vllm/entrypoints/openai/serving_embedding.py,sha256=ejT3CsStaQQFYO3Vms9tsitHkaumFMHr6VxkGq4CWKc,7384
|
|
231
|
+
vllm/entrypoints/openai/serving_engine.py,sha256=xI31D9Pht4d5bwVd71j7oz2f0aQNXDoWrA6OTLG4dGk,38943
|
|
232
|
+
vllm/entrypoints/openai/serving_models.py,sha256=GYqPJtMw350_fpm8b0kxjHU1z_omJQTPgptTq0lJgPM,12797
|
|
233
|
+
vllm/entrypoints/openai/serving_pooling.py,sha256=u9WWLUuiNCzrFWVBPKui0v1HMMCvhxsepaVMuZlYkNY,8788
|
|
234
|
+
vllm/entrypoints/openai/serving_score.py,sha256=9RB5VPrK0TOlvQfLcGvlGthT_sfQ5Y0Mx3ySk2UcRuk,15874
|
|
235
|
+
vllm/entrypoints/openai/serving_tokenization.py,sha256=9SMgGGjM3uLkmXRfzRno57BEX6xOMgSm9pJtET1XCTM,6090
|
|
236
|
+
vllm/entrypoints/openai/serving_transcription.py,sha256=9fC69G29zYk9zbQHsrBfjf4Y0mVwAayDJXfijAMFkDI,5406
|
|
237
|
+
vllm/entrypoints/openai/speech_to_text.py,sha256=y3fBU3g-YgHVVUFtqyND28Xf8MAHNbYSCLMRAizZ3EM,16646
|
|
238
|
+
vllm/entrypoints/openai/tool_parsers/__init__.py,sha256=Wj3QTkShDPQ7mvwbxJqGzKaCipt87dvlUYf42avl-vU,1239
|
|
239
|
+
vllm/entrypoints/openai/tool_parsers/abstract_tool_parser.py,sha256=UyO8engPSTh8Ej8EuQay-mDz9YPzHAsmzJA43-4vmq8,6095
|
|
240
|
+
vllm/entrypoints/openai/tool_parsers/deepseekv3_tool_parser.py,sha256=_D9ZPcyXrr4ZC5Uvn1JAx2m3zYqbQBnQjO2S8E8urbw,16692
|
|
241
|
+
vllm/entrypoints/openai/tool_parsers/granite_20b_fc_tool_parser.py,sha256=YqhxroDlNDpZOwbrAHrdpBLKRnahVNQahd2N2z9Lpl4,11502
|
|
242
|
+
vllm/entrypoints/openai/tool_parsers/granite_tool_parser.py,sha256=1LKw06AkMy82c4zXRu41Edthks6Z4xazB4nyhLiRy9g,10723
|
|
243
|
+
vllm/entrypoints/openai/tool_parsers/hermes_tool_parser.py,sha256=BTNW2L9BHkqNEmiTkqTZlYrCecr5KNIIvbAB4SIquTY,16891
|
|
244
|
+
vllm/entrypoints/openai/tool_parsers/internlm2_tool_parser.py,sha256=4cNKa6P7IrMVi2PqH4zqO57Fsq61ONP5UX867C8m-6M,9465
|
|
245
|
+
vllm/entrypoints/openai/tool_parsers/jamba_tool_parser.py,sha256=R1uMMM4Vnji28xyHVqB1N2O0CpHaW6NISeoc1NsxjJQ,13947
|
|
246
|
+
vllm/entrypoints/openai/tool_parsers/llama4_pythonic_tool_parser.py,sha256=k6f1xFWCjG1KIyHOQ-bN2nYaPbgW2bNvkMpn8GV2FsM,13258
|
|
247
|
+
vllm/entrypoints/openai/tool_parsers/llama_tool_parser.py,sha256=yY9n9uxy0q5SQ5yI9VGf6dSpOcde-3gY-o-wZjSncPU,12313
|
|
248
|
+
vllm/entrypoints/openai/tool_parsers/minimax_tool_parser.py,sha256=DHFKM3XGLW7GnukQ2OjNosCjkXlzJDQxCtOOex9PcVY,16597
|
|
249
|
+
vllm/entrypoints/openai/tool_parsers/mistral_tool_parser.py,sha256=SfxxAVcyFkCJkctRRSf-XKET42DeLREy6I_rNy6Efsc,16544
|
|
250
|
+
vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py,sha256=o7RbhWFthf2VKwtuxZfZyVdJAQ_5iOuSLHdsoz2Hf4E,4346
|
|
251
|
+
vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py,sha256=xJELNmJ0_6tHl6OZh_EmY57b5QjGO1yQ3rLI46XoozU,12636
|
|
252
|
+
vllm/entrypoints/openai/tool_parsers/utils.py,sha256=RrvMsSpaYYMPefvM1ktVKzo9Gs5KsHpi21QaP1h4EKU,3874
|
|
253
|
+
vllm/entrypoints/openai/tool_parsers/xlam_tool_parser.py,sha256=CIrKFUR0b-7O81zmpwbcaQbPXKo_vFqoQlkSU0xiiEo,21370
|
|
254
|
+
vllm/executor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
255
|
+
vllm/executor/executor_base.py,sha256=L9dpD4kIXgn2KJ5XTHvtZ2OpMXM1JEJfZ1-QVIbCcRI,15732
|
|
256
|
+
vllm/executor/mp_distributed_executor.py,sha256=zhyIz7Smu33879dkoQ4FHO0r47BSWjBnFfpwWjqsf-w,9923
|
|
257
|
+
vllm/executor/msgspec_utils.py,sha256=0tCYOinMJxzOI-U8fAY8C9A9seN0f4MdaE9H8PJuuAE,978
|
|
258
|
+
vllm/executor/multiproc_worker_utils.py,sha256=1Ddh8AEFrh6GIWbRqm7I-Kupluw40FPIVijgak_5434,10794
|
|
259
|
+
vllm/executor/ray_distributed_executor.py,sha256=bk3p0Q1hzPcJH5H2_BEtofhZaa9xNlItzQmyS9O9XvQ,30921
|
|
260
|
+
vllm/executor/ray_utils.py,sha256=rsav_z9cZnKIGz37knp2YUtx3ThtYAdP85smG2y21d4,16883
|
|
261
|
+
vllm/executor/uniproc_executor.py,sha256=23FH6Z3EqfCQEf7IOFFkhKIaycByazM5EkQrUNoZkbM,5548
|
|
262
|
+
vllm/inputs/__init__.py,sha256=8cagQSlaOP05DjPdGL1EPpOOYaYkWlNHzQ25JigzVu4,1329
|
|
263
|
+
vllm/inputs/data.py,sha256=_KoSfLXeSwi4981LvUyMJU22Sjs2oO4KfkRUKcth2RA,10829
|
|
264
|
+
vllm/inputs/parse.py,sha256=_Lbf4PQyczm3OPsLgvyPf3CiKGNP1Ctd4bW_AnuORpk,4499
|
|
265
|
+
vllm/inputs/preprocess.py,sha256=8Al2bfJ2UtifNoiZSuvqRrrspDDl2_ZnVjBuX1WlzmE,35310
|
|
266
|
+
vllm/inputs/registry.py,sha256=zN3YtGaE0VhwOlbU4Lcr1kCLcgAEdJrQtyTTIRdOdjU,7928
|
|
267
|
+
vllm/logging_utils/__init__.py,sha256=lGnFUwOOIQYnuCu-Pf3LKtxPRmx6DgkxlxknU9fO3-Q,205
|
|
268
|
+
vllm/logging_utils/dump_input.py,sha256=g9nr91If5qsBTNXuKD9FeCOs8Z9N4zsj-kMpJISODKk,3071
|
|
269
|
+
vllm/logging_utils/formatter.py,sha256=kIZNddJTgIcB1RRoJc0fFmDtsVv3X0GGUgblS2PdW48,594
|
|
270
|
+
vllm/lora/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
271
|
+
vllm/lora/fully_sharded_layers.py,sha256=6o8xjkxFJd1A6ESz1KeEDPYWrs0RNjHAJZ8d6IUntc8,12694
|
|
272
|
+
vllm/lora/layers.py,sha256=4hCNy2hikilII0BrxHHV_RS7o89r_0ZVtue4sQI1jII,46741
|
|
273
|
+
vllm/lora/lora.py,sha256=AuAxQNXr-6RLCn7Kc28qqbgA715IDb7yfuReHchu10I,6294
|
|
274
|
+
vllm/lora/models.py,sha256=4BI3xb5pkqQF0sp-6D3aaYuiZsFKCRQ0R4ysJLeokdE,36044
|
|
275
|
+
vllm/lora/peft_helper.py,sha256=VBwUFq0hnhQZK8qL90VEjazb4ClFDO2lro_-UVwOYcg,5334
|
|
276
|
+
vllm/lora/request.py,sha256=spYbJvjKyPlu1a1otY3sxI4JBpAzUvLLjhyxFJP2Cg0,3178
|
|
277
|
+
vllm/lora/resolver.py,sha256=6iZpDMfxWGcy8MWlj3nCCcVmgr6nKs8EzzOhaN4TiCs,2881
|
|
278
|
+
vllm/lora/utils.py,sha256=yi5k_4gUwrJv4g_rNrEgUMUBci2xASELsROgOUISC8g,9318
|
|
279
|
+
vllm/lora/worker_manager.py,sha256=6xLqeBYVf0HTRBnujIY_ZfbhzocBJOKNXocOGs5OR4c,10970
|
|
280
|
+
vllm/lora/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
281
|
+
vllm/lora/ops/torch_ops/__init__.py,sha256=ywu1d5miStgp7A9BRAo6kUvuE3AcgOAOJHxYHD4cKvQ,535
|
|
282
|
+
vllm/lora/ops/torch_ops/lora_ops.py,sha256=LOSdfKpQM365cIWVkyElcLpfgn8cF44IVw-KUN2NMKs,4517
|
|
283
|
+
vllm/lora/ops/triton_ops/__init__.py,sha256=arDrNt_kvrDaC4mN3RNbu6-0YACXQRp9Md2cJxXI1ao,384
|
|
284
|
+
vllm/lora/ops/triton_ops/kernel_utils.py,sha256=3P-CWMjNQR2vp3QUNynjXAIaWQy06mEFDTRLRQljDME,8509
|
|
285
|
+
vllm/lora/ops/triton_ops/lora_expand_op.py,sha256=740f2SjW7lP2rtbFIGFl2e-FnCHxGv_tVs9WmbqftBE,8965
|
|
286
|
+
vllm/lora/ops/triton_ops/lora_kernel_metadata.py,sha256=YgL-K9fVeFZebx68DJNvrqsfZI5o0thpa---d4NYlnA,5967
|
|
287
|
+
vllm/lora/ops/triton_ops/lora_shrink_op.py,sha256=WfuQ1-7dtJAQ_Pc7sN8yl7jRkcsYX0MXZ08uwatdEfg,7996
|
|
288
|
+
vllm/lora/ops/triton_ops/utils.py,sha256=zsQcSl0sWdYUefY5IWqVOpjdXySLSSsHgTwNPwKkWJY,4916
|
|
289
|
+
vllm/lora/ops/xla_ops/__init__.py,sha256=2Yh5hqiUt7hGz9SwznSZlj-_G7-SknTauNyHGDcUjBY,304
|
|
290
|
+
vllm/lora/ops/xla_ops/lora_ops.py,sha256=hLERTyHuXcH5J5ePn_3cak2Mi5S8_i0BcXiJmNZHBEk,4400
|
|
291
|
+
vllm/lora/punica_wrapper/__init__.py,sha256=A5cDJmdCPRBN23kwLfemRlWI4YA-t_7qIxeoeimCkT8,313
|
|
292
|
+
vllm/lora/punica_wrapper/punica_base.py,sha256=oR-f11G-ga_JOazy2M3iBoBaRb1D6ifWn7xbkCB3gGI,18500
|
|
293
|
+
vllm/lora/punica_wrapper/punica_cpu.py,sha256=sFBBu_qBEL8LGALamK7hE1ympyipYNT4qpav-V1nllU,12527
|
|
294
|
+
vllm/lora/punica_wrapper/punica_gpu.py,sha256=Wg8n1z8_pdxolBakhIPV8rNi059HnmzK2l1kPS_2LV4,10885
|
|
295
|
+
vllm/lora/punica_wrapper/punica_hpu.py,sha256=qljiMC-THj_SIhaFeHygMQuB13wBKyz7dr-ba_aqpaI,5848
|
|
296
|
+
vllm/lora/punica_wrapper/punica_selector.py,sha256=Of6p5uYMMLnA6g46VK7M3xJT8Xq4q1VFoeOpTIsPf3s,799
|
|
297
|
+
vllm/lora/punica_wrapper/punica_tpu.py,sha256=utenbLEam1-CCYjnXFDC-zKfzp2H8ndBop3XRlCp5YU,16290
|
|
298
|
+
vllm/lora/punica_wrapper/utils.py,sha256=UekPGq8Xm11GtUtxhnGRv0mopTYL82nqyJg7YtXrjRk,7048
|
|
299
|
+
vllm/model_executor/__init__.py,sha256=vE7mcT8ZyKWc-wlc4pq2-ofRwEDVYT67HSgD-hLut0Y,574
|
|
300
|
+
vllm/model_executor/custom_op.py,sha256=Z7HWjzCFMT7-kdS_wD5a6siDPbF8vRIxNBs-gk8eCwE,8145
|
|
301
|
+
vllm/model_executor/parameter.py,sha256=H_qq9zP0q0QbDaPbDkH9coanlZZVWsTZ_kbvlt7KYEc,16758
|
|
302
|
+
vllm/model_executor/pooling_metadata.py,sha256=bbOjrSCh_8aX9M3oML5oyUzijmJhy9Gb5_7bURoCi6w,2127
|
|
303
|
+
vllm/model_executor/sampling_metadata.py,sha256=6uc7pahkFyei2c-4Mn0jX10MQFQKKKhm7VJUCxRbQ8Q,23013
|
|
304
|
+
vllm/model_executor/utils.py,sha256=by3e0DLA6BRNRLvduXVWeiYMjYH4T_d_2bIvUHvGoew,3066
|
|
305
|
+
vllm/model_executor/guided_decoding/__init__.py,sha256=XEvEfOGGBuBsKrwc_mOi9XjbzCdr0SK6N0PmyWyhyVs,8332
|
|
306
|
+
vllm/model_executor/guided_decoding/guidance_decoding.py,sha256=-goDVm60krE6RH482nbUTXSeDQ0jnxnWVCW3ep8qoRo,2600
|
|
307
|
+
vllm/model_executor/guided_decoding/guidance_logits_processors.py,sha256=mcy35zX1YHfKoxJZADvLxkP5F8OYiEHO_P-Xg_lQZrA,3344
|
|
308
|
+
vllm/model_executor/guided_decoding/guided_fields.py,sha256=KSAGqffFpedIz4LfgwAodX2eJkyOZ4RTD49ynzSbrTU,1566
|
|
309
|
+
vllm/model_executor/guided_decoding/lm_format_enforcer_decoding.py,sha256=jl5gxFhJkIL2pSOzKhgyHL_1qRszIakyNN6LbrFJXfs,2747
|
|
310
|
+
vllm/model_executor/guided_decoding/outlines_decoding.py,sha256=-MKzmEGn1QuulI2JDU1cAejfo03nHxlQluadMJe27h0,5571
|
|
311
|
+
vllm/model_executor/guided_decoding/outlines_logits_processors.py,sha256=UfCgpaI1KwSFNjtQ-2lmBTYkLszSXQrVZhtvKpeKras,10889
|
|
312
|
+
vllm/model_executor/guided_decoding/utils.py,sha256=n6prXaBa-qiTes5wPhIX6CJg4Chrje_wQNsWxYuiYf8,7966
|
|
313
|
+
vllm/model_executor/guided_decoding/xgrammar_decoding.py,sha256=plEHV0pFHJF06jgMg2w1Tlok2h31D3M6C2GA-Zpx7lU,16833
|
|
314
|
+
vllm/model_executor/layers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
315
|
+
vllm/model_executor/layers/activation.py,sha256=90nuTBBkLIV67E8sf6PJmKps8C1YLTRmk27lEGHoHHQ,14833
|
|
316
|
+
vllm/model_executor/layers/layernorm.py,sha256=TJ8SzNBK-ojTf6-ttBvBlpfaoMTMeLLtI7iJh-NuQrU,9229
|
|
317
|
+
vllm/model_executor/layers/lightning_attn.py,sha256=KqXTG_XlaAu2K6kT1wSNU5fGAKWEcrZR1CR0RmdpxCM,20962
|
|
318
|
+
vllm/model_executor/layers/linear.py,sha256=sR56AyoR1hWo261RvoLU7UfxQXiXZmUT774GOwriU6E,66592
|
|
319
|
+
vllm/model_executor/layers/logits_processor.py,sha256=ehI9fTIQE3eOUxZTl9tzjYSWtq6NtPvPPW_HlzqYBq4,7825
|
|
320
|
+
vllm/model_executor/layers/pooler.py,sha256=5BQli05V2Or7eK6K6xbqKs1HjUr8D9gNmVo2qSa6LzE,17616
|
|
321
|
+
vllm/model_executor/layers/rejection_sampler.py,sha256=bxKc8EWgs7weN47bQ0--kBWoO-2R4_syZHpcsQIXVMU,16381
|
|
322
|
+
vllm/model_executor/layers/resampler.py,sha256=jDG2clcusNHfxLptLZUbbwxmxC3f_I-KJ8tJIdjyuLM,10506
|
|
323
|
+
vllm/model_executor/layers/rotary_embedding.py,sha256=Ts4WCp2nv_UynBEEmMO4wPdLzRl8XvinEVWtrgcWvpU,85280
|
|
324
|
+
vllm/model_executor/layers/sampler.py,sha256=gOsxvuWntPAVabVMCKSma_pS6XnmOr80QMAE1iAxdbw,49689
|
|
325
|
+
vllm/model_executor/layers/spec_decode_base_sampler.py,sha256=ZtvhMhd0DYJlYpqkLyIoiUec0gvqVT8IqnotqN60EAE,10253
|
|
326
|
+
vllm/model_executor/layers/typical_acceptance_sampler.py,sha256=AZ-q02vuqxGMQLgBL07uLl67T3Zrw_YtwglJwmyu5UA,7026
|
|
327
|
+
vllm/model_executor/layers/utils.py,sha256=cxNhw8xipShiVCHzIplhn57MCo7JhsRrePB9BaWRuyg,4648
|
|
328
|
+
vllm/model_executor/layers/vocab_parallel_embedding.py,sha256=fFc0n_9FIS5vh4RnnbYga2Kai7DeWa4eH9xAAbUrrk0,22772
|
|
329
|
+
vllm/model_executor/layers/fused_moe/__init__.py,sha256=CHNvtswV3WEKnB-45jKGsEthRmrh8EYuwgCbYW3l0LY,2567
|
|
330
|
+
vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py,sha256=7xm-S5BCFBe9oh7_0MvWg12NNHdBv-O8bNinSUdPrr8,10139
|
|
331
|
+
vllm/model_executor/layers/fused_moe/batched_triton_or_deep_gemm_moe.py,sha256=caL17KrwQqdvWsTQBSmHnoQ8xohQk9sd9TgMFBYLhe4,5732
|
|
332
|
+
vllm/model_executor/layers/fused_moe/config.py,sha256=z7xVCUb4QIyR1p3VHNtpbUi_oPG6rZDSV6a_sbLkxEU,15807
|
|
333
|
+
vllm/model_executor/layers/fused_moe/cpu_fused_moe.py,sha256=1MNK6sAY1S5oGHcKi5ubYlvmfUhdeKaJsfVfbG2TYwA,8052
|
|
334
|
+
vllm/model_executor/layers/fused_moe/cutlass_moe.py,sha256=nc9YumSMU0RUgIqrV1noJ2Zb7aKhjwIO71Qj5VScfSE,25502
|
|
335
|
+
vllm/model_executor/layers/fused_moe/deep_gemm_moe.py,sha256=89GqTv9spTJYjXunPPjJ4y2RbMpKbD19NJIhFljkiz0,9038
|
|
336
|
+
vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py,sha256=eOVM570DVo6O6XXP8C9rNeMjKDjB08B7Oh6Q3bNAlAw,9502
|
|
337
|
+
vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py,sha256=Tlti7vl8KDK5J8eJRFQaERCGc13Ab0Vjvybm0Wu0Wyo,7106
|
|
338
|
+
vllm/model_executor/layers/fused_moe/fused_batched_moe.py,sha256=r8UOaKontRIOvP0xNU6OYFrsUogrOT8BN645B9ScIGE,33507
|
|
339
|
+
vllm/model_executor/layers/fused_moe/fused_marlin_moe.py,sha256=LAhBZlguQT0cEyCbq2zPRUMgjySjJnyJt6BYLUYFrdM,9097
|
|
340
|
+
vllm/model_executor/layers/fused_moe/fused_moe.py,sha256=C8NFnOcTjgzAcchyaGnQD-ilfzI5EvETz4RJMXWLqRM,69626
|
|
341
|
+
vllm/model_executor/layers/fused_moe/layer.py,sha256=NGfsBfkd2FpqCrDnxTTPqEKs014HEqgNS2t1keGDpiI,65074
|
|
342
|
+
vllm/model_executor/layers/fused_moe/modular_kernel.py,sha256=hapIoxtr97WDkCV4YM8JsE97Q3BG3nlWQyFWrVaNu7s,23803
|
|
343
|
+
vllm/model_executor/layers/fused_moe/moe_align_block_size.py,sha256=RI35iIYmK-SX_GkkkA2QmZSC83kJ6Z89leBvsuHh5uE,7986
|
|
344
|
+
vllm/model_executor/layers/fused_moe/moe_pallas.py,sha256=AynMAg-Va0T9qvSeofHp4ZuRYWN6pQdZPTL5EKHRcps,3158
|
|
345
|
+
vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py,sha256=A8JBstS-8q_zQG_QCcSGrQUpFgajfE-rOxIkrkVRYCA,7973
|
|
346
|
+
vllm/model_executor/layers/fused_moe/moe_torch_iterative.py,sha256=ZSvVVU8rUzENLnHycTypPg2UhO9eF_eu6wm1HEtpl-s,2156
|
|
347
|
+
vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py,sha256=2eayFDjwZbwiMAqZAVOnuUuy2oGy_ksCbxZ0-rSYgvw,8259
|
|
348
|
+
vllm/model_executor/layers/fused_moe/prepare_finalize.py,sha256=6tqGCFXGWZU6rH2Iw2JLgW7fwN3R2qgHTVZnTJb7xBg,2321
|
|
349
|
+
vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py,sha256=kcoT5dukDEr-C1tEOmIeuso6uRO1qMf2zBEm6DvIhBQ,14806
|
|
350
|
+
vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py,sha256=ZlRDlL5ve_GIFzEykzc0jYwQQ6YSfzwuxJcb7dv5fR8,4921
|
|
351
|
+
vllm/model_executor/layers/fused_moe/utils.py,sha256=Ig6dAafqf8wDzpbu6j_iRjmknRhxMKsFGNGovSYzwQA,4796
|
|
352
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=iNGsE2ZeVnQEnN4A8UJ9Jv0d3hbRF2MJ9oBgjup5Szk,2737
|
|
353
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=hH5rRN9Wtyv35azxMzyUMHWtiKgOHev5tNjIG8j6dsE,2751
|
|
354
|
+
"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
|
|
355
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=s47lb8VLnyxMgWlqcIR4BdPBsjKWL4olXF49uZvygzQ,4140
|
|
356
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=gzfjrYDcS0vsACq7ONGVkNA3FqVjr3e89q9fO9kokkg,4133
|
|
357
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Np7yRX9Z7Y7Z5Nutbl02wpKdZRltbt4WqlPlleiYs2E,4146
|
|
358
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=XsNfNXY8v0eatazkLCDiDclI0FnTudUGLYO01e1_4aA,4149
|
|
359
|
+
"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
|
|
360
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=arPqstZMzZjz8BNpY3alKT4vGCJyUj5I2hEeK02aq98,4152
|
|
361
|
+
"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
|
|
362
|
+
"vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=7WHPz_0fxeI3Ed0D9VIpZVoeN9RtJVVARvptfcmQu40,4146
|
|
363
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=2kWS9Qvy5Q3mvUFmbPVures5iZAriAXsy8WrtE5wu00,3727
|
|
364
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=D2dn9vXyN4FCKsZCf7VYgAWLedCx8XpPjbkQVVAvwAA,4737
|
|
365
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=5QqFljwwA8OaPlFnXy1zogl5oi6aE0OqN39xk2IUC64,3245
|
|
366
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I3k416HbXU_rYb8scD8gAI4fuBlElHl06PM347Qa11w,3253
|
|
367
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20-3e.json",sha256=CoC3pMKx0vkjI9T6rqRLTIwbDskxljTj31fCHI34B5w,3232
|
|
368
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20.json",sha256=RgV8C4F1LO09h01YsgF_eqX6GNoBtC7ulPfJRUUbg_g,3241
|
|
369
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H200.json",sha256=nsNEuDNks0tVLfQfIm7xxFwEeptTfQcoa9fJy0NS8xQ,3247
|
|
370
|
+
"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
|
|
371
|
+
"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
|
|
372
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=PflsK6VWRhwGaDKSIQ9vD7NMHcKLg3B4wENarR0aIq4,3252
|
|
373
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e.json",sha256=gkimxy2r78McckKxx4U4R3xahTI1KMH2pMOdUFOUdu8,3234
|
|
374
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20.json",sha256=vS2DRIDOqWyiBvbG6H746ownfkD1F8Aj2YZ0ET9xll8,3232
|
|
375
|
+
"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
|
|
376
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200.json",sha256=xqhl748it8GV2KXX0XixitE_ywnsKksqK8AGL7tAgT8,3254
|
|
377
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=FsWbV4Q6AzAtgegVuENBDz2ZcSJsqNiwUIVfQbpP7hQ,3244
|
|
378
|
+
"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
|
|
379
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=dPe_9-JH0wF8q7Mhec4WWSLSGRE2gj_AQT3dnR3FREI,3257
|
|
380
|
+
"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
|
|
381
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json",sha256=Nd2qn9-7yjO6vAQSHAuetP4ytysnd6UxekL8UADiLKg,3254
|
|
382
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json",sha256=10Ntu2aVD5vGLonx-jW0qNw-tgZWdZmzMGx7utDVeng,3237
|
|
383
|
+
"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
|
|
384
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200.json",sha256=JraM-Nvbg5V_TJkSl6UPFYZN1zHHoIbr2pAcksenoTY,3248
|
|
385
|
+
"vllm/model_executor/layers/fused_moe/configs/E=128,N=96,device_name=NVIDIA_H20.json",sha256=JtcHRlPz8xQEAqJ9EWI63oYvdmjQFG6VTHqtt85VOSA,3221
|
|
386
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=AMD_Instinct_MI300X.json",sha256=f3iM3xm8hGUirJ4ilAIPO6Pe9bs4sm3qaRKMswN9SKE,4731
|
|
387
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200,dtype=fp8_w8a8.json",sha256=Pux4G7sjfPL22uOJU6t35TXe-VU3OaoPA97TDj9_wZQ,3251
|
|
388
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200.json",sha256=he873aoOy7KfFg-uMoTFV4IP7Yk0Dk7mOTuLCTqwZZc,3250
|
|
389
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H100.json",sha256=Bq57MPQXuSib06u6OwiEmSzOr3XvPYoD6ohYDJaBnII,3244
|
|
390
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=pCCKkdUzzuBVtljyk7AEIAbeDf12DUiieXaODZXzm5E,3254
|
|
391
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=trX2-c4N6hTTD6zFNi6A2bT3FkhxKjkM2rPl-o1K9ss,3250
|
|
392
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=I4d56uD7E1JMXD9RAxq3FebdPquDsnNEkVaIY9Ctm9w,3246
|
|
393
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json",sha256=ypuAxMQ7JESPXLBltt68wly2wTrJzlnobhUMip6xAmc,2751
|
|
394
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=tUptlureu5QgyAEedtx5sm7CFudXAE6fIXepOb9gfas,2745
|
|
395
|
+
"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
|
|
396
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=JmXhUnhX6YOy8RsmT0zFLGyNCpRBPV2q2Db9Y9ctZeE,4144
|
|
397
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=G4PKqWxh0MlBhg7QHKj0m--_fP3Ll0gs7VJaeg-NIDM,3254
|
|
398
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=bKX9AvcxN6k-i3RUmHSchZZ3rjoYRYb4iBqhCI4L3MY,3257
|
|
399
|
+
"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
|
|
400
|
+
"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
|
|
401
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=_9HO7SaR6aQeh6vqCDpo3kjHnGJ9BVKLiMwYYgd3SmQ,2913
|
|
402
|
+
"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
|
|
403
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=Twkm9DVNxijpowfvioJ_4cKwIIlAWdyNWO9TA3gxAHs,4149
|
|
404
|
+
"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
|
|
405
|
+
"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
|
|
406
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=iySqae0zI_PRBLqV-vfSCwDS4Jxcl5QjWa2NnhndL0U,2752
|
|
407
|
+
"vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json",sha256=Uhq0SrWiCrldkWbb0ZZZhWaCZ0SsvpiNL4z30KZUN5g,2747
|
|
408
|
+
"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
|
|
409
|
+
"vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=TtDngG7ljrU5RtWZ7g-xxdBT3uEuawiKhP8EwPr97XM,3254
|
|
410
|
+
"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
|
|
411
|
+
"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
|
|
412
|
+
"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
|
|
413
|
+
"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
|
|
414
|
+
"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
|
|
415
|
+
"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
|
|
416
|
+
"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
|
|
417
|
+
"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
|
|
418
|
+
"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
|
|
419
|
+
"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
|
|
420
|
+
"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
|
|
421
|
+
"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
|
|
422
|
+
"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
|
|
423
|
+
"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
|
|
424
|
+
"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
|
|
425
|
+
"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
|
|
426
|
+
"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
|
|
427
|
+
"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
|
|
428
|
+
"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
|
|
429
|
+
"vllm/model_executor/layers/fused_moe/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=rVORXxNsxy4WmO5SJR8Sd4k7vozKqhYf50wZNCMeQzs,3239
|
|
430
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json",sha256=4UXbsSNHmrSWnD85SdRMLp4cFGRufndzJjB6hoQPclU,4736
|
|
431
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json",sha256=p6TKUp-KDeLB9E9LqThR1e7J2-ogSXPJojISdHgCxaY,4727
|
|
432
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json",sha256=gHxtmO_uvpueLVlsJgXBVE3_pS1S9EeRxNmHG_ZQszg,4729
|
|
433
|
+
"vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json",sha256=tVdpbIU1scsylx6oz3IADhkcwvZaNqw-_QVb7a6oVX8,4732
|
|
434
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=6QPLhZurIqcMVdy3w0Dd7gLViKxsyJRBz-qd8agpi6Q,3248
|
|
435
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=WPu80-OWyEJBy1hdnewLN1H1neFW8UVJrqyeDGegXc0,3250
|
|
436
|
+
"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
|
|
437
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=ozS2ECxk-Dsd4Y9DgCGGwDwJlCf5T20ANf5gnTUMuSc,3252
|
|
438
|
+
"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
|
|
439
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200.json",sha256=w18R3eHB4oUhfbcCXjHyDvp0RiDSeCrfM-VFESim2hQ,3253
|
|
440
|
+
"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
|
|
441
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=dYpKgvuG7Jji0W0zg_E9NfIojStBAdBcKd4B3nhimqk,3263
|
|
442
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200.json",sha256=CXiHlGpea5cEGmFi28Jec34uxEZITF2XldVFcJteZX0,3251
|
|
443
|
+
"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
|
|
444
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tku4-yTbIr0H5TNrm1Pq3tJJFYTXqHpdzJDSEF3bk9A,3238
|
|
445
|
+
"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
|
|
446
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200.json",sha256=bM9g-XpirsThO3Q2x8ChSx3PPtHuHRXLvVMnTWt8jLI,3243
|
|
447
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=oxOKFDrgmw1YmgxTtRa1uoe3p09ylTLrkj_jOTqNh1Q,3249
|
|
448
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json",sha256=-B6gZAEYLwMJZOnpO81pTxqs-YVKs_144Nn9BSLaMh0,3247
|
|
449
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json",sha256=GPjPHicomrS7ntHu7nnvgNXcHCoUw9vhyTUewkXpppo,3252
|
|
450
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=ObHUCUAgHTnld8Cq9Dy1n3ilmbBzyNC4jZcz6YYhMXA,3264
|
|
451
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=WegYsHl39QVlHu_4EZJSrgA4LQ5fYxSVNWFhoL6W2Rc,3251
|
|
452
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=Hrlas0Nt7d3JMr1vTpI3OVgkzxqcRziSMfFf_U5pQ58,3267
|
|
453
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200.json",sha256=J59rmqF8NQWkqmay__ahA3t3IwaPXNu5AVNLnTaDfYA,3252
|
|
454
|
+
"vllm/model_executor/layers/fused_moe/configs/E=64,N=896,device_name=NVIDIA_H20.json",sha256=GNbp4W4MBoHHN4-0sXJovY0lX6rHfZzGyKicrumupGQ,3225
|
|
455
|
+
"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
|
|
456
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json",sha256=FsIv5bqSpkWbxK2dBfg1N6tX9epZ55ZhgkJCD7hENlY,4733
|
|
457
|
+
"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
|
|
458
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json",sha256=fnO-v4YqBz0vUo0UtOTTD0n7VDG_ivczeQ1tR6Qm9f0,4734
|
|
459
|
+
"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
|
|
460
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=QaITFIJU4UsrOBXaGdPYJwTmYJ0nT9kiiqeUiZzvd1k,3270
|
|
461
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200.json",sha256=CC_jsMhXzrYne7eIOroDa0fCBKNnffiaVW2TKd4P-ek,3260
|
|
462
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=LgHbxG1kQV36zZPkJcnurHYzwAjMh04lvEHEsfzS1t0,3732
|
|
463
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json",sha256=_fcdkmWvdMqHiH8ZAGke-zXhH7qVPQx5CmKELW5hRCA,4735
|
|
464
|
+
"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
|
|
465
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json",sha256=JKYW21c0CzR0fgE5ZnYp6C1sY_tVRlm8L_lgak5V5zE,4736
|
|
466
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=yTf2R9cngSf4OafucAYlDDn4-bftaMFKaY7qhaBZPqQ,3739
|
|
467
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json",sha256=_1eVE7ok935L2V43-3D3bVNWSVaoViia19sh0VrXmXM,4735
|
|
468
|
+
"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
|
|
469
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json",sha256=18v6YruKbQ95pXPV8ocV4VdM1zNw3aZFp3WByeUkNSM,4736
|
|
470
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=AffDc0_51ML8HiA3757zbD10TZJdUsUDIYIqO4g0yUw,3250
|
|
471
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=IEYBNjt9HGnzoOVSWvL0A0jUqq926QD0_BvVYR4RA1Y,3252
|
|
472
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=Ns9Y12aZbJnFhcG3nwb67bDqqiQAo9tdTAIe8K2Ajz4,3255
|
|
473
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=uGSLFPZXK_JQ3GTDUAEiIecDor1yjbC3bJvMolF0Xl8,3267
|
|
474
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200.json",sha256=8q6ol5JQBWj6yVfzFOn7Gz5MSXTaW9javL7qQmYVOwg,3245
|
|
475
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=6jRC0oOpVpq5c1xePFKNRy-Xtmb038i4LE9N2zao2W4,3730
|
|
476
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json",sha256=cFWeyNJtEbs-Bfohgzclxo1rcYGU863oV0BzJyQ4T0w,4734
|
|
477
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=SMtsqtQeqcyy8aNwl9hPxRvx_XQdT7I3SBDNJ3OIvwY,3728
|
|
478
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.json",sha256=ZyOFJB6GUgGZsAjjT43XJwG8P-QrZ5yTvmgzQP7ThQY,4734
|
|
479
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=HOxWmCI2ifHmWc0or2y8nEen86jDeLDov1-tuMzuhxo,3256
|
|
480
|
+
"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
|
|
481
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=_5weLBinQCDzyV75hHKIT95Y0ce94KWft2_5BC6EkbQ,3254
|
|
482
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=DlatRLPaSr8HJuO50gRZ2lzXoelx55EP3SDUdgIT2v4,3269
|
|
483
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200.json",sha256=TXSOoqvi-x8H13xPqrB9qz2T3opEGA-2D0v_4n5BEG4,3259
|
|
484
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ro3drDpWAdeXH7IjMvx8wYGhIuDPOl0bpbJaIB5Msns,3732
|
|
485
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json",sha256=w_R2LL8k5jNVUARcqvSgGLvNoQiQC0Mh73ciqSIAz54,4734
|
|
486
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=hjDoTXRmEFLKhhmBFEjPowQus_z23ISonxFljql3c9k,3732
|
|
487
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json",sha256=AdOTy7ASetdAXUhNM8buoU8_rLLjcUYF0m8RGFrLWRo,4733
|
|
488
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json",sha256=Ru460ZgnUP4U8OsJfwF8n-AI-gfcolNR3_qzoxG6DtY,3254
|
|
489
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=K6BGrKw_oHTAtHjsZldcjp-BUM1dIecKXrrRn9OpRGs,3254
|
|
490
|
+
"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
|
|
491
|
+
"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
|
|
492
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=-5nkLIunjG1ghPoUEtt2AXEQw9oGiilP7K3UvQv9CqE,3252
|
|
493
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WKzddrIXo-KavpuXuouW3aLLAptu5Q4XJUb5K2PLgDM,3262
|
|
494
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200.json",sha256=ad1ZkkSyLJwRGb4Kf24qg5hW_DPmt0BXrKR85oAiV34,3257
|
|
495
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_L40S.json",sha256=qX5_yErBEwDRzhv2FvxrS3pEMa8zn0GHzLp5TUMX90g,3872
|
|
496
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=ysRCWmxV20K2BYD9XEUtxwREFGtA3QHI191vHRA0k_Q,3733
|
|
497
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json",sha256=L8VA1sfygHoyLJ-Ybfs8DP5c0YWFmMkwxHT8yJ9PEFM,4732
|
|
498
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=FJWpDLr13XF3hHiHfJykpjbLiP7Ccu2en3U6BL-QwXw,3732
|
|
499
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X.json",sha256=FnVcfzf5gXkQRt0XgsRzIQVbDPaUDOwWJX_9qOlyvRc,4731
|
|
500
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=DxYu8regZOSFu8ugFGA_QbwWK4g8xwQUZF9a_nNY4Cs,3255
|
|
501
|
+
"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
|
|
502
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=qwKy8oaMsd3QrXgQbM_x9xcfYiHK_Ou1CEwDPL5Gbgo,3259
|
|
503
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=qUifbWbE4cOKZbIHWmmLx68VRaslQX69eZHwRIQx-7I,3269
|
|
504
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200.json",sha256=JT-ZMLhAqqzSkqivOW5ATTKRlyyaFQkqQDnaPS4DE10,3262
|
|
505
|
+
"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
|
|
506
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json",sha256=EtVorGY4khTEuimlqZu0AAlPz84PH3ZkDZmVpxLtgQw,4735
|
|
507
|
+
"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
|
|
508
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json",sha256=JPdO0azlh4yUvbpC9dEHYpRT11ELEr5LXBSb5XP4E_4,4735
|
|
509
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json",sha256=BAJnXTZoewwCtzJLUPJ0oYuALv640MvDuLseGcsYaaw,3252
|
|
510
|
+
"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
|
|
511
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json",sha256=tme0ydWzIxdABZLk4tU8G_X2dJUYGGZNkQzNGcmcvUc,3261
|
|
512
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=g6Ivy4wvadaCAMJ4ZElbUU-CwyTMdbaa49M7IVQhVjk,3273
|
|
513
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200.json",sha256=GstQosPPHUn_I2DV3eMGtn3xXOw6kl1hb8L0EvRsbEU,3261
|
|
514
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json",sha256=kF4Fx0yHUmiMSLFNXT6xqAEA4AgCaHOoy_3irv4dNss,3732
|
|
515
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json",sha256=uOlVzTdJl_4VrRK4wmxIb8JKfveFZRjO9syjw_oEeL0,4732
|
|
516
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json",sha256=plnx7r9jkcYXkhvapbeeNvUg3NMGdGsIgIPSrfVy2qU,3733
|
|
517
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X.json",sha256=UC-iTgh8_dUSXRaYHOIhDH31KOiJmcfqM_Bv_UBf3ks,4733
|
|
518
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json",sha256=sY2nWMPh9lsIkhPCjkHO245wpnfFbrHmzdcZDVFPVww,3265
|
|
519
|
+
"vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json",sha256=WQLKugnKzlQ0avf1N-41lRHtG6wJ56DfVPv_nip6NBc,3273
|
|
520
|
+
vllm/model_executor/layers/fused_moe/configs/README,sha256=W2yIZkP9O8GGlg97We9BJfTtWUtPbuz5ZH3esrrjBX0,572
|
|
521
|
+
vllm/model_executor/layers/mamba/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
522
|
+
vllm/model_executor/layers/mamba/mamba2_metadata.py,sha256=nkO73Gy2bXldUCJsNMptrCwyHvIEL0cdYzNf4zCQn88,5093
|
|
523
|
+
vllm/model_executor/layers/mamba/mamba_mixer.py,sha256=8Ee4TAKRrTICZKJ83XHP56S5-WjFvwN9BNgiFBXUdpc,10210
|
|
524
|
+
vllm/model_executor/layers/mamba/mamba_mixer2.py,sha256=e5VxYPk7820cJux_HOxXskJKS2cCmHUgD-skkux_V7s,29926
|
|
525
|
+
vllm/model_executor/layers/mamba/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
526
|
+
vllm/model_executor/layers/mamba/ops/causal_conv1d.py,sha256=BF7OI_1NkflshfWnoYGD1hJ-4sjfEpm30od2EpG_HK8,4539
|
|
527
|
+
vllm/model_executor/layers/mamba/ops/mamba_ssm.py,sha256=yeQw-x6ra4uJ31osVp5naJWJcpnqlKw2Ro1XSACYq18,14247
|
|
528
|
+
vllm/model_executor/layers/mamba/ops/ssd_bmm.py,sha256=_k43ejVu7CTTVnxNNQPQ8_ByedPi9kUDirJpcD0jzhw,8640
|
|
529
|
+
vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py,sha256=HjpasgV0w53ypVrSbOhI7BbuyUhe7_wYxrW46Z0YYtg,20905
|
|
530
|
+
vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py,sha256=xzJ-nC6bIY2Ixv_HDHZVTcEgSTfdaAFvz9z7yrsiURg,25682
|
|
531
|
+
vllm/model_executor/layers/mamba/ops/ssd_combined.py,sha256=vNqBweQEvwdIEl_woyMenhdItwEAXjG1L0B8LmY89sg,9401
|
|
532
|
+
vllm/model_executor/layers/mamba/ops/ssd_state_passing.py,sha256=4jeOPs4utX_CfzkjIgZv6XUjX-wCnYtJNembsov12-o,7438
|
|
533
|
+
vllm/model_executor/layers/quantization/__init__.py,sha256=yLUNT6iH3XMWVq0_IwnIESakIQL3xrO9n_INO3minoc,5287
|
|
534
|
+
vllm/model_executor/layers/quantization/aqlm.py,sha256=4djL6YcziiKOPdzOy2ozHN7Bd0Sbro6H-RCFEvHPtJA,13777
|
|
535
|
+
vllm/model_executor/layers/quantization/auto_round.py,sha256=pE1IiSCk4ekyjAlyN4z5L5_ZSvuBAJZ4mNkZK-ODn_M,13421
|
|
536
|
+
vllm/model_executor/layers/quantization/awq.py,sha256=qIDhYxL82nIVYFZYSbulRIQFdwrKjp3oUKdbk7rPHEo,8949
|
|
537
|
+
vllm/model_executor/layers/quantization/awq_marlin.py,sha256=TyNn8etOSJx4UFQNiSBG83GJVjyyaay7p2RfqG8kDew,21605
|
|
538
|
+
vllm/model_executor/layers/quantization/awq_triton.py,sha256=SAYgtOiFmM43fsuLICbGpeJzF9Of1dc3iXIQKhczJ80,12483
|
|
539
|
+
vllm/model_executor/layers/quantization/base_config.py,sha256=Y5Alamy6edy3EYpUUukxZITy97eQkfKBdf9gg46qWuM,5771
|
|
540
|
+
vllm/model_executor/layers/quantization/bitblas.py,sha256=V262G4LywpF_QQGaDhBWpkUt0R4hlsNaDZQL-yphIHE,17587
|
|
541
|
+
vllm/model_executor/layers/quantization/bitsandbytes.py,sha256=pFFmh0Pp64ck9UMkQbc_5fv9tVD77dThJ4-k6onw25A,15321
|
|
542
|
+
vllm/model_executor/layers/quantization/deepgemm.py,sha256=MZu6U6QUB3Da2_ZPNWssLUBeg9CVylkF1dVWjrSo7lU,2297
|
|
543
|
+
vllm/model_executor/layers/quantization/deepspeedfp.py,sha256=Q_QmEjovzhMyJjWoF79-myHwOQGzaC9EMXxZm4Ljf3I,7286
|
|
544
|
+
vllm/model_executor/layers/quantization/experts_int8.py,sha256=PWgZwdRXXE4UH0y2n5-GPkRJCkM4bzKuLg6x9BMoRok,8041
|
|
545
|
+
vllm/model_executor/layers/quantization/fbgemm_fp8.py,sha256=rGi__Usa7F08TeGFt6i_ezuBC46UrXSNa4dQNmjeygA,6964
|
|
546
|
+
vllm/model_executor/layers/quantization/fp8.py,sha256=XfnDoS-BuQTbt5LlJeTJeV6muXwufmYIR1GJq-cfNW0,44299
|
|
547
|
+
vllm/model_executor/layers/quantization/gguf.py,sha256=mvlvfqdDeuNP_2LXaSBVdwLjUjzxZjaBgM6c30q3k3U,21690
|
|
548
|
+
vllm/model_executor/layers/quantization/gptq.py,sha256=J0tyDms8oZj-MIcaOHMNzKpYqZWSe7i9uZQlRPTewQA,10838
|
|
549
|
+
vllm/model_executor/layers/quantization/gptq_bitblas.py,sha256=uHw1xmiXcwtYfpSfd1Zt21Yu6diYC-qBp9tYoO7VdKw,17045
|
|
550
|
+
vllm/model_executor/layers/quantization/gptq_marlin.py,sha256=4Hdc3QtJ32zXrpjNvRAddUFaaDlMZe08ia1JnBf9Q4E,27232
|
|
551
|
+
vllm/model_executor/layers/quantization/gptq_marlin_24.py,sha256=f72YUgTT0ijIZoALWx4wn6M0L8aYpZxxKrb-cRWmZKU,11018
|
|
552
|
+
vllm/model_executor/layers/quantization/hqq_marlin.py,sha256=aXhrjhWHL8HdRffMzd2ttSLrvMZAthWXbPPXgk_Mh2Q,12912
|
|
553
|
+
vllm/model_executor/layers/quantization/ipex_quant.py,sha256=H0SmYwF0mbhZOl11st0TPruEtFaTtIt5haKrnV67EKo,9842
|
|
554
|
+
vllm/model_executor/layers/quantization/kv_cache.py,sha256=8e7uCDHW4rPO27FvzNeN5yk46jNSXgRse8lCzYQkTgM,6226
|
|
555
|
+
vllm/model_executor/layers/quantization/marlin.py,sha256=v_d8u15OdkX6qAgewRtn9d6ZrpeODjfomjwpEKBaAUA,9755
|
|
556
|
+
vllm/model_executor/layers/quantization/modelopt.py,sha256=VQSs4DN1xOSSQ8iCeFDfzvNlmuwufHDfY6jzzf1aW8E,31587
|
|
557
|
+
vllm/model_executor/layers/quantization/moe_wna16.py,sha256=ChL8C9NBTHXlobP9AbbjZKIMWzNNL5wGoSvv__BfB-4,20188
|
|
558
|
+
vllm/model_executor/layers/quantization/neuron_quant.py,sha256=j7px2wDFac330ezDhUxvu6reYcQPRHTHkqHHUwCOdOk,2730
|
|
559
|
+
vllm/model_executor/layers/quantization/ptpc_fp8.py,sha256=UZ7eQtNb0YiXwuVFUSSemq1Xpp0e-Qc3Q_abIW-BOMI,5351
|
|
560
|
+
vllm/model_executor/layers/quantization/qqq.py,sha256=b_Ar5gW6hUXaugMmj4X3Ajzi9k4QchpVeZELNtSaWXU,10083
|
|
561
|
+
vllm/model_executor/layers/quantization/rtn.py,sha256=BDNb2eUyalJRpRPZbQXPB6-6ZQCAshOIlsPV5n9UFGY,9905
|
|
562
|
+
vllm/model_executor/layers/quantization/schema.py,sha256=x7y16hNaValmG7etgyK0RwpeBCPapT1_GznqWBQ5kGg,3749
|
|
563
|
+
vllm/model_executor/layers/quantization/torchao.py,sha256=59vGg-P3WaTLcrizcLFIbUxr00nSrBAlc0c5Cn4gkEs,7541
|
|
564
|
+
vllm/model_executor/layers/quantization/tpu_int8.py,sha256=NJ4oRWVCxebWqG8vztU22_ntye7te_Nk6YK1z4gh0ms,4581
|
|
565
|
+
vllm/model_executor/layers/quantization/compressed_tensors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
566
|
+
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py,sha256=QbWt8IIY5O3Ib876NAxAB72V8-5x7sisFjZwpFcMfsQ,30469
|
|
567
|
+
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py,sha256=euIWvfAgzkv8hSj2BDpqHZhjtqjK7jdO5Lw1e5i5ddI,70725
|
|
568
|
+
vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py,sha256=nbbIQHQ0e7RzGJKHz6j4BeHtV_pFO5ewl1_jjaI9zRo,7851
|
|
569
|
+
vllm/model_executor/layers/quantization/compressed_tensors/utils.py,sha256=QIonPI7CuMCJwRYgajuT1ohv6t4zk9-Q165TRe6b53w,7859
|
|
570
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py,sha256=sqmMJiVttpUjs-SmJrk3jO4VKsNe5dpmf_aKxWBZeU4,1199
|
|
571
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py,sha256=R1W0Q4pEe_WUjR31fTU1bfhPwaA6eiJzpoJBULBQod4,14115
|
|
572
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py,sha256=phymTDNBBnHfLXhq9vmwklinzKDZKdYrfp59en2VOok,1596
|
|
573
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py,sha256=002voQj76mVNI3xF3d3IDmI5LM3-_eGXs7VJOarOWuU,6270
|
|
574
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py,sha256=Lgr2COqF2sCxUTnwlBu-P9J9N01aNlf0fqFL8y_d3U0,4649
|
|
575
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py,sha256=33WkRc5CHwYDIQxWtLECE6PTm9UqzDg1x07zMX7Uo9Y,6278
|
|
576
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py,sha256=Z1-7Bh_1qTwnKkbbj2xO1zn19O76iU-uLWRZwdH08QA,5491
|
|
577
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py,sha256=pgtg07yokeUP3Cu_CwDrn8fyqPsq1FXWfv79-ADAWR4,6506
|
|
578
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py,sha256=TpqBbRB2j5Jbvo4Gczvjy4vqlIEP-j8fljl_nQ66UtI,4930
|
|
579
|
+
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py,sha256=tmixOaeebRl-bVTUwRwZMlqr-vhBXE6BeixzhzAqCdg,8541
|
|
580
|
+
vllm/model_executor/layers/quantization/kernels/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
581
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py,sha256=n6clH1JvR3UZ6TPUKIj4xmnRRliIMaOgM4PM50BrRPs,2941
|
|
582
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py,sha256=i847I8VXbTiXeV2YD_QpkUjQFJLP20UlSDNeErWg6ng,3205
|
|
583
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py,sha256=feWdTXJ4hDpJjQEIQhabjfyZs56JVY-uza8UD81i5MA,4444
|
|
584
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py,sha256=RUeSb5-gb5wsEUy0-1WfgD3g6qCOjRVBONNXKOrC9dw,12036
|
|
585
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py,sha256=rKbWF_TyxXjbkm_a28tge9GhOowg121HECmWJIIAm-o,6213
|
|
586
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py,sha256=SVPOfVZht3qCqq3dKsgGVAabZk0EhU_y8gWCmoyY2V4,5736
|
|
587
|
+
vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py,sha256=L4TpdojuurExORWS-aaPv2gcGFN4yNR0c9XXc0N8WGw,5760
|
|
588
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py,sha256=0cL2WbqxsGFMJMlg4AgAt5_EDOncrIB2z3vlg6FoOk8,2108
|
|
589
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py,sha256=4n01vds_ytbnGQ5jFtEJekgSbum5aZzyT39uwE2bGc4,3507
|
|
590
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py,sha256=EJiwelJCPuryD3f4wYJed52ebxWsGTdGcfTJkD-9O1w,4884
|
|
591
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py,sha256=wc9MAgmQFFcg0_wqGRIeXrdAO-_78MoaKfEvqT6odFw,6064
|
|
592
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py,sha256=CgQydI5ERFdaOzOJNR5SPTYIkAUDI-pWr8BqydEB46A,1345
|
|
593
|
+
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py,sha256=KxcEOM3PQnLXqvSRIxb6UnGNZlbuE5qrkGY_cdARgfU,4365
|
|
594
|
+
vllm/model_executor/layers/quantization/quark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
595
|
+
vllm/model_executor/layers/quantization/quark/quark.py,sha256=hNhmj3NsW2c_aMz1PAREMGpEdcRrpatZns8xN-G-n0Y,18727
|
|
596
|
+
vllm/model_executor/layers/quantization/quark/quark_moe.py,sha256=XcCP7Y3mYKrALJwdiA_HiXWBT8cDfNy--x-wJhqtogw,11198
|
|
597
|
+
vllm/model_executor/layers/quantization/quark/utils.py,sha256=Y1MHt_RTfPOCSb7_kQHK2CQZCaQvG1A6mMA9s70vbDQ,3658
|
|
598
|
+
vllm/model_executor/layers/quantization/quark/schemes/__init__.py,sha256=TvlHrwGTaJp9nBDtUl4n5xtuuPCR18XQVyYGa11AdMM,353
|
|
599
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py,sha256=YkvgTw1sECoubOhGXMixFd47StURg3bzGiYsur_izzg,1560
|
|
600
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w4a4_mxfp4.py,sha256=LXtP0CTKNOMD8v_7r7VxN-m9W71Ngrqtptwl2bh7Egg,4729
|
|
601
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py,sha256=1TPKJjwTpRCTnhvVBdxHFNBhwVgUdizI9HCz_gfCDE0,6957
|
|
602
|
+
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py,sha256=TAZaMWM1lydY9bxKj-mdzRbMcUhSVTIPXvUmt8vll0I,5462
|
|
603
|
+
vllm/model_executor/layers/quantization/utils/__init__.py,sha256=k9dh5aEvZi-6ECfjG_Jq2iijwEfjmdRA9fcHjG9uKd8,235
|
|
604
|
+
vllm/model_executor/layers/quantization/utils/allspark_utils.py,sha256=ejjOMJ4V0UhgYiSvYJf5_x6zJA5iQkAYtzLqaw2AuXE,2260
|
|
605
|
+
vllm/model_executor/layers/quantization/utils/bitblas_utils.py,sha256=BGT0qmMJi66O1PX2HS2nd7bApVpLNm5cJIYqUqsr_5g,8213
|
|
606
|
+
vllm/model_executor/layers/quantization/utils/fp8_utils.py,sha256=30cM0FR42WkHO-d-J88TA74MJVn9-ISSjC5AzrFS_k0,21384
|
|
607
|
+
vllm/model_executor/layers/quantization/utils/gptq_utils.py,sha256=e49tTqau8qyu95QN4vLXH-UGA-JU6dtpTY6IYPWa1TU,3874
|
|
608
|
+
vllm/model_executor/layers/quantization/utils/int8_utils.py,sha256=NkBqRLleVM-ZmIEF0P6aaWRaDS_L_i5gsZgtOsn9z_M,15114
|
|
609
|
+
vllm/model_executor/layers/quantization/utils/layer_utils.py,sha256=KwNOkW1XYBIOjb8UJgyEKd6T_chNqE_YVskWMtrOmyo,1631
|
|
610
|
+
vllm/model_executor/layers/quantization/utils/machete_utils.py,sha256=1lvRUPFOjZj_wNl5XMTxntf_sM_J1KS-8WFj4vFxeRQ,1658
|
|
611
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils.py,sha256=KCrE0m7TRSFKYvAx_qdq_k9ToNCy8oTuUvf0JOtF3RE,19007
|
|
612
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py,sha256=mlHZqTXRV0aO5TYqywOnYZUh26FOM01buE3s6oKHh6U,11235
|
|
613
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py,sha256=UBXQyCa52ixKbH_kMJZnktbARcmsVy86O8lXuByKkLE,13152
|
|
614
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test.py,sha256=GtmzVpQhQCQ8-ajEADNfzUhZW_Ph0GWs0VoSx8QJJ-o,5374
|
|
615
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py,sha256=3_204vZjqNj1Em7VxymB0CfK3TpoHpaS0xY0p29WyDY,17603
|
|
616
|
+
vllm/model_executor/layers/quantization/utils/marlin_utils_test_qqq.py,sha256=zbQaHDmhnWSrZUBLPsT4ZQgIwytQUTwD23DWaSYH_RQ,4145
|
|
617
|
+
vllm/model_executor/layers/quantization/utils/mxfp4_utils.py,sha256=xC1klknQQztk1wVla1y2MNHqU-0V0p8GnfPyyD4d1jo,1645
|
|
618
|
+
vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py,sha256=pePebcH0dtAfnrmKK58bybC0MUNFhAa5DCi2z3jLDeg,5266
|
|
619
|
+
vllm/model_executor/layers/quantization/utils/quant_utils.py,sha256=sn5_s-X8ijBsqrT4n-yXK8PPr_OqBkNPFIb3APHVBJU,19541
|
|
620
|
+
vllm/model_executor/layers/quantization/utils/w8a8_utils.py,sha256=TaE_0zKzrIQZT-r72ZrH5qyo-7yLuL9zHp1j3zKXEWY,16766
|
|
621
|
+
"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
|
|
622
|
+
"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
|
|
623
|
+
"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
|
|
624
|
+
"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
|
|
625
|
+
"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
|
|
626
|
+
"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
|
|
627
|
+
"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
|
|
628
|
+
"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
|
|
629
|
+
"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
|
|
630
|
+
"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
|
|
631
|
+
"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
|
|
632
|
+
"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
|
|
633
|
+
"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
|
|
634
|
+
"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
|
|
635
|
+
"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
|
|
636
|
+
"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
|
|
637
|
+
"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
|
|
638
|
+
"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
|
|
639
|
+
"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
|
|
640
|
+
"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
|
|
641
|
+
"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
|
|
642
|
+
"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
|
|
643
|
+
"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
|
|
644
|
+
"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
|
|
645
|
+
"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
|
|
646
|
+
"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
|
|
647
|
+
"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
|
|
648
|
+
"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
|
|
649
|
+
"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
|
|
650
|
+
"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
|
|
651
|
+
"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
|
|
652
|
+
"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
|
|
653
|
+
"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
|
|
654
|
+
"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
|
|
655
|
+
"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
|
|
656
|
+
"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
|
|
657
|
+
"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
|
|
658
|
+
"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
|
|
659
|
+
"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
|
|
660
|
+
"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
|
|
661
|
+
"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
|
|
662
|
+
"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
|
|
663
|
+
"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
|
|
664
|
+
"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
|
|
665
|
+
"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
|
|
666
|
+
"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
|
|
667
|
+
"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
|
|
668
|
+
"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
|
|
669
|
+
"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
|
|
670
|
+
"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
|
|
671
|
+
"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
|
|
672
|
+
"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
|
|
673
|
+
"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
|
|
674
|
+
"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
|
|
675
|
+
"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
|
|
676
|
+
"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
|
|
677
|
+
"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
|
|
678
|
+
"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
|
|
679
|
+
"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
|
|
680
|
+
"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
|
|
681
|
+
"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
|
|
682
|
+
"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
|
|
683
|
+
"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
|
|
684
|
+
"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
|
|
685
|
+
"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
|
|
686
|
+
"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
|
|
687
|
+
"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
|
|
688
|
+
"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
|
|
689
|
+
"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
|
|
690
|
+
"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
|
|
691
|
+
"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
|
|
692
|
+
"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
|
|
693
|
+
"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
|
|
694
|
+
"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
|
|
695
|
+
"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
|
|
696
|
+
"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
|
|
697
|
+
"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
|
|
698
|
+
"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
|
|
699
|
+
"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
|
|
700
|
+
"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
|
|
701
|
+
"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
|
|
702
|
+
"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
|
|
703
|
+
"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
|
|
704
|
+
"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
|
|
705
|
+
"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
|
|
706
|
+
"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
|
|
707
|
+
"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
|
|
708
|
+
"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
|
|
709
|
+
"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
|
|
710
|
+
"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
|
|
711
|
+
"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
|
|
712
|
+
"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
|
|
713
|
+
"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
|
|
714
|
+
"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
|
|
715
|
+
"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
|
|
716
|
+
"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
|
|
717
|
+
"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
|
|
718
|
+
"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
|
|
719
|
+
"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
|
|
720
|
+
"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
|
|
721
|
+
"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
|
|
722
|
+
"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
|
|
723
|
+
"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
|
|
724
|
+
"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
|
|
725
|
+
"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
|
|
726
|
+
"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
|
|
727
|
+
"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
|
|
728
|
+
"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
|
|
729
|
+
"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
|
|
730
|
+
"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
|
|
731
|
+
"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
|
|
732
|
+
"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
|
|
733
|
+
"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
|
|
734
|
+
"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
|
|
735
|
+
"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
|
|
736
|
+
"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
|
|
737
|
+
"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
|
|
738
|
+
"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
|
|
739
|
+
"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
|
|
740
|
+
"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
|
|
741
|
+
"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
|
|
742
|
+
"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
|
|
743
|
+
"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
|
|
744
|
+
"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
|
|
745
|
+
"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
|
|
746
|
+
"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
|
|
747
|
+
"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
|
|
748
|
+
"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
|
|
749
|
+
"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
|
|
750
|
+
"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
|
|
751
|
+
"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
|
|
752
|
+
"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
|
|
753
|
+
"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
|
|
754
|
+
"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
|
|
755
|
+
"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
|
|
756
|
+
"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
|
|
757
|
+
"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
|
|
758
|
+
"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
|
|
759
|
+
"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
|
|
760
|
+
"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
|
|
761
|
+
"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
|
|
762
|
+
"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
|
|
763
|
+
"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
|
|
764
|
+
"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
|
|
765
|
+
"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
|
|
766
|
+
"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
|
|
767
|
+
"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
|
|
768
|
+
"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
|
|
769
|
+
"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
|
|
770
|
+
"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
|
|
771
|
+
"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
|
|
772
|
+
"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
|
|
773
|
+
"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
|
|
774
|
+
"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
|
|
775
|
+
"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
|
|
776
|
+
"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
|
|
777
|
+
"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
|
|
778
|
+
"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
|
|
779
|
+
"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
|
|
780
|
+
"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
|
|
781
|
+
"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
|
|
782
|
+
"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
|
|
783
|
+
"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
|
|
784
|
+
"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
|
|
785
|
+
"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
|
|
786
|
+
"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
|
|
787
|
+
"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
|
|
788
|
+
"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
|
|
789
|
+
"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
|
|
790
|
+
"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
|
|
791
|
+
"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
|
|
792
|
+
"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
|
|
793
|
+
"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
|
|
794
|
+
"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
|
|
795
|
+
"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
|
|
796
|
+
"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
|
|
797
|
+
"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
|
|
798
|
+
"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
|
|
799
|
+
"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
|
|
800
|
+
"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
|
|
801
|
+
"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
|
|
802
|
+
"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
|
|
803
|
+
"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
|
|
804
|
+
"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
|
|
805
|
+
"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
|
|
806
|
+
"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
|
|
807
|
+
"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
|
|
808
|
+
"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
|
|
809
|
+
"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
|
|
810
|
+
"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
|
|
811
|
+
"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
|
|
812
|
+
"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
|
|
813
|
+
"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
|
|
814
|
+
"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
|
|
815
|
+
"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
|
|
816
|
+
"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
|
|
817
|
+
"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
|
|
818
|
+
"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
|
|
819
|
+
"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
|
|
820
|
+
"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
|
|
821
|
+
"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
|
|
822
|
+
"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
|
|
823
|
+
vllm/model_executor/model_loader/__init__.py,sha256=x6IQi3rPANOtWtMjFqffOEGCBJUddmWxsS3XXCsG75s,2792
|
|
824
|
+
vllm/model_executor/model_loader/base_loader.py,sha256=I6Q-W48VimC49Chd6FJSm4kIWoLe7bGDoF5wy37SuBI,1743
|
|
825
|
+
vllm/model_executor/model_loader/bitsandbytes_loader.py,sha256=hU3LQdsvRKUdbBXzQ2H3k24m9N872rXRCp6PI3urjF0,27652
|
|
826
|
+
vllm/model_executor/model_loader/default_loader.py,sha256=heCRhupa4ANn7ssMBOY6unTVIF_HCA-FdWcfDVp0kcU,11409
|
|
827
|
+
vllm/model_executor/model_loader/dummy_loader.py,sha256=QHjsazcUyw6aMTI4wocgtFzDylK6rDT0paw733iOE5A,1098
|
|
828
|
+
vllm/model_executor/model_loader/gguf_loader.py,sha256=uApRTt0Mb9WSaLQp3_kTJmlEUbSIzJMUbCGV9zeqkv4,5490
|
|
829
|
+
vllm/model_executor/model_loader/neuron.py,sha256=S7924o11-QrnIixME0vuyq-yTqqeReKNVkJNIQpDBUk,19869
|
|
830
|
+
vllm/model_executor/model_loader/neuronx_distributed.py,sha256=FaWp1IGJas7zTsh8U-3842Ylmth_DU51QEPXjJrWPGs,31285
|
|
831
|
+
vllm/model_executor/model_loader/runai_streamer_loader.py,sha256=gQg_bRxKOZFOLf7eG24wTp21M_jMLJlzH9hsmZeL5Pw,4415
|
|
832
|
+
vllm/model_executor/model_loader/sharded_state_loader.py,sha256=N4uH8NgaKX7TDatrOLnx3CK5hCmTSiofeZRhY7xn72A,8064
|
|
833
|
+
vllm/model_executor/model_loader/tensorizer.py,sha256=UsNEfABbMfvAOyrFqzKayE4x6fRwgkilywUFw_c5-jg,24333
|
|
834
|
+
vllm/model_executor/model_loader/tensorizer_loader.py,sha256=fgrnQ8SSnbldReO7iC0AtUfbRuluJdUisvKTPpTipic,5377
|
|
835
|
+
vllm/model_executor/model_loader/tpu.py,sha256=vHA2cFpc-SLO7EhX-_v2f9B_9Ir6U14lyV0rvKCYyfs,4789
|
|
836
|
+
vllm/model_executor/model_loader/utils.py,sha256=CLchyCUHvF5xZC0ucua62Tls_iGbqxmg7YuLRFAbRco,13602
|
|
837
|
+
vllm/model_executor/model_loader/weight_utils.py,sha256=VsZgTiLHzh_tIZnQUe6r8orJd8WUnNdvH6yiz6AsIsU,29950
|
|
838
|
+
vllm/model_executor/models/__init__.py,sha256=rO5tFElw7pqtnqzv4kPGR-4I2x_J0MvxMYhnwWlfjTw,1038
|
|
839
|
+
vllm/model_executor/models/adapters.py,sha256=2f98fGv6eVlSLBoQSclRUCpTh9ZgsJHJ9vDzICkRb9s,13280
|
|
840
|
+
vllm/model_executor/models/aimv2.py,sha256=fzq5a8XtmAmoEHnQT0kEqJRb5XX0gXR1E8bANLy3YOc,8661
|
|
841
|
+
vllm/model_executor/models/arctic.py,sha256=PMmXq8JXcLb8gNuwH9I7X4EwC4CvTYY5k5bCIqw2KUo,24472
|
|
842
|
+
vllm/model_executor/models/aria.py,sha256=usVdfF4hk7Vn7hFSwqTn_7L42cXdKSusUtgSoXYbL18,26256
|
|
843
|
+
vllm/model_executor/models/aya_vision.py,sha256=QlXfau1rJIKVtlDqY99u2Ckkc7tMIqdrqAo__GbV2aA,19763
|
|
844
|
+
vllm/model_executor/models/baichuan.py,sha256=fW0K7dHjYAzHMDFK83-DiwGk4VOMnlit_wXRkb4EMfk,18950
|
|
845
|
+
vllm/model_executor/models/bamba.py,sha256=5IA2P_bWegKozs1VRcvggncL4aKrwwHcMO4EOvIbQzA,21865
|
|
846
|
+
vllm/model_executor/models/bart.py,sha256=YBWWU4aL0nOKA0tVHqItdGi3z2piEDg9FYoOZ0std6U,33889
|
|
847
|
+
vllm/model_executor/models/bert.py,sha256=S0yufylDEpcbrMVZ07KqLrQmjnVE_0KrkSAjZe9HDrk,20258
|
|
848
|
+
vllm/model_executor/models/bert_with_rope.py,sha256=Df2rTNEVl1FTpgH164iGG8wD4BaFH32pMsySxPWl_Ak,24120
|
|
849
|
+
vllm/model_executor/models/blip.py,sha256=E0Qw2SGxfBPBttkLIqhuIZTmwkS6tAy2-9R48mc3NYM,12402
|
|
850
|
+
vllm/model_executor/models/blip2.py,sha256=5LybGe94KcfrfeGYY5Tl1aoda5f83IP-UmWDrLK03xQ,26281
|
|
851
|
+
vllm/model_executor/models/bloom.py,sha256=JpU-c7z6HdjADppHa57wNyNcRG33Q7HEOo8yYnTaIaI,14523
|
|
852
|
+
vllm/model_executor/models/chameleon.py,sha256=vp86k-AkhLWYi_GdnX9nsKEQS56AosuXH8cswvyttSI,45783
|
|
853
|
+
vllm/model_executor/models/chatglm.py,sha256=yqtyEDROvPTfBJHoIFjO5ytOzujyeZnJtfR_NiC6s-U,18460
|
|
854
|
+
vllm/model_executor/models/clip.py,sha256=rrt1JfGp1KSVWV9ioWgIks6wZEw_WT2HKvGRuf0T0lY,14924
|
|
855
|
+
vllm/model_executor/models/commandr.py,sha256=WZTQShOkVVNpoAnNNYrewQt9zzbVqYX_3q11xegQ9hI,19386
|
|
856
|
+
vllm/model_executor/models/config.py,sha256=Kteoe79o8sYR8HGhZhfFnItCzZWGLuMCeA9xnmYYB40,8052
|
|
857
|
+
vllm/model_executor/models/constant_size_cache.py,sha256=O7tfU9CrkKNIHVc8FIPP4IGOn_naP5Q8r-IagakUYzE,5908
|
|
858
|
+
vllm/model_executor/models/dbrx.py,sha256=u_ITrs1XlLjd0q_p-ohcEBrKRdvq_i6HMfq6wEHyeHg,18433
|
|
859
|
+
vllm/model_executor/models/deepseek.py,sha256=s9WL-LoXexUURKjvwOB9FRYKgoNBmetF378CJu9cV6c,19869
|
|
860
|
+
vllm/model_executor/models/deepseek_mtp.py,sha256=-h8bb797-aP3CE79Oksp-MRlA4UO9BCgoam8OdoUFW4,11731
|
|
861
|
+
vllm/model_executor/models/deepseek_v2.py,sha256=2J7EhkZRq15QJKKRAkySejhWiEKfAfi6MdL1KokPhqo,39635
|
|
862
|
+
vllm/model_executor/models/deepseek_vl2.py,sha256=GHtE9t5g54Zc3ioKTzfAtJ_jv8C3tW4kKKlsznfooos,25724
|
|
863
|
+
vllm/model_executor/models/dots1.py,sha256=_1bn7qCIEjyzihfTMg3uqTw-9yM5Vs4sXQKi4UhU6Ew,21679
|
|
864
|
+
vllm/model_executor/models/eagle.py,sha256=WjztGAtIwBuyltc0OjZ_YyM0htko912C6h0-y8-wlwo,11804
|
|
865
|
+
vllm/model_executor/models/ernie45.py,sha256=6feTp5gJbG5-JL6N4kq6s0WL8KojDy8HrAe6yPYNfzs,1972
|
|
866
|
+
vllm/model_executor/models/ernie45_moe.py,sha256=KNU7ZmgA2LAjpVXQZyF1ARb2OsAUri1QZh3h14SMg4k,23347
|
|
867
|
+
vllm/model_executor/models/exaone.py,sha256=eW-1d3aj-VNOPFQARNxzq3IYCAobAHgwlourzeUiSFc,21157
|
|
868
|
+
vllm/model_executor/models/fairseq2_llama.py,sha256=62IX9r3OrOKXD-TiNJRx_mI_TMLyqUOvmQxk8aoUZ-g,6555
|
|
869
|
+
vllm/model_executor/models/falcon.py,sha256=rjS9x_rMHNfwdXj-_xZf4FGPc7XorREripli3MRdra8,21383
|
|
870
|
+
vllm/model_executor/models/falcon_h1.py,sha256=OB_H2EHE94pyurn_1J-5iEbAV2DzqSIvog07z6LzzuI,27573
|
|
871
|
+
vllm/model_executor/models/florence2.py,sha256=olJbxtTL7VP7M-sNE-y6GzRacYzmls68LKbVOmGwkts,39645
|
|
872
|
+
vllm/model_executor/models/fuyu.py,sha256=Vlc47P_8xc2bEs_FIXoifGJ94SCzYnN-7ilstWXhQlo,14926
|
|
873
|
+
vllm/model_executor/models/gemma.py,sha256=oDw6BJDBepxkd71skB3pX2FRR9GCiazIsBqfcT5cuTo,16384
|
|
874
|
+
vllm/model_executor/models/gemma2.py,sha256=9AN-NnXW1QhvFl9g7kLI4vV_3pqGtwiclKyK6ZfTkb0,17615
|
|
875
|
+
vllm/model_executor/models/gemma3.py,sha256=yH5K1NIyTx5mQMWxESQqlDx5QOPoeoTKnK0ocb7Xic4,21826
|
|
876
|
+
vllm/model_executor/models/gemma3_mm.py,sha256=1PmKJaDhvkF4O64-0LzFK0dBoqKv2gmEYfAFk1Fk6P8,26497
|
|
877
|
+
vllm/model_executor/models/gemma3n.py,sha256=ZtqYZvR4MZNIkWMLeGgMfdJMcHdmXIQRUvYJNkEqRdw,32792
|
|
878
|
+
vllm/model_executor/models/glm.py,sha256=d2mDle-FA4NVjt8bVZwYQm1ddtp75b8Ji-1aVlYKb28,1059
|
|
879
|
+
vllm/model_executor/models/glm4.py,sha256=J_NOzM6avf9dNJjJkA6XnKaXblh-xEaynmLvPrcShNg,11864
|
|
880
|
+
vllm/model_executor/models/glm4_1v.py,sha256=4kGkPYmlQXDXZ20cQ5Pkdh34KTFZoV_k8sG9ToZ1Wwo,60964
|
|
881
|
+
vllm/model_executor/models/glm4v.py,sha256=l7lcInk2Rvf_nqFMtx_eWRDybcbzdLn7D4f6t6cmNKg,22549
|
|
882
|
+
vllm/model_executor/models/gpt2.py,sha256=JAVyxKRx4F4itOa6t9nnwAfh49PZNa541VBGE8mbN4Y,14951
|
|
883
|
+
vllm/model_executor/models/gpt_bigcode.py,sha256=Z8KWyYGY0to0iizR05TsVSXezYAezcJzT1wHj-9MNDk,13179
|
|
884
|
+
vllm/model_executor/models/gpt_j.py,sha256=DXwkPWHvcyfYANh_q9cD4hsF6oDDrB41Qbznupbw2ew,13248
|
|
885
|
+
vllm/model_executor/models/gpt_neox.py,sha256=U4Qta239p3CHLT4haOgzh-ZijHTf1XBS5gfYHcWHi18,13387
|
|
886
|
+
vllm/model_executor/models/granite.py,sha256=0LHRQCxu_4SaKhqb4CRZ1h7saWbjj9MVpoOoLXzQ9zY,20125
|
|
887
|
+
vllm/model_executor/models/granite_speech.py,sha256=qVvk5_ualIZcGpS3wEa-ytEMdlVemGos8E8BBbNpzLc,31682
|
|
888
|
+
vllm/model_executor/models/granitemoe.py,sha256=xEo_FLUnplEBWQzwzOSlmXeB-7aKrjZsqkgQP-JHzmA,17976
|
|
889
|
+
vllm/model_executor/models/granitemoehybrid.py,sha256=nnqW7tLoCsXC-qgTj6hZKZ3azXMwp5YL2XGFysYg1HE,27193
|
|
890
|
+
vllm/model_executor/models/granitemoeshared.py,sha256=aOMNA3QROPISeXBLYNLp9zxVTLcDHeI9mzgA3Wj-Mqg,13763
|
|
891
|
+
vllm/model_executor/models/gritlm.py,sha256=JeCdwTJLg_VHJX0YDDA1msgjDZGA7Ow6O1i6YTyIoek,8165
|
|
892
|
+
vllm/model_executor/models/grok1.py,sha256=htPR-OsKJVdor9c3iwsWcLwZM8wyt9TfZTB2yQeyzRQ,22507
|
|
893
|
+
vllm/model_executor/models/h2ovl.py,sha256=PupWx1vJuixEx2pfRZwK_o4SjPkx6SGj67X7AzXBp8g,18506
|
|
894
|
+
vllm/model_executor/models/hunyuan_v1_moe.py,sha256=6yv-BudfkTsU-fepnA_U-VdbEIlgftPoOo_Y7YfjOV4,35588
|
|
895
|
+
vllm/model_executor/models/idefics2_vision_model.py,sha256=kIJ7fIH6EqRDz9zyb8aybH28CCntgRODy0Sc-VNi3io,15032
|
|
896
|
+
vllm/model_executor/models/idefics3.py,sha256=MrYZkast2H3WmhFV5c_VDGuuuMkHk_Qrrnhn97gYzMY,28422
|
|
897
|
+
vllm/model_executor/models/interfaces.py,sha256=z-eXeNYPHvxfOJNW5I7FJx_2G77WasUP9Eb4GryeC6g,19992
|
|
898
|
+
vllm/model_executor/models/interfaces_base.py,sha256=JzOV3tbmnDd7T9ioD-0QhhPfwsTpJYGthSUUov-hfDg,4432
|
|
899
|
+
vllm/model_executor/models/intern_vit.py,sha256=moNji6HTfcM01A74d4g9m5ZUumuMnvxgWnhpse7bh5k,17312
|
|
900
|
+
vllm/model_executor/models/internlm2.py,sha256=zqG49lANNdrA8QdVl6ufUA0ibCQJMDt9UBK4Y7GCycM,17258
|
|
901
|
+
vllm/model_executor/models/internlm2_ve.py,sha256=PBc0lISli_zQWI1KUPFaYGiU0MMqjjB0i48DbjayVrQ,5801
|
|
902
|
+
vllm/model_executor/models/internvl.py,sha256=aWku87n60ERgG6uT2YbRh8v29_MkxIPo9DgHrIlAz8o,52040
|
|
903
|
+
vllm/model_executor/models/jais.py,sha256=g5_UOoxXLe77ynXWP9yiqa40Nvz_bhK6buqdfEubhP0,14615
|
|
904
|
+
vllm/model_executor/models/jamba.py,sha256=jf-HS6Qd2UUZu61dG450kub4Xi3pUMGA4X-EzbrVPEU,24339
|
|
905
|
+
vllm/model_executor/models/keye.py,sha256=yhbMMpDufKG-5xrbtu0JnKAcAySZ7RQ2x-C-bSWQNis,62916
|
|
906
|
+
vllm/model_executor/models/kimi_vl.py,sha256=ik6D2bKDewjxVHRGPe-kdCIN9XfUp6hR5msKmAArkfE,24766
|
|
907
|
+
vllm/model_executor/models/llama.py,sha256=9F2-D-X6iV4E0Zqly9e4gfi4bf8awz0IKY-9E4-xU7g,25953
|
|
908
|
+
vllm/model_executor/models/llama4.py,sha256=o2DrZ8ZMutmppRRh4hXMh8S9w-b9lpO-B5NGdhr8emM,21815
|
|
909
|
+
vllm/model_executor/models/llama_eagle.py,sha256=iwQuxwCvJmkwvgTm0Vda-m5tsMDO7QB92O_rXrEIPT0,5889
|
|
910
|
+
vllm/model_executor/models/llama_eagle3.py,sha256=HDljQQQMno0w4fQrMRuCP2DvQGmjDaF1Yj6udggDtj0,9499
|
|
911
|
+
vllm/model_executor/models/llava.py,sha256=gn4SDNSqd8T7aLgCHA-hAxA6HrkZYZ6HPWRQVm2Uce0,33217
|
|
912
|
+
vllm/model_executor/models/llava_next.py,sha256=fLhKxWNmpkqVH1TwFtKBqU4IKyZloZ0ddTIeTII8HKI,24582
|
|
913
|
+
vllm/model_executor/models/llava_next_video.py,sha256=4oXojLAWRfHdMlVKcs90OMyb8sn-ZSlynMezX_h0M28,18546
|
|
914
|
+
vllm/model_executor/models/llava_onevision.py,sha256=IV-ZYTf3pmZ-J67_ft0EdObytBQ_sV-q5wwp-mc3flI,38206
|
|
915
|
+
vllm/model_executor/models/mamba.py,sha256=w_gqekW_61yAvd4pTPkQk8ULH1XmgF7uuZWkm2Uh61A,11648
|
|
916
|
+
vllm/model_executor/models/mamba2.py,sha256=Iz1XT2eW9huv5Q6FmnBcy5ZBatayUymd16Sug2aNNls,13153
|
|
917
|
+
vllm/model_executor/models/mamba_cache.py,sha256=jeDF4fTtFfhHEFiLqa2nrbOjg11_KS7qVqz5Jp8cMMM,2967
|
|
918
|
+
vllm/model_executor/models/medusa.py,sha256=iR59lwoGI-KtA_rh0O7ABUJiDOWocdbdrAbND6qmqVY,9003
|
|
919
|
+
vllm/model_executor/models/mimo.py,sha256=HhJVShVhvEuyxCTuqQUPUX4tmfbNB2X97CrLLKVUSuY,7916
|
|
920
|
+
vllm/model_executor/models/mimo_mtp.py,sha256=0l_36yBG6UgRiCsQrmV6P3McyeYS6W0XwOkTJFIaPtE,11445
|
|
921
|
+
vllm/model_executor/models/minicpm.py,sha256=HPi3QK4F96zXHH8bwysx83Tq7agKz8-2NcffeTd6S3c,23905
|
|
922
|
+
vllm/model_executor/models/minicpm3.py,sha256=3gR9YhnAHhgoi9hfQupHmNhhAt--aeyMDMerp7sncuw,9429
|
|
923
|
+
vllm/model_executor/models/minicpm_eagle.py,sha256=qOHJH4raDUbtTJYiOWpAUBfYo3dUow4ImkdZfx6K88w,15901
|
|
924
|
+
vllm/model_executor/models/minicpmo.py,sha256=CEwqmmgp_tHkjNzYxXggO_WkKbP-JQNBCyHPsBa_sOQ,29397
|
|
925
|
+
vllm/model_executor/models/minicpmv.py,sha256=ZipcRzr4XutYEmnzDl6XcbanzHsdkWWeaEkTtHN-ZUM,48155
|
|
926
|
+
vllm/model_executor/models/minimax_cache.py,sha256=k52vWrBlTlPPEOxeZ4Pn8scFroolWzI5DYXpBtX1fjo,1212
|
|
927
|
+
vllm/model_executor/models/minimax_text_01.py,sha256=Oy41hfzsLwuzAFkO8HmIzlsUk4XQqkxFZ2UoPQ6t-AY,51742
|
|
928
|
+
vllm/model_executor/models/minimax_vl_01.py,sha256=8Qnx1WpI2VZ8g0FUVeejOKLFzFFEOM76ugiqh3urscw,14333
|
|
929
|
+
vllm/model_executor/models/mistral3.py,sha256=ZbUnC4At7wrF7NBa7WIJbXz3-Cga6c0wbqyKd_RrtVQ,23785
|
|
930
|
+
vllm/model_executor/models/mixtral.py,sha256=wROyHrIf3ZGywQgvY5Y-RGjo08VyWtYJgSjMKY900X8,20207
|
|
931
|
+
vllm/model_executor/models/mixtral_quant.py,sha256=_xjMW4N6E8zWmdFff1ISjGt0VL4IXNSovtfXg67lRRQ,18555
|
|
932
|
+
vllm/model_executor/models/mllama.py,sha256=HjmIWsDNJaBIyoNKDJWichhpZLHzCp7Pz4S2a9La_Rk,69388
|
|
933
|
+
vllm/model_executor/models/mllama4.py,sha256=YyLp2tXHnJ6XSub21GQbBmQGdzUH0fbiwUPz4Hf4ZOo,34849
|
|
934
|
+
vllm/model_executor/models/mlp_speculator.py,sha256=Y7j6_gQPcxM53DHel_hLHdT2Xm1t3V6bv2_Q2e_jgFI,7965
|
|
935
|
+
vllm/model_executor/models/modernbert.py,sha256=wP1_Pr9Y9N_huQIPErJD6NyDGImzxj0_b4j2zLUnCs4,13156
|
|
936
|
+
vllm/model_executor/models/module_mapping.py,sha256=vNEOOezDnDR5JgMltbviAANLu8CM6tQdr3RX6tZu_i0,1844
|
|
937
|
+
vllm/model_executor/models/molmo.py,sha256=ZQV8fyFJpxElo38ELIHcLoSp1RTOn4eQ0X5IV5aYxQE,55219
|
|
938
|
+
vllm/model_executor/models/moonvit.py,sha256=uIhdvvpCQImQCVXAKFAfM_2BbgvHycdQcGR9q1UA_7U,24120
|
|
939
|
+
vllm/model_executor/models/mpt.py,sha256=OlBtxlKQL-NfEElsrlZwd5G8luQ42-06N7p8ZLFgK8A,12754
|
|
940
|
+
vllm/model_executor/models/nemotron.py,sha256=Ir2Jq2DAypuwWLpda_dyjNeENZfiK4MwlUQsJRgn-r4,20715
|
|
941
|
+
vllm/model_executor/models/nemotron_h.py,sha256=O7udE0Wahyb4KAn7ExIcPpzncmffrUn4st3lv2utdoc,21591
|
|
942
|
+
vllm/model_executor/models/nemotron_nas.py,sha256=t_uY2L4iPWCun6h6ZGRYqreEucld_1sH87u5Os6QETI,19207
|
|
943
|
+
vllm/model_executor/models/nvlm_d.py,sha256=7AeV--WpvjDOe5sotcAx-8sxjCO-lgz4xZkmduQmvaM,8066
|
|
944
|
+
vllm/model_executor/models/olmo.py,sha256=FklGAz1Q3vGrLQIfTuRUuIRtKMEnMx20tWVgBPp4W8I,14924
|
|
945
|
+
vllm/model_executor/models/olmo2.py,sha256=24LqnlygqCbumLWlCMtF1g2qPaVmZzqxAE39DFkeTag,15984
|
|
946
|
+
vllm/model_executor/models/olmoe.py,sha256=Ha9Kmux5e_EVmyPIywkw0cg74kpXQhEOFGEz8zgOtkI,19416
|
|
947
|
+
vllm/model_executor/models/opt.py,sha256=SRHn5LMjOnO5ECwJxfXjBYq_MINaRD0ynTUwzsIozFo,16572
|
|
948
|
+
vllm/model_executor/models/orion.py,sha256=DeAgZLf8sOiQcJ5dVPjtc1EJ74G4CkjxReF2_5_SpOA,13862
|
|
949
|
+
vllm/model_executor/models/ovis.py,sha256=x2D7qeHAw6Ldg97MJOO__aYEYMejxLcRJHSinbYT00Y,22227
|
|
950
|
+
vllm/model_executor/models/paligemma.py,sha256=rKRahsfuBUuERtv3lkKA3OfAhxZvtZ8RJiTD_UGIhF0,15554
|
|
951
|
+
vllm/model_executor/models/persimmon.py,sha256=zcVATPUTd1A3Jl1TrQXd5KulD1B_AhcPob_N9PvWMUs,14328
|
|
952
|
+
vllm/model_executor/models/phi.py,sha256=1dUL1DRw8swSgChiBgdMB9bgIdMwWefBN746VasstVo,14172
|
|
953
|
+
vllm/model_executor/models/phi3.py,sha256=OdDcrMZ2IYHzg_R_gu89ae3lijNSFlxUXKTw4mmcR8U,457
|
|
954
|
+
vllm/model_executor/models/phi3_small.py,sha256=bStcKwV5apKKy2GYp2hlf8NjWPTopyVlWOUmCqd_Qho,18292
|
|
955
|
+
vllm/model_executor/models/phi3v.py,sha256=8BmUdNa26qDQeIeppe6udiSbWGJoaCFWFVdZmGXW_kY,28850
|
|
956
|
+
vllm/model_executor/models/phi4mm.py,sha256=0i258ZOEAbfzkRNyJi0HfCFL-4qMHiub_hEkhMuwsZA,49840
|
|
957
|
+
vllm/model_executor/models/phi4mm_audio.py,sha256=e9iFyY9QABfhPI3gtPwtsquhnMzHew1Il34AjrDBFHk,49134
|
|
958
|
+
vllm/model_executor/models/phi4mm_utils.py,sha256=dg5ivyxJCdlyWmKxX4pZOF6I-BTgpUMqY4nmHdZFCEk,66739
|
|
959
|
+
vllm/model_executor/models/phimoe.py,sha256=oMOD3BBwHSa29SWaIORYokOrSi_Zz3clSk7mBoAGZso,25101
|
|
960
|
+
vllm/model_executor/models/pixtral.py,sha256=lZy-PzWZkJIhYUfkW8TtZISoFBgMLBUcbIYTgJEcAZw,48772
|
|
961
|
+
vllm/model_executor/models/plamo2.py,sha256=_RujxGJdXQnep1ws4g-7cW-1dUYKhuPiUn8YPvpehS4,30125
|
|
962
|
+
vllm/model_executor/models/prithvi_geospatial_mae.py,sha256=H0u7L1bgsuBTJGwk3puRo6eRItvSrWL5B-xcQFOFlTw,9543
|
|
963
|
+
vllm/model_executor/models/qwen.py,sha256=aRjSXkeI2dwoOhf5yvYu0Nj_-rLezwQQR1UnKpNghJM,13916
|
|
964
|
+
vllm/model_executor/models/qwen2.py,sha256=-i0q-2GvZkkNbY7YQCu_l7Z-lSG0IfLZ_q92eBf2sFc,19879
|
|
965
|
+
vllm/model_executor/models/qwen2_5_omni_thinker.py,sha256=xKeMA-INEJcCYx3hfc47HygYHdmXMdQq8op7umC15KU,38268
|
|
966
|
+
vllm/model_executor/models/qwen2_5_vl.py,sha256=rTrJZOQWoIrp1enKQlrl6LoBMiEzKNNspNx1R_2_XYM,48024
|
|
967
|
+
vllm/model_executor/models/qwen2_audio.py,sha256=7RNQ-dEbeGPKawVNzW2J9AS_szTI_wXIXbt5hpIW4Cw,16981
|
|
968
|
+
vllm/model_executor/models/qwen2_moe.py,sha256=SYlWCTr5dTpVA0DyTfg7G3TVbpZfwRNY7lRL7bysFh8,23070
|
|
969
|
+
vllm/model_executor/models/qwen2_rm.py,sha256=FuJX7g8pz7b-0ZYIP2xKWo5W-35q4Se2hYYo283Iac8,4455
|
|
970
|
+
vllm/model_executor/models/qwen2_vl.py,sha256=oR3S3iMHWIPn9pfQ3-5ljuN3lMjduiHyyzlUgTi3MDQ,57893
|
|
971
|
+
vllm/model_executor/models/qwen3.py,sha256=Fmdv-O4ju_x_8C-VowJyh4q-jquz-dTm1AxWLAdGCb0,12583
|
|
972
|
+
vllm/model_executor/models/qwen3_moe.py,sha256=rszNURZlObvtb2X1i50cUnRcpKzUDW0pAZFL-Kxt8Q8,23237
|
|
973
|
+
vllm/model_executor/models/qwen_vl.py,sha256=6RwI-q1Csx1dTNpzHlK521lSOQMBeANWP3n6L04DrPw,27267
|
|
974
|
+
vllm/model_executor/models/registry.py,sha256=Xsu2JBDzOAqht1vJQh18NKk3PsNX8Eel0bs6AE3Ur_E,26779
|
|
975
|
+
vllm/model_executor/models/roberta.py,sha256=Y1COSzEF2tuNSnGBsflZFIv7f4bc4zoGz--s1plyafo,11319
|
|
976
|
+
vllm/model_executor/models/siglip.py,sha256=zfwSZK8jlQL8B6_C1WvF_sUlacyRNMIDXk_Gp2NPrfM,18720
|
|
977
|
+
vllm/model_executor/models/skyworkr1v.py,sha256=pBIIK4bjDxx8q6sltp7TWdpHuk7scw0Mu6AmJjjCnfA,34399
|
|
978
|
+
vllm/model_executor/models/smolvlm.py,sha256=5Lopc0syQDwQQZ6agYHWi2Ew8c5PdzOLfcLfBFqv27A,1799
|
|
979
|
+
vllm/model_executor/models/solar.py,sha256=HLDduE5re-mJnZEEq6djQTugObzWM6HBYFMs3yhJaXU,19962
|
|
980
|
+
vllm/model_executor/models/stablelm.py,sha256=HOSTK482W_yh2yCoMxH_200DsyTGIRGsd7Ymga0AA5M,15007
|
|
981
|
+
vllm/model_executor/models/starcoder2.py,sha256=fC4Vg6oFZow9GBS1QeyuumChhfv8AuBRZOLkTBhdjMs,14610
|
|
982
|
+
vllm/model_executor/models/tarsier.py,sha256=GYJF1oKOP7iaJMtl8krgw9f5_i3aixv7f7-mFvnaDcU,26643
|
|
983
|
+
vllm/model_executor/models/telechat2.py,sha256=s6Xfzd3cBY06n3kT3w8RjID5M5imOYVLWkXSDPeWrkQ,6063
|
|
984
|
+
vllm/model_executor/models/teleflm.py,sha256=8BsSo5Ox4ENo4Y1UKicd2nq41lksPZhW-ippU-498NU,3212
|
|
985
|
+
vllm/model_executor/models/transformers.py,sha256=w1Xe7SCYiL0Ae9WXb-dxUBG-TU1J5KLkGIICg-KnD3A,20543
|
|
986
|
+
vllm/model_executor/models/ultravox.py,sha256=WGim1GG_g_PXmbqJKNNY3gCVBU2OeD6EepYhVeUC0iA,27478
|
|
987
|
+
vllm/model_executor/models/utils.py,sha256=X1QRbhVpZ-pbtv0uNvl3W-eHV0UNLEnW9kaB5rL9Ks0,25395
|
|
988
|
+
vllm/model_executor/models/vision.py,sha256=ocDWi7KE4XXlz9iOZpYxkYg8dD9-z_jHU1hh1pdPZuc,5603
|
|
989
|
+
vllm/model_executor/models/whisper.py,sha256=BF8r_T1soh3UIfZ4UwKUuK7eVFa8PIFzIDFGGKwAy5c,31202
|
|
990
|
+
vllm/model_executor/models/zamba2.py,sha256=obIf2tc80sHOfp5xkh2Jvw-68rXru7Zf-tU0G9dbuno,41152
|
|
991
|
+
vllm/multimodal/__init__.py,sha256=itu8-L_cTTq8GzajfSi4OHsAGe4lqyOyKjOlk6GLlPk,1059
|
|
992
|
+
vllm/multimodal/audio.py,sha256=YNvIWS7DJHSbV1RJSo0xCpoP4vOFzbw_Ot5U3FEGHvw,3478
|
|
993
|
+
vllm/multimodal/base.py,sha256=7D7GyxhfTkqSOsHtUuKqXWR1znFk71Mq7ByHD45KP60,7002
|
|
994
|
+
vllm/multimodal/hasher.py,sha256=27AeslgZzShkcuYC6iKnt8EEPocn6YmkdbnN_2xkWK8,2780
|
|
995
|
+
vllm/multimodal/image.py,sha256=SZs770NesTSo6JtomPqMWE5vRj5Qfn20R27ay3a4WpI,3301
|
|
996
|
+
vllm/multimodal/inputs.py,sha256=3O3M3I0RmdQOPOrXuSWi9-az5j9MGjzQ8XX2bH21bfw,28533
|
|
997
|
+
vllm/multimodal/parse.py,sha256=fl4wwsjfPWkLQlCwaUjx6vbPXbviT98DREkmfAMehTw,15841
|
|
998
|
+
vllm/multimodal/processing.py,sha256=ffRrhr4E5Kos_FR4YPNxBZZzjcfX0TGtE0ra5b3b6jQ,63803
|
|
999
|
+
vllm/multimodal/profiling.py,sha256=SdpnpVfP-8sqZyxVFp3UbdVlRf60DlTMmdDGAwsfVTc,10020
|
|
1000
|
+
vllm/multimodal/registry.py,sha256=4OS18qN4_7168jA0o44lwrO77DAeq6Vh2WXv38h6ygs,11254
|
|
1001
|
+
vllm/multimodal/utils.py,sha256=ssy0pFH1g2nYvAHyroBBM1OE15so39YfHrKJB-I2Gvs,16398
|
|
1002
|
+
vllm/multimodal/video.py,sha256=rJE0DsuPmKUQcKkQmIks3wPXAaleR5z-ZPbuhEyI0vs,7147
|
|
1003
|
+
vllm/platforms/__init__.py,sha256=_vGc1ySlqBeuEjIE75yobQ0jeuk2TbMP4112uogrXaE,10637
|
|
1004
|
+
vllm/platforms/cpu.py,sha256=vCAMoXoS8zKkF-TGvjFEm0IXuXyZV6ezGhUgsURNj1k,11304
|
|
1005
|
+
vllm/platforms/cuda.py,sha256=M-HWOK03iz6FBgcOL3oRIPWvwAL9w1wYvRS8xU2goNo,23214
|
|
1006
|
+
vllm/platforms/hpu.py,sha256=FLff8i9N1klXT7UORGVGc_EP-6GgFXBfqKPqonJ6p1o,4206
|
|
1007
|
+
vllm/platforms/interface.py,sha256=12l23jZzic2LQ_Ohny0Ysx-hbaeZI8RbecC2RMqaOUY,17932
|
|
1008
|
+
vllm/platforms/neuron.py,sha256=4kGXZ7nuMKkIXlGBqCa8UMFKe9308pbZDW41hzAVx8c,5575
|
|
1009
|
+
vllm/platforms/rocm.py,sha256=zlt-OkpFYBPCuk_uOBBYqheLB0LF5He-zRaxkvMfauE,17800
|
|
1010
|
+
vllm/platforms/tpu.py,sha256=PRoSoHhd2MnZ3X8Bbm423qHiicnDITGaWoCcSm2Lrbs,7794
|
|
1011
|
+
vllm/platforms/xpu.py,sha256=-crpaWHQZcPgmRJ6VK9SOkHhiqILCvgqIL-xDK7RwlA,7592
|
|
1012
|
+
vllm/plugins/__init__.py,sha256=XZWErO0pxklJEsdPQiqL7LWi_JQ1AbvbY2UrZSQ4R6o,3322
|
|
1013
|
+
vllm/plugins/lora_resolvers/README.md,sha256=I4lYxAwarJdoR322hv-UQqsvuqjdQIxexWtBVdwyrL0,828
|
|
1014
|
+
vllm/plugins/lora_resolvers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1015
|
+
vllm/plugins/lora_resolvers/filesystem_resolver.py,sha256=Ic4o6SWF7DeDhNAAE1dxzaAMb_0L03DNzM0590FC1Fk,2086
|
|
1016
|
+
vllm/profiler/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1017
|
+
vllm/profiler/layerwise_profile.py,sha256=ePkIStAYP58wRo3WUuy9dvOMvd4t5fRPeUN2QDALW0U,13887
|
|
1018
|
+
vllm/profiler/utils.py,sha256=zh9V6T6baIqC_EXfG39TUF2-d0z20JVqxfVtKWFDl6Q,4714
|
|
1019
|
+
vllm/prompt_adapter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1020
|
+
vllm/prompt_adapter/layers.py,sha256=qa3iB58VSjE9dZPBVrLwNnBbANgp9KwhBtAd7DLLttc,2795
|
|
1021
|
+
vllm/prompt_adapter/models.py,sha256=s3K69Ul2W8GVfM8oJip_Mymz1T4d0FamTQO5U5nyFMQ,13791
|
|
1022
|
+
vllm/prompt_adapter/request.py,sha256=ZUEDOsSr938VwW19gh2pv8H7d7TjJbsd97DvfaYB6WI,907
|
|
1023
|
+
vllm/prompt_adapter/utils.py,sha256=1iulqD-AWfgrBwwa87FIz_OMb3Zy6aEqmAQQMoEeCaw,3737
|
|
1024
|
+
vllm/prompt_adapter/worker_manager.py,sha256=emiWFvvZJew530MDzT3WwbbebvPO9Y1DyvuKQeeviI0,7605
|
|
1025
|
+
vllm/reasoning/__init__.py,sha256=4sr5FvUGkzpACLGXKoJu075EFK5Bs4gXsDWKgRxAU8s,528
|
|
1026
|
+
vllm/reasoning/abs_reasoning_parsers.py,sha256=jmxq1sBhGLfIQQrLSIhFma5mHOWyQtnpPZwdsvVGdaE,6645
|
|
1027
|
+
vllm/reasoning/deepseek_r1_reasoning_parser.py,sha256=fVAV4ZsMfd_6bB3Rf6ucSGnMJLnI1NjcAMA2i2yucwA,7465
|
|
1028
|
+
vllm/reasoning/granite_reasoning_parser.py,sha256=1D8ojEdvWm391P8xoovSgLsEk2pESZIeNv3vqwfo-Yo,15899
|
|
1029
|
+
vllm/reasoning/qwen3_reasoning_parser.py,sha256=gzC5_aje9dv5Juw5TRXQIOOP4QRPa_BXZkcE6cmrb68,6496
|
|
1030
|
+
vllm/spec_decode/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1031
|
+
vllm/spec_decode/batch_expansion.py,sha256=XXuJzD1RxHYRVA_az4ULrt7bFuWW24dy2eE8y7xvXZE,22809
|
|
1032
|
+
vllm/spec_decode/draft_model_runner.py,sha256=CCT401JFi-5_SmVfqteN98scAGS_eapYX_NH3YdkBKI,15222
|
|
1033
|
+
vllm/spec_decode/interfaces.py,sha256=9BnwWHd0SiMOOInnnjFHyyiidD6uk2HE7avvdgtNdvY,3155
|
|
1034
|
+
vllm/spec_decode/medusa_worker.py,sha256=EtxnCq_wFhOAxx4VYZjdZIp0KK2pSiYq0tukM6TqzdA,4969
|
|
1035
|
+
vllm/spec_decode/metrics.py,sha256=K-g8vi-_RoyMlEThMYcyb36Or5iXHz0Y5-jpnh7KE6o,8152
|
|
1036
|
+
vllm/spec_decode/mlp_speculator_worker.py,sha256=cofbNTCITpuRV8k6QeaIgm5RlDYHMvDavU6Gzsk2CNU,3806
|
|
1037
|
+
vllm/spec_decode/mqa_scorer.py,sha256=QttFp8DNHqVBAI4dGprnKjM_pIorE82jJZeDKk_FSBs,7577
|
|
1038
|
+
vllm/spec_decode/multi_step_worker.py,sha256=tPwGnoIKLuUoQeJprtOvESBvQfSgasJ2R8vbOn6biBk,19673
|
|
1039
|
+
vllm/spec_decode/ngram_worker.py,sha256=lCof1qiVJgLwRs5yuTUDzGca9WuVnHWgsYO5gqs6fh8,7896
|
|
1040
|
+
vllm/spec_decode/proposer_worker_base.py,sha256=rffkFH0N1Z3roRimkMdqTiaZqZ1GLhvn6fBg8bKgNDo,2158
|
|
1041
|
+
vllm/spec_decode/smaller_tp_proposer_worker.py,sha256=8w0TnEbusk49rf3GoTIZq8mklYjYTkxXu093qhmZuz0,6952
|
|
1042
|
+
vllm/spec_decode/spec_decode_worker.py,sha256=Q-hPtClVLfyO-cIJnLo4FWTTeS8fMMjn52Pur8k40ys,63027
|
|
1043
|
+
vllm/spec_decode/target_model_runner.py,sha256=evuaAOQnTwrRsXo-yMOXM-0SICI7gYNpnUrhPKRMQAk,2142
|
|
1044
|
+
vllm/spec_decode/top1_proposer.py,sha256=Cljv7ojLAzqVMPUdKsxISdTo2aF6io47gVsKUpq5F9c,12423
|
|
1045
|
+
vllm/spec_decode/util.py,sha256=H22iXEsK3HPptmui5JldppTXPLN8efrEbaKLj9NCMDU,9957
|
|
1046
|
+
vllm/third_party/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1047
|
+
vllm/third_party/pynvml.py,sha256=p0NkH1xRdvKZlP9F6Wfy5mBzdP4tbKpHc2TsFj0V_pw,234653
|
|
1048
|
+
vllm/transformers_utils/__init__.py,sha256=yVNs7WNM1UWvqmKYPW-R4D9NXhYWEjKYQKlfcpxL5HI,910
|
|
1049
|
+
vllm/transformers_utils/config.py,sha256=BeGowdDnNHFhJYPadLxrwdI9QgAKW1u_P1BHj_TVTsk,34103
|
|
1050
|
+
vllm/transformers_utils/detokenizer.py,sha256=UkxFpYPV-TwBGy9GhnPmSnf-SBslKcw4LQaIYgbEJsI,7299
|
|
1051
|
+
vllm/transformers_utils/detokenizer_utils.py,sha256=UoNBvr9gUNhgDNxMmVIT78HjY_KZZHbad8SgwSI6ltE,7321
|
|
1052
|
+
vllm/transformers_utils/processor.py,sha256=FNOmqYVq2Y-foTJs1xsvjqFhazb9mJh9rcS4iYse-XA,7602
|
|
1053
|
+
vllm/transformers_utils/s3_utils.py,sha256=3j5x2VDqiSsW4YwJRG-3bdbSONiw74cEQpf2Qz0SzLw,4954
|
|
1054
|
+
vllm/transformers_utils/tokenizer.py,sha256=kuzCvWjPiXCEYBlU854jBfVwsE5QyEvo6Av89g9PFXo,10721
|
|
1055
|
+
vllm/transformers_utils/tokenizer_base.py,sha256=_1iqKJZTSQW9ITGpZkC-A1lhYw7ND1ZDzpY3SpDhj_c,4029
|
|
1056
|
+
vllm/transformers_utils/tokenizer_group.py,sha256=RqfnicvJU7xQjcAGF1C6czeDf4xjKZoBcWuTlpQYPTc,5259
|
|
1057
|
+
vllm/transformers_utils/utils.py,sha256=C7fFp4Eyw5dGw9neyADzwExlhK5A0g0efIDVL3PHnzg,2699
|
|
1058
|
+
vllm/transformers_utils/chat_templates/__init__.py,sha256=U1sUyX9swSjxaULlg0B6rSroU5H8upeyInuHsF74SEE,208
|
|
1059
|
+
vllm/transformers_utils/chat_templates/registry.py,sha256=ZmIsEElC787e2vLsWnuyhmnB4nmlGDjGpF_tAYWno5k,1945
|
|
1060
|
+
vllm/transformers_utils/chat_templates/template_basic.jinja,sha256=DMH0156UMA7eoJelXKUMEDzB-SigjbyCOBxIu9OyFJE,78
|
|
1061
|
+
vllm/transformers_utils/chat_templates/template_blip2.jinja,sha256=ltMbjFdK7T4HUcN_OQaX4hj2r0PGlS1EJ9zhSlnTz1c,332
|
|
1062
|
+
vllm/transformers_utils/chat_templates/template_chatml.jinja,sha256=CKxCWf_KemM_DntV70Hf03WNkDvxznolyW-03SJJw54,370
|
|
1063
|
+
vllm/transformers_utils/chat_templates/template_deepseek_vl2.jinja,sha256=WX32uOZ7h8_xqrWvmsI5R-6Ns8ZcXVn74CKB7FJOifA,785
|
|
1064
|
+
vllm/transformers_utils/chat_templates/template_fuyu.jinja,sha256=hzdsPgeUMaZnd5L23QPiz2oC6_wMBy5WgZkXMVs3Dgo,85
|
|
1065
|
+
vllm/transformers_utils/configs/__init__.py,sha256=IAAGZKcyHn6oQJv85DjFeOywu8KfhAECUCLwohMvy5A,2451
|
|
1066
|
+
vllm/transformers_utils/configs/arctic.py,sha256=8WAZRegtPG1_qaFIplNemJJLlCLHBYB3p3m8ZR5co88,9053
|
|
1067
|
+
vllm/transformers_utils/configs/chatglm.py,sha256=6jt7jwkyzTBLCYQsNbFwww1-FCgBxfhoV8y-PBqm0-Y,2939
|
|
1068
|
+
vllm/transformers_utils/configs/cohere2.py,sha256=GaulobYCg5yygFpKJKiwT5EeI3VGkZBFZ36Cuv10WEc,10422
|
|
1069
|
+
vllm/transformers_utils/configs/dbrx.py,sha256=7zZOGYrASjYZiiXjHRtx8NcHin3efEz3X5y830qzZUk,10984
|
|
1070
|
+
vllm/transformers_utils/configs/deepseek_vl2.py,sha256=BwZtrbgFNLRHyOu-yMpOS8uGIFamH8_DAWxw8RtzFJA,7296
|
|
1071
|
+
vllm/transformers_utils/configs/eagle.py,sha256=pfj6dlz4ElIMGZykeCp1snCCBB-rapqtBrN_JuH2M84,3217
|
|
1072
|
+
vllm/transformers_utils/configs/exaone.py,sha256=19I7krrE3PayhGglYd0H4zzH0gaFCl0mehaGJkayomM,8927
|
|
1073
|
+
vllm/transformers_utils/configs/falcon.py,sha256=vKXtykJL5NGzcDFfSnE532vBV5KLrQvOKm7v5P58y-Y,2986
|
|
1074
|
+
vllm/transformers_utils/configs/jais.py,sha256=1jEXh11bRdFpH8ptGPKOZaTOr-Ck_BCgMbXpc959eVg,10432
|
|
1075
|
+
vllm/transformers_utils/configs/kimi_vl.py,sha256=xXtkLgTdOt5ZgSxva36iLzgZqqklIoiHaoJhCNgJyVw,1486
|
|
1076
|
+
vllm/transformers_utils/configs/medusa.py,sha256=ZZcus4c6s4A1iTOPCR2bwzJpSHKsms98dycjVpmoi2E,2012
|
|
1077
|
+
vllm/transformers_utils/configs/minimax_text_01.py,sha256=XcsvDZWzH1KHP9SQiD13yUQ5ox6WJsG9PMgz46ygqC0,2384
|
|
1078
|
+
vllm/transformers_utils/configs/minimax_vl_01.py,sha256=M9PrR1OoyRuRrA2KE2YhTnMCb88hu24QVnfiJ-Uqriw,2617
|
|
1079
|
+
vllm/transformers_utils/configs/mllama.py,sha256=DK3NNVpe70EH-HC8CWjtlhXRvzt95uQnDIOZ3kIOrwI,874
|
|
1080
|
+
vllm/transformers_utils/configs/mlp_speculator.py,sha256=2it7HgAv-ZqGDLoE7q66oxXjk8R_mBdnGw31_TVXI7w,2500
|
|
1081
|
+
vllm/transformers_utils/configs/moonvit.py,sha256=Egyjh8mvpzPlX-RmbfDf8ZmeBe7K9fqimYX-QgK9NrQ,1272
|
|
1082
|
+
vllm/transformers_utils/configs/mpt.py,sha256=8G0gnNNmTousHr6yInzh68_XGmqJkL9vptWpDPe3xUw,7652
|
|
1083
|
+
vllm/transformers_utils/configs/nemotron.py,sha256=8_mTkW7hUq0gLXuyrdQjsJDwQlmn_fkTFz-8xCUi7pI,9043
|
|
1084
|
+
vllm/transformers_utils/configs/nemotron_h.py,sha256=ZGU7OLStOK_qnmg8Drp3lilJbLAEUdKdSvVFSFyb9-M,12264
|
|
1085
|
+
vllm/transformers_utils/configs/nvlm_d.py,sha256=yT9rWArSnIGdah2xiD-kdlzpEHZIjmys_pel8rm5nm8,1048
|
|
1086
|
+
vllm/transformers_utils/configs/ovis.py,sha256=tuFDhwa1tfivFenL6Os1PImwTkfcsVy2ll7nS5aNS40,7724
|
|
1087
|
+
vllm/transformers_utils/configs/skyworkr1v.py,sha256=tFblvu0RGA1yVxAlegYtX_he7vBp5gb4czxDzhXGatU,1938
|
|
1088
|
+
vllm/transformers_utils/configs/solar.py,sha256=2BDfqhbvjutvzoNvqrJ6a1ESouK7YmIAQGJBIgfLTIU,10910
|
|
1089
|
+
vllm/transformers_utils/configs/telechat2.py,sha256=i-VmqZFsMjS2O7-ikd0-9cmFQHxUgM-Hz7cfnWsLuVc,2269
|
|
1090
|
+
vllm/transformers_utils/configs/ultravox.py,sha256=K1hw-jFVbTpOZ1mw7PsHXXNus-W8jf7cqjmS3zslkUY,4528
|
|
1091
|
+
vllm/transformers_utils/processors/__init__.py,sha256=w199hgueQE5uEOCjzPLiU1JKZNzB-1XAl4Asz_LdmYA,317
|
|
1092
|
+
vllm/transformers_utils/processors/deepseek_vl2.py,sha256=jhVoBgnvziilKiZjGoePzrIcDJM0lYluQGTkcJ-8El8,14639
|
|
1093
|
+
vllm/transformers_utils/processors/ovis.py,sha256=8hih8piZ7roFiih6-2CBSjNS6Staz6B8hQL2x4MiAOM,18927
|
|
1094
|
+
vllm/transformers_utils/tokenizers/__init__.py,sha256=dN6RDCTGacE-3exN7VSZHlEcHhu__4dQM6Ry0lQ43w8,372
|
|
1095
|
+
vllm/transformers_utils/tokenizers/mistral.py,sha256=YxvurhrAcpEiGPs6u-_KpgTsm2_ZgIwlMEMe-3WCZNw,19107
|
|
1096
|
+
vllm/triton_utils/__init__.py,sha256=QuRhc0qyR8n2bM64Mv4VqhR3lIcWl77dQO8XX8d9prI,433
|
|
1097
|
+
vllm/triton_utils/importing.py,sha256=v_dNRwDZnAvk4d_Un6BJBeEN8LS5iC4Pl1Tupelf4FU,3422
|
|
1098
|
+
vllm/usage/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1099
|
+
vllm/usage/usage_lib.py,sha256=qFy6_zSdBRAfeA4vdYFUDi5kDZqeY5o0Yaw4mjEHX-Y,9020
|
|
1100
|
+
vllm/utils/__init__.py,sha256=cZFhFiy_wCrhus9bai1XNWXAj9KIKohgYftpNSi7vb8,101845
|
|
1101
|
+
vllm/v1/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1102
|
+
vllm/v1/kv_cache_interface.py,sha256=D-rwRcuZsi614upycdfncYn_9rWQeJSVKCccRFPaZJw,7342
|
|
1103
|
+
vllm/v1/outputs.py,sha256=Nfqnm29UGmg1wtI4ORcFEWmWXjyQCL2aXfEH88BIfAY,4086
|
|
1104
|
+
vllm/v1/request.py,sha256=ur6bL1qlE7ofxm4LlXImv2L55xoD4Cbu4ALA1whm014,8582
|
|
1105
|
+
vllm/v1/serial_utils.py,sha256=OjbbDw2iqPZGQAkaY8Np2ni00BHLH8x2PU9fRH2cu9c,13220
|
|
1106
|
+
vllm/v1/utils.py,sha256=kErViY1AiUQiDYref2q62MtG_BwVzoh2DIoLI1J1UVg,13110
|
|
1107
|
+
vllm/v1/attention/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1108
|
+
vllm/v1/attention/backends/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1109
|
+
vllm/v1/attention/backends/cpu_attn.py,sha256=GqZcEWcjjfULpjtTcYt-FwhZ4MFkHnok4AFW3ie1Pzc,7587
|
|
1110
|
+
vllm/v1/attention/backends/flash_attn.py,sha256=H8B2SxBFVf7o5dQKCQTKStfaHTaVDR_fn-hqJvCgBR0,32254
|
|
1111
|
+
vllm/v1/attention/backends/flashinfer.py,sha256=YPePPw27EPRXEJoqd7TysDN-zSf-EW0_Px_ko2YIa6w,28642
|
|
1112
|
+
vllm/v1/attention/backends/flex_attention.py,sha256=jtBKWLNxYrpXzw9vomS7UQeKMd499OMQZj_NCV8VhLk,18931
|
|
1113
|
+
vllm/v1/attention/backends/mamba_attn.py,sha256=S6A5CV6OU_M80Q4oF2JzY09Q5LRTVuZ4KtU2Qop4ANQ,8014
|
|
1114
|
+
vllm/v1/attention/backends/pallas.py,sha256=Xq5wHB_3EdcwoKaDiIfcf4W54HzgUmddmH-AYEImD-Y,12770
|
|
1115
|
+
vllm/v1/attention/backends/rocm_aiter_fa.py,sha256=pCJYa6tDCblL_IBvnBwtefSm0_ovV5EbI1l5H7xqjlo,24422
|
|
1116
|
+
vllm/v1/attention/backends/triton_attn.py,sha256=TYxupPP9yHNQGAvHVaqZqJPD_nubn6Pj_0FxNPeuVEw,18320
|
|
1117
|
+
vllm/v1/attention/backends/utils.py,sha256=K6EP4364ZOildoJdpTavOd0z59gqfdCX_jN6xb0l0p0,12641
|
|
1118
|
+
vllm/v1/attention/backends/mla/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1119
|
+
vllm/v1/attention/backends/mla/common.py,sha256=sibx5YvTBC6pkZjYm1E8V-KCrqbmV8c54K1TIlciXIU,38445
|
|
1120
|
+
vllm/v1/attention/backends/mla/cutlass_mla.py,sha256=ChLnuLLrKrduYI8Y7wHmntIeSU3F-3hUaot4RzzbZkg,3548
|
|
1121
|
+
vllm/v1/attention/backends/mla/flashmla.py,sha256=-7CxVUePV1JLXwUeDoBnB7hUWET9-L1wZnuRzf5vfQ4,6787
|
|
1122
|
+
vllm/v1/attention/backends/mla/rocm_aiter_mla.py,sha256=zU2CnRgCfLwQqsueprETGkEFXE-NxZVWM9tyk5ja6fU,9367
|
|
1123
|
+
vllm/v1/attention/backends/mla/triton_mla.py,sha256=c2GgxeFNvURb__JRxP2m2A-7M9_Fa4W3tZ2w4AQWM3U,6528
|
|
1124
|
+
vllm/v1/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1125
|
+
vllm/v1/core/block_pool.py,sha256=hFU1r4q220ZrAne94YPOBt4fbGB-URNjgeM7BCO0kXU,14645
|
|
1126
|
+
vllm/v1/core/encoder_cache_manager.py,sha256=PPQX2I8iu69DSQbUXboOEOclqZiAu9ngN3UaIRUyFRs,9702
|
|
1127
|
+
vllm/v1/core/kv_cache_coordinator.py,sha256=W6ha-k1hl3lg3kfss9HPxvgGPH4b1CH2nCjKQDGEd6M,15497
|
|
1128
|
+
vllm/v1/core/kv_cache_manager.py,sha256=VEil1ZU66Cr__2VnNHS2x2l7VC6yy13i-SiOH8LtuXk,16867
|
|
1129
|
+
vllm/v1/core/kv_cache_utils.py,sha256=qyDrfQOmokzTsQ3OiR0Eou_l1FLeQ2mgnRyfbfDci_A,40782
|
|
1130
|
+
vllm/v1/core/single_type_kv_cache_manager.py,sha256=6GKL_NO6_SownrtEK6dDIctEO2-LHgnqxNhXJUpUnkE,17966
|
|
1131
|
+
vllm/v1/core/sched/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1132
|
+
vllm/v1/core/sched/interface.py,sha256=mKU1I1yEhcSf5PFUt7TSkVtRd8Lliqdh8lpy3w9oB58,5860
|
|
1133
|
+
vllm/v1/core/sched/output.py,sha256=UfOSk0bEwotE0dxZqMNS7Tg5I9ji5Wt4JWODbTlI5Is,5905
|
|
1134
|
+
vllm/v1/core/sched/request_queue.py,sha256=c_fhiQL-oeOPVAoR_oKJppE2TjMRosabUDBQZgfbbI4,7533
|
|
1135
|
+
vllm/v1/core/sched/scheduler.py,sha256=4sRnNFEUi5_y_qBVujgPCvf_BwiK7pcknB2BQP5xaBQ,51731
|
|
1136
|
+
vllm/v1/core/sched/utils.py,sha256=_gRG8gUa_kKd5WKR14p-pfWY-GziBe9431gaQeMeCC0,1215
|
|
1137
|
+
vllm/v1/engine/__init__.py,sha256=3LTgK8NhskBNUVJLU05O8GMQ3-zy5XBuAhIzFbJ6aJo,5467
|
|
1138
|
+
vllm/v1/engine/async_llm.py,sha256=tzzgrVXlMz-9dUseLRZ5pQt_xx4d7WHPrz06JncNyDw,25035
|
|
1139
|
+
vllm/v1/engine/coordinator.py,sha256=EHsO-13fkYm-U59urHnvqabNU664gOjX_tHmvF2vFWk,11917
|
|
1140
|
+
vllm/v1/engine/core.py,sha256=p5olHWNROwtUCltFY5pCdo-V9ckePc7-4T6ArIlsBfg,43767
|
|
1141
|
+
vllm/v1/engine/core_client.py,sha256=_dhvwXtkzWeuBTspaAYaQJMlCNZuSuFhV96MahxZKAw,41573
|
|
1142
|
+
vllm/v1/engine/detokenizer.py,sha256=tu8vE2RkuniJAp3GLCGALTyf_HB1kZMn1Yt3K7ymwKE,10966
|
|
1143
|
+
vllm/v1/engine/exceptions.py,sha256=OurXOSPqCuoLWzIZ2vi5ahe9NnyGESnO-HZqlvSB-Xs,731
|
|
1144
|
+
vllm/v1/engine/llm_engine.py,sha256=QHQ6e4oNgcF3dva2ATuzghRht2hh_H7wblrwu-QPR2A,12844
|
|
1145
|
+
vllm/v1/engine/logprobs.py,sha256=maj6-ji_4Xj5pF5hetQHjllpaoRTO5919cd0CP99ngQ,7179
|
|
1146
|
+
vllm/v1/engine/mm_input_cache.py,sha256=FxnAXtNQqtrWGLSY1Qz60LGJd0kEEnuI75zNsO31c4U,3217
|
|
1147
|
+
vllm/v1/engine/output_processor.py,sha256=dYC1fbM74ZC59hzAxdf7Nqs0tYIx9u8Zbn4QYss9dnQ,18412
|
|
1148
|
+
vllm/v1/engine/parallel_sampling.py,sha256=uViFaH5NFxMQfWBz8rOdRZ5eIb_ZHMlJu3aCuhq2TIM,4834
|
|
1149
|
+
vllm/v1/engine/processor.py,sha256=Bcf4mDYSgNE4bpy9fB4IFNBKzmSnnc47Oiaqm0pptcs,18571
|
|
1150
|
+
vllm/v1/engine/utils.py,sha256=g-yYPlq6jcbR8KzKG7YnMeD-Eq0Pvu-cTxr7SE7hGsY,21422
|
|
1151
|
+
vllm/v1/executor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1152
|
+
vllm/v1/executor/abstract.py,sha256=PT8RwkVRgGjwuXeVZUU-h0_Vk5ywGolNU5iu-l8vbQY,4533
|
|
1153
|
+
vllm/v1/executor/multiproc_executor.py,sha256=2pm5EVCR0rf7iGzN2zH7D5_pWmry1LNyd4qLTvsDY44,20547
|
|
1154
|
+
vllm/v1/executor/ray_distributed_executor.py,sha256=JM3NMLxS_fzbtnK7bq-k5v-VB4h2uSCm29hG7pgpZVY,2061
|
|
1155
|
+
vllm/v1/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1156
|
+
vllm/v1/metrics/loggers.py,sha256=7jApriqK8mQFjxGMBPdF21WRYh8lfwD_0VhZBPH9qAo,22998
|
|
1157
|
+
vllm/v1/metrics/prometheus.py,sha256=RMS41lcHWzKGRrS8l92sbxfMfM0NIPiy8bSJKkKSAak,2821
|
|
1158
|
+
vllm/v1/metrics/ray_wrappers.py,sha256=1MzBlfON0nxqrc-QXK3SncCyvX6owJPJPtGmxwvGzW0,4475
|
|
1159
|
+
vllm/v1/metrics/reader.py,sha256=9rx29TV3t8P49Hx4a_F1LB2WHTwFDHkVc5v3utoEOFg,8702
|
|
1160
|
+
vllm/v1/metrics/stats.py,sha256=kzoJgaH3CHiPatVBZZ1U5mJnlfpukUIeV4KT23wkyRo,9438
|
|
1161
|
+
vllm/v1/pool/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1162
|
+
vllm/v1/pool/metadata.py,sha256=EmtHE4Ou06bD3uBUy_9hnum4qctYK6RwX8qsKpgVo8I,413
|
|
1163
|
+
vllm/v1/sample/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1164
|
+
vllm/v1/sample/logits_processor.py,sha256=03fn1HUfSGdK2EGpoEOTkCYdD1gZ7vKdiCH7JPl-4_4,19822
|
|
1165
|
+
vllm/v1/sample/metadata.py,sha256=6Ey7ZnZeQxCdkg7sErpUjZ3IYAsYsGL1B8BQwJFrAuo,1122
|
|
1166
|
+
vllm/v1/sample/rejection_sampler.py,sha256=wHdMkjv8E__M75iD5N2B5QFNfFcFworhKqSNCQHUZes,23006
|
|
1167
|
+
vllm/v1/sample/sampler.py,sha256=n1BUF7ypG7kalxIc8W-fX9GTjSQc7s0p3Ch5WdbAgpo,8389
|
|
1168
|
+
vllm/v1/sample/ops/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1169
|
+
vllm/v1/sample/ops/bad_words.py,sha256=JOnrJXq2RD45cA7cmePX2ktRjBg_1uJQsPqCc0gf2Vw,1191
|
|
1170
|
+
vllm/v1/sample/ops/penalties.py,sha256=B3IZcrvPBxl2jzTVYlIh3Ty2VSI5y4CD6he1B3Nlkx8,1534
|
|
1171
|
+
vllm/v1/sample/ops/topk_topp_sampler.py,sha256=RFz0jq1u9PiseL4N91ow-lFFwvEHavJFapizW6OP6i0,11303
|
|
1172
|
+
vllm/v1/sample/tpu/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1173
|
+
vllm/v1/sample/tpu/metadata.py,sha256=4UVHpx8QO2lNOnMON7ZY9oSfVzhjRemOa0_w3C05OeI,4695
|
|
1174
|
+
vllm/v1/sample/tpu/sampler.py,sha256=fcT-k807VTSnOOgwg9fDFb_FloHZ4ghLq-GpjdKhFzw,5098
|
|
1175
|
+
vllm/v1/spec_decode/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1176
|
+
vllm/v1/spec_decode/eagle.py,sha256=qRIZpYhgywdN3sGcwRuo_1C2MBnyI2rec6lehYsEz1M,19484
|
|
1177
|
+
vllm/v1/spec_decode/medusa.py,sha256=0RMqOwRkl4lkWWAeAdQGds1IwgEKtu8aMQnMiZ55oUs,2263
|
|
1178
|
+
vllm/v1/spec_decode/metadata.py,sha256=I3rD5wVyLs5ID9LnIN3E5hy0lu5Eetz5DGcxstQMeR0,2257
|
|
1179
|
+
vllm/v1/spec_decode/metrics.py,sha256=_Ql1shXH0DurEm1MRuB1SIv8j0VOZywNnBPEonKOU4I,6735
|
|
1180
|
+
vllm/v1/spec_decode/ngram_proposer.py,sha256=l5tmQWxkdg8brzW-KA39GX6s8RjUUQS3VpV54k-hndY,4293
|
|
1181
|
+
vllm/v1/spec_decode/utils.py,sha256=YOWiiHDBUYu8IVltwMQAGNW6ks7UXooOpDYbwoIXEyA,1300
|
|
1182
|
+
vllm/v1/structured_output/__init__.py,sha256=sPaRuECnO1mA3Q12J_2NlTS3FupsDJZL-6lLAlCrxqM,10045
|
|
1183
|
+
vllm/v1/structured_output/backend_guidance.py,sha256=X_5Ajlp2t1twy10Oit1OVU3t4pWQelu5Q-N8JXOTzpc,8784
|
|
1184
|
+
vllm/v1/structured_output/backend_types.py,sha256=AvBbM-6oA7KcX60ecRLTa3geFnc4Dbgwa5HPcyax6D0,3806
|
|
1185
|
+
vllm/v1/structured_output/backend_xgrammar.py,sha256=Nkdy9bh7vZxvuATE8T3c3GK4hyH6zCxw1V20QOuGqPE,12249
|
|
1186
|
+
vllm/v1/structured_output/request.py,sha256=qEeKTd0vL27BJ4cPvnlF8O9bVzfALoxekG-fNA3Sr8o,3220
|
|
1187
|
+
vllm/v1/structured_output/utils.py,sha256=KYQOcqpl3TGmWkYXpFFqAyZE4IwiSHa8uqjyHrmKD1g,5866
|
|
1188
|
+
vllm/v1/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1189
|
+
vllm/v1/worker/block_table.py,sha256=e51jo43IYbk1JpR5DzdXBKhL6Fd76Rs5EfmLidOGPeo,5112
|
|
1190
|
+
vllm/v1/worker/cpu_model_runner.py,sha256=hkcFVgZXKPoKkGh2D62oJUbxuZfOlp_6iwSIAoM1FAo,3482
|
|
1191
|
+
vllm/v1/worker/cpu_worker.py,sha256=CSjL_yJhwsuyn433NYASh03Syf-hlWwQEZdiAWDM-0w,6273
|
|
1192
|
+
vllm/v1/worker/gpu_input_batch.py,sha256=zoQ3858kSc8-IYDFdWpn8tcLWk5bcWFeW_dgc4YrbgE,33106
|
|
1193
|
+
vllm/v1/worker/gpu_model_runner.py,sha256=fU-jpPlol-KjoFeZlGZ1pX07ZsBGNoID02hpm3buzS0,126302
|
|
1194
|
+
vllm/v1/worker/gpu_worker.py,sha256=aP4DDXrix4a8dDlgrym7C_Wn06684LKZCt94xFB6f8c,17289
|
|
1195
|
+
vllm/v1/worker/lora_model_runner_mixin.py,sha256=2OYJG903pjICgfakvxHW0NP_M-9KiGR5y8LZ7VarlOk,6924
|
|
1196
|
+
vllm/v1/worker/tpu_input_batch.py,sha256=cMdio9ZPbeWDAMCTuzi1x5mOoVFhBSkayoDZY1vt5W4,26015
|
|
1197
|
+
vllm/v1/worker/tpu_model_runner.py,sha256=SNu3IjXoNE6F5DjbiK-uuuGYPL1jaKG43Kkzl_FI9q4,87698
|
|
1198
|
+
vllm/v1/worker/tpu_worker.py,sha256=Kul8udvcH-LRMmd66ibYbqQmC86-ijspaph4JvdxlzQ,13701
|
|
1199
|
+
vllm/v1/worker/utils.py,sha256=EQliDceSKruSaMPB2U-FtK7Kk1h71U87kxPQnTWZNqA,4427
|
|
1200
|
+
vllm/v1/worker/worker_base.py,sha256=VXzA1tCiP-UfXxQ_h-WeP41KSC_8JidGW4j0-S4nKIk,2045
|
|
1201
|
+
vllm/v1/worker/xpu_model_runner.py,sha256=zVI5z_A7TTVUhzULOCqWQ1GtjfojK8RliluLOhpnpAw,781
|
|
1202
|
+
vllm/v1/worker/xpu_worker.py,sha256=DlzA5qCJ2za-RTkzQ3RJAg6TRKG1HwuDnJWZQhkQNUY,7289
|
|
1203
|
+
vllm/vllm_flash_attn/.gitkeep,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1204
|
+
vllm/worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
1205
|
+
vllm/worker/cache_engine.py,sha256=CsyWo93EoS2h6VKrn-LfgGMlEq_X8B5Mu4j_og6qhaY,6075
|
|
1206
|
+
vllm/worker/cpu_enc_dec_model_runner.py,sha256=0TvNYphZ6xL2AZ7VWR__jySDkE_jqJ68kNRvF2SOjGk,13089
|
|
1207
|
+
vllm/worker/cpu_model_runner.py,sha256=Y5Hp-IFdTq4OQM4RvD-tL0VcOk9EbNOX0ALvFqGqwO8,28375
|
|
1208
|
+
vllm/worker/cpu_pooling_model_runner.py,sha256=IDZqfWjSTwGQho4H5Mcq2gmfdwuniUz15bwv0BzcO14,4830
|
|
1209
|
+
vllm/worker/cpu_worker.py,sha256=QeWZOXTGoPyG16DA6cGr4_JA-DB5iJce03zJlq01OQU,18582
|
|
1210
|
+
vllm/worker/enc_dec_model_runner.py,sha256=9n8QPo1z5hc7Ab08MEWyalOrbidIBBkNsz8umv4Yd58,24066
|
|
1211
|
+
vllm/worker/hpu_model_runner.py,sha256=dyiK-QSRZZXBeAhOFtAbihJYFDIoCaizX3c849lM6FM,104410
|
|
1212
|
+
vllm/worker/hpu_worker.py,sha256=0iWcTgXJqtrNFYeA_Wv_5TplTA2L82H99xPbUGdb_3Y,21648
|
|
1213
|
+
vllm/worker/model_runner.py,sha256=4Jz7uXeAlUDLGmjVK9Ho2IAOHvgRavU1mTfxdQ3QhT0,97895
|
|
1214
|
+
vllm/worker/model_runner_base.py,sha256=yzPjB5vhVYBMQGK0fMAWz4mwnv0pW9Y5F_mpxopwh_8,9439
|
|
1215
|
+
vllm/worker/multi_step_hpu_worker.py,sha256=HYUA_dkgxGDjNDt0WoIdiD6hfH4qej3YVrYGVJMgdxo,5365
|
|
1216
|
+
vllm/worker/multi_step_model_runner.py,sha256=-1ZO_o6IKHwR3zZzzmeevCoOpatfHiLAa2OoOtSNGso,39410
|
|
1217
|
+
vllm/worker/multi_step_neuron_model_runner.py,sha256=8m851aQ_GEeVRXBdp5xVJSmk8jabYA3MKqpO2R-0ENY,3292
|
|
1218
|
+
vllm/worker/multi_step_neuronx_distributed_model_runner.py,sha256=GhGSxnwC8B5gAoby7BsunFszu1xJL9iHL_bX_3PJ8pk,2199
|
|
1219
|
+
vllm/worker/multi_step_tpu_worker.py,sha256=YExBBMoOldMmgqhh0H80nZm9h4Q1EwGLAjLRs5iK1DE,4519
|
|
1220
|
+
vllm/worker/multi_step_worker.py,sha256=-OyCJfuXibg_qsLQfNkdNt4giuySR96Vkz5TsKHik-U,9485
|
|
1221
|
+
vllm/worker/neuron_model_runner.py,sha256=81JUkKFU9jVEQo3GHOfDnojUOxHGNlIVh7IxVU_874Y,19651
|
|
1222
|
+
vllm/worker/neuron_worker.py,sha256=aA-rK2XcrcbHvo6MMXE3O3oFEMM-vfg_yaMVBRRAVpY,7486
|
|
1223
|
+
vllm/worker/neuronx_distributed_model_runner.py,sha256=hdEN_hzfk_opVKM7VwfHuGaJ7sn30QTJU0S8Fvz5vz8,12667
|
|
1224
|
+
vllm/worker/pooling_model_runner.py,sha256=24D8B5IYzMX-Mz9pUk4MeNyV6HdyD1smMH4xv87qK0g,9193
|
|
1225
|
+
vllm/worker/tpu_model_runner.py,sha256=iD0gf6sp3TCFjr3hBvXfdEkJI2MlLUd7oBoN9w1z_TI,40840
|
|
1226
|
+
vllm/worker/tpu_worker.py,sha256=CEmhDsd-7f0JX0uyBbmQDMap8YHGIaYounYywKloe0M,14861
|
|
1227
|
+
vllm/worker/utils.py,sha256=BTNX3J84abaAQBEYkYbfv474Ye36KqkZqTK61IqJ_OQ,1980
|
|
1228
|
+
vllm/worker/worker.py,sha256=h946LI_ca1r1g-abtAlM82S19T4K8j_7QPkIlItYZgU,25551
|
|
1229
|
+
vllm/worker/worker_base.py,sha256=jdtdHBiLQGSY3OZjwK2VvUfDx-4NqOiNZacoGfCXhYA,26215
|
|
1230
|
+
vllm/worker/xpu_model_runner.py,sha256=_4-ioHBnFw4hx0WecoqGdudAjr5lUoqeowPuTbYme3s,24547
|
|
1231
|
+
vllm/worker/xpu_worker.py,sha256=NQ6h-2gjTmjEHUP2gPvOSaQFk3uOkRc2KFcz08ZpEhA,7990
|
|
1232
|
+
vllm_cpu-0.9.2.post2.dist-info/METADATA,sha256=Xlc7CoHwwI5vieFmQG3-3g3YAOn93WkRb5m25bI0S-8,16150
|
|
1233
|
+
vllm_cpu-0.9.2.post2.dist-info/WHEEL,sha256=mj6h_6Y3xNaeND8ADslYRBh2X-k6KwikXBL-DKxsDNk,114
|
|
1234
|
+
vllm_cpu-0.9.2.post2.dist-info/entry_points.txt,sha256=ErfiCUEEMrGDD3jBwf8c54AolBCFv7qrc8Ix9iqzzfs,184
|
|
1235
|
+
vllm_cpu-0.9.2.post2.dist-info/top_level.txt,sha256=fAgb8Pt4zQoKTUA3ZnKEIgcjh0L97_dwEjYDTL5MEEo,5
|
|
1236
|
+
vllm_cpu-0.9.2.post2.dist-info/RECORD,,
|