3583 lines
187 KiB
Plaintext
3583 lines
187 KiB
Plaintext
.clang-format
|
|
.coveragerc
|
|
.dockerignore
|
|
.git-blame-ignore-revs
|
|
.gitignore
|
|
.markdownlint.yaml
|
|
.pre-commit-config.yaml
|
|
.readthedocs.yaml
|
|
.shellcheckrc
|
|
.yapfignore
|
|
CMakeLists.txt
|
|
CODE_OF_CONDUCT.md
|
|
CONTRIBUTING.md
|
|
DCO
|
|
LICENSE
|
|
MANIFEST.in
|
|
README.md
|
|
RELEASE.md
|
|
SECURITY.md
|
|
codecov.yml
|
|
mkdocs.yaml
|
|
pyproject.toml
|
|
setup.py
|
|
use_existing_torch.py
|
|
.buildkite/check-wheel-size.py
|
|
.buildkite/ci_config.yaml
|
|
.buildkite/release-pipeline.yaml
|
|
.buildkite/test-amd.yaml
|
|
.buildkite/test-pipeline.yaml
|
|
.buildkite/image_build/image_build.sh
|
|
.buildkite/image_build/image_build.yaml
|
|
.buildkite/image_build/image_build_cpu.sh
|
|
.buildkite/image_build/image_build_cpu_arm64.sh
|
|
.buildkite/image_build/image_build_hpu.sh
|
|
.buildkite/lm-eval-harness/conftest.py
|
|
.buildkite/lm-eval-harness/run-lm-eval-chartqa-vllm-vlm-baseline.sh
|
|
.buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh
|
|
.buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh
|
|
.buildkite/lm-eval-harness/run-lm-eval-mmlupro-vllm-baseline.sh
|
|
.buildkite/lm-eval-harness/test_lm_eval_correctness.py
|
|
.buildkite/lm-eval-harness/configs/DeepSeek-V2-Lite-Chat.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3-70B-Instruct.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-Channelwise-compressed-tensors.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-FP8-compressed-tensors.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-FP8.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-INT8-compressed-tensors-asym.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-INT8-compressed-tensors.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct-nonuniform-compressed-tensors.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-QQQ.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3.2-1B-Instruct-FP8-compressed-tensors.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-3.2-1B-Instruct-INT8-compressed-tensors.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-4-Maverick-17B-128E-Instruct-FP8-MM.yaml
|
|
.buildkite/lm-eval-harness/configs/Meta-Llama-4-Maverick-17B-128E-Instruct-FP8.yaml
|
|
.buildkite/lm-eval-harness/configs/Minitron-4B-Base-FP8.yaml
|
|
.buildkite/lm-eval-harness/configs/Mixtral-8x22B-Instruct-v0.1-FP8-Dynamic.yaml
|
|
.buildkite/lm-eval-harness/configs/Mixtral-8x7B-Instruct-v0.1-FP8.yaml
|
|
.buildkite/lm-eval-harness/configs/Mixtral-8x7B-Instruct-v0.1.yaml
|
|
.buildkite/lm-eval-harness/configs/Qwen1.5-MoE-W4A16-compressed-tensors.yaml
|
|
.buildkite/lm-eval-harness/configs/Qwen2-1.5B-Instruct-FP8W8.yaml
|
|
.buildkite/lm-eval-harness/configs/Qwen2-1.5B-Instruct-INT8-compressed-tensors.yaml
|
|
.buildkite/lm-eval-harness/configs/Qwen2-57B-A14-Instruct.yaml
|
|
.buildkite/lm-eval-harness/configs/Qwen2.5-1.5B-Instruct.yaml
|
|
.buildkite/lm-eval-harness/configs/Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
|
|
.buildkite/lm-eval-harness/configs/Qwen2.5-VL-7B-Instruct.yaml
|
|
.buildkite/lm-eval-harness/configs/Qwen3-235B-A22B-Instruct-2507-FP8.yaml
|
|
.buildkite/lm-eval-harness/configs/SparseLlama3.1_2of4_fp8_compressed.yaml
|
|
.buildkite/lm-eval-harness/configs/models-large-hopper.txt
|
|
.buildkite/lm-eval-harness/configs/models-large-rocm.txt
|
|
.buildkite/lm-eval-harness/configs/models-large.txt
|
|
.buildkite/lm-eval-harness/configs/models-mm-large-h100.txt
|
|
.buildkite/lm-eval-harness/configs/models-mm-small.txt
|
|
.buildkite/lm-eval-harness/configs/models-small.txt
|
|
.buildkite/performance-benchmarks/README.md
|
|
.buildkite/performance-benchmarks/performance-benchmarks-descriptions.md
|
|
.buildkite/performance-benchmarks/scripts/compare-json-results.py
|
|
.buildkite/performance-benchmarks/scripts/convert-results-json-to-markdown.py
|
|
.buildkite/performance-benchmarks/scripts/launch-server.sh
|
|
.buildkite/performance-benchmarks/scripts/run-performance-benchmarks.sh
|
|
.buildkite/performance-benchmarks/tests/genai-perf-tests.json
|
|
.buildkite/performance-benchmarks/tests/latency-tests-cpu.json
|
|
.buildkite/performance-benchmarks/tests/latency-tests-hpu.json
|
|
.buildkite/performance-benchmarks/tests/latency-tests.json
|
|
.buildkite/performance-benchmarks/tests/nightly-tests.json
|
|
.buildkite/performance-benchmarks/tests/serving-tests-cpu.json
|
|
.buildkite/performance-benchmarks/tests/serving-tests-hpu.json
|
|
.buildkite/performance-benchmarks/tests/serving-tests.json
|
|
.buildkite/performance-benchmarks/tests/throughput-tests-cpu.json
|
|
.buildkite/performance-benchmarks/tests/throughput-tests-hpu.json
|
|
.buildkite/performance-benchmarks/tests/throughput-tests.json
|
|
.buildkite/scripts/annotate-release.sh
|
|
.buildkite/scripts/ci-clean-log.sh
|
|
.buildkite/scripts/cleanup-nightly-builds.sh
|
|
.buildkite/scripts/generate-nightly-index.py
|
|
.buildkite/scripts/rerun-test.sh
|
|
.buildkite/scripts/run-benchmarks.sh
|
|
.buildkite/scripts/run-multi-node-test.sh
|
|
.buildkite/scripts/run-prime-rl-test.sh
|
|
.buildkite/scripts/upload-wheels.sh
|
|
.buildkite/scripts/hardware_ci/run-amd-test.sh
|
|
.buildkite/scripts/hardware_ci/run-cpu-test-arm.sh
|
|
.buildkite/scripts/hardware_ci/run-cpu-test-ppc64le.sh
|
|
.buildkite/scripts/hardware_ci/run-cpu-test-s390x.sh
|
|
.buildkite/scripts/hardware_ci/run-cpu-test.sh
|
|
.buildkite/scripts/hardware_ci/run-gh200-test.sh
|
|
.buildkite/scripts/hardware_ci/run-hpu-test.sh
|
|
.buildkite/scripts/hardware_ci/run-npu-test.sh
|
|
.buildkite/scripts/hardware_ci/run-tpu-v1-test-part2.sh
|
|
.buildkite/scripts/hardware_ci/run-tpu-v1-test.sh
|
|
.buildkite/scripts/hardware_ci/run-xpu-test.sh
|
|
.buildkite/scripts/scheduled_integration_test/deepseek_v2_lite_ep_eplb.sh
|
|
.buildkite/scripts/scheduled_integration_test/qwen30b_a3b_fp8_block_ep_eplb.sh
|
|
.buildkite/scripts/scheduled_integration_test/qwen3_next_mtp_async_eplb.sh
|
|
.buildkite/scripts/tpu/cleanup_docker.sh
|
|
.buildkite/scripts/tpu/config_v6e_1.env
|
|
.buildkite/scripts/tpu/docker_run_bm.sh
|
|
.buildkite/scripts/tpu/quantized_v6e_1.env
|
|
.buildkite/scripts/tpu/run_bm.sh
|
|
.buildkite/test_areas/attention.yaml
|
|
.buildkite/test_areas/basic_correctness.yaml
|
|
.buildkite/test_areas/benchmarks.yaml
|
|
.buildkite/test_areas/compile.yaml
|
|
.buildkite/test_areas/cuda.yaml
|
|
.buildkite/test_areas/distributed.yaml
|
|
.buildkite/test_areas/e2e_integration.yaml
|
|
.buildkite/test_areas/engine.yaml
|
|
.buildkite/test_areas/entrypoints.yaml
|
|
.buildkite/test_areas/expert_parallelism.yaml
|
|
.buildkite/test_areas/kernels.yaml
|
|
.buildkite/test_areas/lm_eval.yaml
|
|
.buildkite/test_areas/lora.yaml
|
|
.buildkite/test_areas/misc.yaml
|
|
.buildkite/test_areas/model_executor.yaml
|
|
.buildkite/test_areas/models_basic.yaml
|
|
.buildkite/test_areas/models_distributed.yaml
|
|
.buildkite/test_areas/models_language.yaml
|
|
.buildkite/test_areas/models_multimodal.yaml
|
|
.buildkite/test_areas/plugins.yaml
|
|
.buildkite/test_areas/pytorch.yaml
|
|
.buildkite/test_areas/quantization.yaml
|
|
.buildkite/test_areas/samplers.yaml
|
|
.buildkite/test_areas/tool_use.yaml
|
|
.buildkite/test_areas/weight_loading.yaml
|
|
.gemini/config.yaml
|
|
.github/.bc-linter.yml
|
|
.github/CODEOWNERS
|
|
.github/FUNDING.yml
|
|
.github/PULL_REQUEST_TEMPLATE.md
|
|
.github/dependabot.yml
|
|
.github/mergify.yml
|
|
.github/scale-config.yml
|
|
.github/ISSUE_TEMPLATE/100-documentation.yml
|
|
.github/ISSUE_TEMPLATE/200-installation.yml
|
|
.github/ISSUE_TEMPLATE/300-usage.yml
|
|
.github/ISSUE_TEMPLATE/400-bug-report.yml
|
|
.github/ISSUE_TEMPLATE/450-ci-failure.yml
|
|
.github/ISSUE_TEMPLATE/500-feature-request.yml
|
|
.github/ISSUE_TEMPLATE/600-new-model.yml
|
|
.github/ISSUE_TEMPLATE/700-performance-discussion.yml
|
|
.github/ISSUE_TEMPLATE/750-RFC.yml
|
|
.github/ISSUE_TEMPLATE/config.yml
|
|
.github/scripts/cleanup_pr_body.sh
|
|
.github/workflows/add_label_automerge.yml
|
|
.github/workflows/bc-lint.yml
|
|
.github/workflows/cleanup_pr_body.yml
|
|
.github/workflows/issue_autolabel.yml
|
|
.github/workflows/macos-smoke-test.yml
|
|
.github/workflows/pre-commit.yml
|
|
.github/workflows/reminder_comment.yml
|
|
.github/workflows/stale.yml
|
|
.github/workflows/matchers/actionlint.json
|
|
.github/workflows/matchers/markdownlint.json
|
|
.github/workflows/matchers/mypy.json
|
|
.github/workflows/scripts/build.sh
|
|
.github/workflows/scripts/create_release.js
|
|
.github/workflows/scripts/cuda-install.sh
|
|
.github/workflows/scripts/env.sh
|
|
.github/workflows/scripts/pytorch-install.sh
|
|
benchmarks/README.md
|
|
benchmarks/backend_request_func.py
|
|
benchmarks/benchmark_batch_invariance.py
|
|
benchmarks/benchmark_block_pool.py
|
|
benchmarks/benchmark_hash.py
|
|
benchmarks/benchmark_latency.py
|
|
benchmarks/benchmark_long_document_qa_throughput.py
|
|
benchmarks/benchmark_ngram_proposer.py
|
|
benchmarks/benchmark_prefix_block_hash.py
|
|
benchmarks/benchmark_prefix_caching.py
|
|
benchmarks/benchmark_prioritization.py
|
|
benchmarks/benchmark_serving.py
|
|
benchmarks/benchmark_serving_structured_output.py
|
|
benchmarks/benchmark_throughput.py
|
|
benchmarks/benchmark_utils.py
|
|
benchmarks/run_structured_output_benchmark.sh
|
|
benchmarks/sonnet.txt
|
|
benchmarks/auto_tune/README.md
|
|
benchmarks/auto_tune/auto_tune.sh
|
|
benchmarks/auto_tune/batch_auto_tune.sh
|
|
benchmarks/cutlass_benchmarks/sparse_benchmarks.py
|
|
benchmarks/cutlass_benchmarks/utils.py
|
|
benchmarks/cutlass_benchmarks/w8a8_benchmarks.py
|
|
benchmarks/cutlass_benchmarks/weight_shapes.py
|
|
benchmarks/disagg_benchmarks/disagg_overhead_benchmark.sh
|
|
benchmarks/disagg_benchmarks/disagg_performance_benchmark.sh
|
|
benchmarks/disagg_benchmarks/disagg_prefill_proxy_server.py
|
|
benchmarks/disagg_benchmarks/rate_limiter.py
|
|
benchmarks/disagg_benchmarks/request_queue.py
|
|
benchmarks/disagg_benchmarks/round_robin_proxy.py
|
|
benchmarks/disagg_benchmarks/visualize_benchmark_results.py
|
|
benchmarks/fused_kernels/layernorm_rms_benchmarks.py
|
|
benchmarks/kernels/bench_block_fp8_gemm.py
|
|
benchmarks/kernels/bench_fp8_gemm.py
|
|
benchmarks/kernels/bench_int8_gemm.py
|
|
benchmarks/kernels/bench_mxfp4_qutlass.py
|
|
benchmarks/kernels/bench_nvfp4_gemm.py
|
|
benchmarks/kernels/bench_nvfp4_qutlass.py
|
|
benchmarks/kernels/bench_per_token_quant_fp8.py
|
|
benchmarks/kernels/benchmark_2d_silu_mul_fp8_quant.py
|
|
benchmarks/kernels/benchmark_activation.py
|
|
benchmarks/kernels/benchmark_bitblas.py
|
|
benchmarks/kernels/benchmark_cutlass_fp4_moe.py
|
|
benchmarks/kernels/benchmark_cutlass_moe_fp8.py
|
|
benchmarks/kernels/benchmark_device_communicators.py
|
|
benchmarks/kernels/benchmark_fused_collective.py
|
|
benchmarks/kernels/benchmark_grouped_gemm_cutlass.py
|
|
benchmarks/kernels/benchmark_layernorm.py
|
|
benchmarks/kernels/benchmark_lora.py
|
|
benchmarks/kernels/benchmark_machete.py
|
|
benchmarks/kernels/benchmark_marlin.py
|
|
benchmarks/kernels/benchmark_mla_k_concat.py
|
|
benchmarks/kernels/benchmark_moe.py
|
|
benchmarks/kernels/benchmark_moe_align_block_size.py
|
|
benchmarks/kernels/benchmark_moe_permute_unpermute.py
|
|
benchmarks/kernels/benchmark_mrope.py
|
|
benchmarks/kernels/benchmark_paged_attention.py
|
|
benchmarks/kernels/benchmark_per_token_group_quant.py
|
|
benchmarks/kernels/benchmark_quant.py
|
|
benchmarks/kernels/benchmark_reshape_and_cache.py
|
|
benchmarks/kernels/benchmark_reshape_and_cache_flash.py
|
|
benchmarks/kernels/benchmark_rmsnorm.py
|
|
benchmarks/kernels/benchmark_rope.py
|
|
benchmarks/kernels/benchmark_shapes.py
|
|
benchmarks/kernels/benchmark_silu_mul_fp8_quant.py
|
|
benchmarks/kernels/benchmark_trtllm_decode_attention.py
|
|
benchmarks/kernels/benchmark_trtllm_prefill_attention.py
|
|
benchmarks/kernels/benchmark_w8a8_block_fp8.py
|
|
benchmarks/kernels/graph_machete_bench.py
|
|
benchmarks/kernels/requirements.txt
|
|
benchmarks/kernels/utils.py
|
|
benchmarks/kernels/weight_shapes.py
|
|
benchmarks/kernels/deepgemm/README.md
|
|
benchmarks/kernels/deepgemm/benchmark_fp8_block_dense_gemm.py
|
|
benchmarks/multi_turn/README.md
|
|
benchmarks/multi_turn/bench_dataset.py
|
|
benchmarks/multi_turn/bench_utils.py
|
|
benchmarks/multi_turn/benchmark_serving_multi_turn.py
|
|
benchmarks/multi_turn/convert_sharegpt_to_openai.py
|
|
benchmarks/multi_turn/generate_multi_turn.json
|
|
benchmarks/multi_turn/requirements.txt
|
|
benchmarks/overheads/benchmark_hashing.py
|
|
benchmarks/structured_schemas/structured_schema_1.json
|
|
cmake/cpu_extension.cmake
|
|
cmake/hipify.py
|
|
cmake/utils.cmake
|
|
cmake/external_projects/flashmla.cmake
|
|
cmake/external_projects/qutlass.cmake
|
|
cmake/external_projects/triton_kernels.cmake
|
|
cmake/external_projects/vllm_flash_attn.cmake
|
|
csrc/activation_kernels.cu
|
|
csrc/cache.h
|
|
csrc/cache_kernels.cu
|
|
csrc/cub_helpers.h
|
|
csrc/cuda_compat.h
|
|
csrc/cuda_utils.h
|
|
csrc/cuda_utils_kernels.cu
|
|
csrc/cuda_view.cu
|
|
csrc/cumem_allocator.cpp
|
|
csrc/cumem_allocator_compat.h
|
|
csrc/custom_all_reduce.cu
|
|
csrc/custom_all_reduce.cuh
|
|
csrc/custom_all_reduce_test.cu
|
|
csrc/custom_quickreduce.cu
|
|
csrc/dispatch_utils.h
|
|
csrc/fused_qknorm_rope_kernel.cu
|
|
csrc/launch_bounds_utils.h
|
|
csrc/layernorm_kernels.cu
|
|
csrc/layernorm_quant_kernels.cu
|
|
csrc/ops.h
|
|
csrc/permute_cols.cu
|
|
csrc/pos_encoding_kernels.cu
|
|
csrc/sampler.cu
|
|
csrc/torch_bindings.cpp
|
|
csrc/type_convert.cuh
|
|
csrc/attention/attention_dtypes.h
|
|
csrc/attention/attention_generic.cuh
|
|
csrc/attention/attention_kernels.cuh
|
|
csrc/attention/attention_utils.cuh
|
|
csrc/attention/dtype_bfloat16.cuh
|
|
csrc/attention/dtype_float16.cuh
|
|
csrc/attention/dtype_float32.cuh
|
|
csrc/attention/dtype_fp8.cuh
|
|
csrc/attention/merge_attn_states.cu
|
|
csrc/attention/paged_attention_v1.cu
|
|
csrc/attention/paged_attention_v2.cu
|
|
csrc/attention/vertical_slash_index.cu
|
|
csrc/attention/mla/sm100_cutlass_mla_kernel.cu
|
|
csrc/attention/mla/cutlass_sm100_mla/device/sm100_mla.hpp
|
|
csrc/attention/mla/cutlass_sm100_mla/kernel/sm100_fmha_mla_reduction.hpp
|
|
csrc/attention/mla/cutlass_sm100_mla/kernel/sm100_fmha_mla_tma_warpspecialized.hpp
|
|
csrc/attention/mla/cutlass_sm100_mla/kernel/sm100_mla_tile_scheduler.hpp
|
|
csrc/core/batch_invariant.hpp
|
|
csrc/core/exception.hpp
|
|
csrc/core/math.hpp
|
|
csrc/core/registration.h
|
|
csrc/core/scalar_type.hpp
|
|
csrc/cpu/activation.cpp
|
|
csrc/cpu/cpu_attn.cpp
|
|
csrc/cpu/cpu_attn_amx.hpp
|
|
csrc/cpu/cpu_attn_impl.hpp
|
|
csrc/cpu/cpu_attn_macros.h
|
|
csrc/cpu/cpu_attn_neon.hpp
|
|
csrc/cpu/cpu_attn_vec.hpp
|
|
csrc/cpu/cpu_attn_vec16.hpp
|
|
csrc/cpu/cpu_types.hpp
|
|
csrc/cpu/cpu_types_arm.hpp
|
|
csrc/cpu/cpu_types_scalar.hpp
|
|
csrc/cpu/cpu_types_vsx.hpp
|
|
csrc/cpu/cpu_types_vxe.hpp
|
|
csrc/cpu/cpu_types_x86.hpp
|
|
csrc/cpu/cpu_wna16.cpp
|
|
csrc/cpu/dnnl_helper.cpp
|
|
csrc/cpu/dnnl_helper.h
|
|
csrc/cpu/dnnl_kernels.cpp
|
|
csrc/cpu/float_convert.hpp
|
|
csrc/cpu/layernorm.cpp
|
|
csrc/cpu/mla_decode.cpp
|
|
csrc/cpu/pos_encoding.cpp
|
|
csrc/cpu/scratchpad_manager.cpp
|
|
csrc/cpu/scratchpad_manager.h
|
|
csrc/cpu/shm.cpp
|
|
csrc/cpu/torch_bindings.cpp
|
|
csrc/cpu/utils.cpp
|
|
csrc/cpu/utils.hpp
|
|
csrc/cpu/micro_gemm/cpu_micro_gemm_amx.hpp
|
|
csrc/cpu/micro_gemm/cpu_micro_gemm_impl.hpp
|
|
csrc/cpu/micro_gemm/cpu_micro_gemm_vec.hpp
|
|
csrc/cpu/sgl-kernels/common.h
|
|
csrc/cpu/sgl-kernels/gemm.cpp
|
|
csrc/cpu/sgl-kernels/gemm.h
|
|
csrc/cpu/sgl-kernels/gemm_fp8.cpp
|
|
csrc/cpu/sgl-kernels/gemm_int8.cpp
|
|
csrc/cpu/sgl-kernels/moe.cpp
|
|
csrc/cpu/sgl-kernels/moe_fp8.cpp
|
|
csrc/cpu/sgl-kernels/moe_int8.cpp
|
|
csrc/cpu/sgl-kernels/vec.h
|
|
csrc/cutlass_extensions/common.cpp
|
|
csrc/cutlass_extensions/common.hpp
|
|
csrc/cutlass_extensions/cute_utils.cuh
|
|
csrc/cutlass_extensions/torch_utils.hpp
|
|
csrc/cutlass_extensions/vllm_collective_builder.cuh
|
|
csrc/cutlass_extensions/vllm_custom_types.cuh
|
|
csrc/cutlass_extensions/vllm_cutlass_library_extension.py
|
|
csrc/cutlass_extensions/vllm_numeric_conversion.cuh
|
|
csrc/cutlass_extensions/vllm_type_utils.cuh
|
|
csrc/cutlass_extensions/epilogue/broadcast_load_epilogue_array_c3x.hpp
|
|
csrc/cutlass_extensions/epilogue/broadcast_load_epilogue_c2x.hpp
|
|
csrc/cutlass_extensions/epilogue/broadcast_load_epilogue_c3x.hpp
|
|
csrc/cutlass_extensions/epilogue/scaled_mm_epilogues_c2x.hpp
|
|
csrc/cutlass_extensions/epilogue/scaled_mm_epilogues_c3x.hpp
|
|
csrc/mamba/mamba_ssm/selective_scan.h
|
|
csrc/mamba/mamba_ssm/selective_scan_fwd.cu
|
|
csrc/mamba/mamba_ssm/static_switch.h
|
|
csrc/moe/dynamic_4bit_int_moe_cpu.cpp
|
|
csrc/moe/grouped_topk_kernels.cu
|
|
csrc/moe/moe_align_sum_kernels.cu
|
|
csrc/moe/moe_ops.h
|
|
csrc/moe/moe_permute_unpermute_op.cu
|
|
csrc/moe/moe_wna16.cu
|
|
csrc/moe/moe_wna16_utils.h
|
|
csrc/moe/topk_softmax_kernels.cu
|
|
csrc/moe/torch_bindings.cpp
|
|
csrc/moe/marlin_moe_wna16/.gitignore
|
|
csrc/moe/marlin_moe_wna16/generate_kernels.py
|
|
csrc/moe/marlin_moe_wna16/kernel.h
|
|
csrc/moe/marlin_moe_wna16/marlin_template.h
|
|
csrc/moe/marlin_moe_wna16/ops.cu
|
|
csrc/moe/permute_unpermute_kernels/dispatch.h
|
|
csrc/moe/permute_unpermute_kernels/moe_permute_unpermute_kernel.cu
|
|
csrc/moe/permute_unpermute_kernels/moe_permute_unpermute_kernel.h
|
|
csrc/moe/permute_unpermute_kernels/moe_permute_unpermute_kernel.inl
|
|
csrc/quantization/activation_kernels.cu
|
|
csrc/quantization/utils.cuh
|
|
csrc/quantization/vectorization.cuh
|
|
csrc/quantization/vectorization_utils.cuh
|
|
csrc/quantization/awq/dequantize.cuh
|
|
csrc/quantization/awq/gemm_kernels.cu
|
|
csrc/quantization/cutlass_w4a8/get_group_starts.cuh
|
|
csrc/quantization/cutlass_w4a8/w4a8_grouped_mm_entry.cu
|
|
csrc/quantization/cutlass_w4a8/w4a8_mm_entry.cu
|
|
csrc/quantization/cutlass_w4a8/w4a8_utils.cu
|
|
csrc/quantization/cutlass_w4a8/w4a8_utils.cuh
|
|
csrc/quantization/fp4/activation_nvfp4_quant_fusion_kernels.cu
|
|
csrc/quantization/fp4/nvfp4_blockwise_moe_kernel.cu
|
|
csrc/quantization/fp4/nvfp4_experts_quant.cu
|
|
csrc/quantization/fp4/nvfp4_quant_entry.cu
|
|
csrc/quantization/fp4/nvfp4_quant_kernels.cu
|
|
csrc/quantization/fp4/nvfp4_scaled_mm_entry.cu
|
|
csrc/quantization/fp4/nvfp4_scaled_mm_kernels.cu
|
|
csrc/quantization/fp4/nvfp4_scaled_mm_sm120_kernels.cu
|
|
csrc/quantization/fp4/nvfp4_utils.cuh
|
|
csrc/quantization/fused_kernels/fused_layernorm_dynamic_per_token_quant.cu
|
|
csrc/quantization/fused_kernels/layernorm_utils.cuh
|
|
csrc/quantization/fused_kernels/quant_conversions.cuh
|
|
csrc/quantization/gguf/dequantize.cuh
|
|
csrc/quantization/gguf/ggml-common.h
|
|
csrc/quantization/gguf/gguf_kernel.cu
|
|
csrc/quantization/gguf/mmq.cuh
|
|
csrc/quantization/gguf/mmvq.cuh
|
|
csrc/quantization/gguf/moe.cuh
|
|
csrc/quantization/gguf/moe_vec.cuh
|
|
csrc/quantization/gguf/vecdotq.cuh
|
|
csrc/quantization/gptq/compat.cuh
|
|
csrc/quantization/gptq/matrix_view.cuh
|
|
csrc/quantization/gptq/q_gemm.cu
|
|
csrc/quantization/gptq/qdq_2.cuh
|
|
csrc/quantization/gptq/qdq_3.cuh
|
|
csrc/quantization/gptq/qdq_4.cuh
|
|
csrc/quantization/gptq/qdq_8.cuh
|
|
csrc/quantization/gptq/qdq_util.cuh
|
|
csrc/quantization/gptq_allspark/allspark_qgemm_w8a16.cu
|
|
csrc/quantization/gptq_allspark/allspark_repack.cu
|
|
csrc/quantization/gptq_allspark/allspark_utils.cuh
|
|
csrc/quantization/gptq_marlin/.gitignore
|
|
csrc/quantization/gptq_marlin/awq_marlin_repack.cu
|
|
csrc/quantization/gptq_marlin/dequant.h
|
|
csrc/quantization/gptq_marlin/generate_kernels.py
|
|
csrc/quantization/gptq_marlin/gptq_marlin.cu
|
|
csrc/quantization/gptq_marlin/gptq_marlin_repack.cu
|
|
csrc/quantization/gptq_marlin/kernel.h
|
|
csrc/quantization/gptq_marlin/marlin.cuh
|
|
csrc/quantization/gptq_marlin/marlin_dtypes.cuh
|
|
csrc/quantization/gptq_marlin/marlin_int4_fp8_preprocess.cu
|
|
csrc/quantization/gptq_marlin/marlin_template.h
|
|
csrc/quantization/hadamard/hadacore/hadamard_transform_cuda.cu
|
|
csrc/quantization/machete/Readme.md
|
|
csrc/quantization/machete/generate.py
|
|
csrc/quantization/machete/machete_collective_builder.cuh
|
|
csrc/quantization/machete/machete_interleaving_utils.cuh
|
|
csrc/quantization/machete/machete_mainloop.cuh
|
|
csrc/quantization/machete/machete_mm_kernel.cuh
|
|
csrc/quantization/machete/machete_mm_launcher.cuh
|
|
csrc/quantization/machete/machete_prepack_kernel.cuh
|
|
csrc/quantization/machete/machete_prepack_launcher.cuh
|
|
csrc/quantization/machete/machete_prepacked_layout.cuh
|
|
csrc/quantization/machete/machete_pytorch.cu
|
|
csrc/quantization/marlin/sparse/LICENSE
|
|
csrc/quantization/marlin/sparse/marlin_24_cuda_kernel.cu
|
|
csrc/quantization/marlin/sparse/common/base.h
|
|
csrc/quantization/marlin/sparse/common/mem.h
|
|
csrc/quantization/marlin/sparse/common/mma.h
|
|
csrc/quantization/w8a8/per_token_group_quant_8bit.h
|
|
csrc/quantization/w8a8/cutlass/Epilogues.md
|
|
csrc/quantization/w8a8/cutlass/scaled_mm_c2x.cu
|
|
csrc/quantization/w8a8/cutlass/scaled_mm_c2x.cuh
|
|
csrc/quantization/w8a8/cutlass/scaled_mm_c2x_sm75_dispatch.cuh
|
|
csrc/quantization/w8a8/cutlass/scaled_mm_c2x_sm80_dispatch.cuh
|
|
csrc/quantization/w8a8/cutlass/scaled_mm_c2x_sm89_fp8_dispatch.cuh
|
|
csrc/quantization/w8a8/cutlass/scaled_mm_c2x_sm89_int8_dispatch.cuh
|
|
csrc/quantization/w8a8/cutlass/scaled_mm_c3x_sm100.cu
|
|
csrc/quantization/w8a8/cutlass/scaled_mm_c3x_sm120.cu
|
|
csrc/quantization/w8a8/cutlass/scaled_mm_c3x_sm90.cu
|
|
csrc/quantization/w8a8/cutlass/scaled_mm_entry.cu
|
|
csrc/quantization/w8a8/cutlass/c3x/cutlass_gemm_caller.cuh
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm.cuh
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_azp_sm90_int8.cu
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm100_fp8.cu
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm100_fp8_dispatch.cuh
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm120_fp8.cu
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm120_fp8_dispatch.cuh
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm90_fp8.cu
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_blockwise_sm90_fp8_dispatch.cuh
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_helper.hpp
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_kernels.hpp
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm100_fp8.cu
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm100_fp8_dispatch.cuh
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm120_fp8.cu
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm120_fp8_dispatch.cuh
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm90_fp8.cu
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm90_fp8_dispatch.cuh
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm90_int8.cu
|
|
csrc/quantization/w8a8/cutlass/c3x/scaled_mm_sm90_int8_dispatch.cuh
|
|
csrc/quantization/w8a8/cutlass/moe/blockwise_scaled_group_mm_sm100.cu
|
|
csrc/quantization/w8a8/cutlass/moe/get_group_starts.cuh
|
|
csrc/quantization/w8a8/cutlass/moe/grouped_mm_c3x.cuh
|
|
csrc/quantization/w8a8/cutlass/moe/grouped_mm_c3x_sm100.cu
|
|
csrc/quantization/w8a8/cutlass/moe/grouped_mm_c3x_sm90.cu
|
|
csrc/quantization/w8a8/cutlass/moe/moe_data.cu
|
|
csrc/quantization/w8a8/fp8/common.cu
|
|
csrc/quantization/w8a8/fp8/common.cuh
|
|
csrc/quantization/w8a8/fp8/per_token_group_quant.cu
|
|
csrc/quantization/w8a8/fp8/amd/quant_utils.cuh
|
|
csrc/quantization/w8a8/fp8/nvidia/quant_utils.cuh
|
|
csrc/quantization/w8a8/int8/per_token_group_quant.cu
|
|
csrc/quantization/w8a8/int8/scaled_quant.cu
|
|
csrc/quickreduce/base.h
|
|
csrc/quickreduce/quick_reduce.h
|
|
csrc/quickreduce/quick_reduce_impl.cuh
|
|
csrc/rocm/attention.cu
|
|
csrc/rocm/ops.h
|
|
csrc/rocm/skinny_gemms.cu
|
|
csrc/rocm/torch_bindings.cpp
|
|
csrc/sparse/cutlass/sparse_compressor_c3x.cuh
|
|
csrc/sparse/cutlass/sparse_scaled_mm_c3x.cu
|
|
csrc/sparse/cutlass/sparse_scaled_mm_c3x.cuh
|
|
csrc/sparse/cutlass/sparse_scaled_mm_entry.cu
|
|
docker/Dockerfile
|
|
docker/Dockerfile.cpu
|
|
docker/Dockerfile.nightly_torch
|
|
docker/Dockerfile.ppc64le
|
|
docker/Dockerfile.rocm
|
|
docker/Dockerfile.rocm_base
|
|
docker/Dockerfile.s390x
|
|
docker/Dockerfile.tpu
|
|
docker/Dockerfile.xpu
|
|
docs/.nav.yml
|
|
docs/README.md
|
|
docs/api/README.md
|
|
docs/api/vllm/.meta.yml
|
|
docs/assets/contributing/dockerfile-stages-dependency.png
|
|
docs/assets/contributing/load-pattern-examples.png
|
|
docs/assets/deployment/anything-llm-chat-with-doc.png
|
|
docs/assets/deployment/anything-llm-chat-without-doc.png
|
|
docs/assets/deployment/anything-llm-provider.png
|
|
docs/assets/deployment/anything-llm-upload-doc.png
|
|
docs/assets/deployment/architecture_helm_deployment.png
|
|
docs/assets/deployment/chatbox-chat.png
|
|
docs/assets/deployment/chatbox-settings.png
|
|
docs/assets/deployment/dify-chat.png
|
|
docs/assets/deployment/dify-create-chatbot.png
|
|
docs/assets/deployment/dify-settings.png
|
|
docs/assets/deployment/dp_external_lb.png
|
|
docs/assets/deployment/dp_internal_lb.png
|
|
docs/assets/deployment/hf-inference-endpoints-catalog.png
|
|
docs/assets/deployment/hf-inference-endpoints-choose-infra.png
|
|
docs/assets/deployment/hf-inference-endpoints-click-deploy-button.png
|
|
docs/assets/deployment/hf-inference-endpoints-configure-container.png
|
|
docs/assets/deployment/hf-inference-endpoints-create-endpoint.png
|
|
docs/assets/deployment/hf-inference-endpoints-locate-deploy-button.png
|
|
docs/assets/deployment/hf-inference-endpoints-new-endpoint.png
|
|
docs/assets/deployment/hf-inference-endpoints-select-hardware.png
|
|
docs/assets/deployment/hf-inference-endpoints-select-model.png
|
|
docs/assets/deployment/open_webui.png
|
|
docs/assets/deployment/streamlit-chat.png
|
|
docs/assets/design/hierarchy.png
|
|
docs/assets/design/arch_overview/entrypoints.excalidraw.png
|
|
docs/assets/design/arch_overview/llm_engine.excalidraw.png
|
|
docs/assets/design/cuda_graphs/current_design.png
|
|
docs/assets/design/cuda_graphs/executor_runtime.png
|
|
docs/assets/design/cuda_graphs/previous_design.png
|
|
docs/assets/design/cuda_graphs/wrapper_flow.png
|
|
docs/assets/design/debug_vllm_compile/design_diagram.png
|
|
docs/assets/design/debug_vllm_compile/dynamic_shapes.png
|
|
docs/assets/design/debug_vllm_compile/tlparse_inductor.png
|
|
docs/assets/design/fused_moe_modular_kernel/fused_experts_blocks.png
|
|
docs/assets/design/fused_moe_modular_kernel/fused_moe_batched.png
|
|
docs/assets/design/fused_moe_modular_kernel/fused_moe_non_batched.png
|
|
docs/assets/design/fused_moe_modular_kernel/prepare_and_finalize_blocks.png
|
|
docs/assets/design/hybrid_kv_cache_manager/basic_grouping_example.png
|
|
docs/assets/design/hybrid_kv_cache_manager/full_attn.png
|
|
docs/assets/design/hybrid_kv_cache_manager/memory_layout.png
|
|
docs/assets/design/hybrid_kv_cache_manager/overview.png
|
|
docs/assets/design/hybrid_kv_cache_manager/sw_attn.png
|
|
docs/assets/design/metrics/intervals-1.png
|
|
docs/assets/design/metrics/intervals-2.png
|
|
docs/assets/design/metrics/intervals-3.png
|
|
docs/assets/design/paged_attention/k_vecs.png
|
|
docs/assets/design/paged_attention/key.png
|
|
docs/assets/design/paged_attention/logits_vec.png
|
|
docs/assets/design/paged_attention/q_vecs.png
|
|
docs/assets/design/paged_attention/query.png
|
|
docs/assets/design/paged_attention/v_vec.png
|
|
docs/assets/design/paged_attention/value.png
|
|
docs/assets/design/prefix_caching/example-time-1.png
|
|
docs/assets/design/prefix_caching/example-time-3.png
|
|
docs/assets/design/prefix_caching/example-time-4.png
|
|
docs/assets/design/prefix_caching/example-time-5.png
|
|
docs/assets/design/prefix_caching/example-time-6.png
|
|
docs/assets/design/prefix_caching/example-time-7.png
|
|
docs/assets/design/prefix_caching/free.png
|
|
docs/assets/design/prefix_caching/overview.png
|
|
docs/assets/design/tpu/most_model_len.png
|
|
docs/assets/features/disagg_encoder/disagg_encoder_flow.png
|
|
docs/assets/features/disagg_prefill/abstraction.jpg
|
|
docs/assets/features/disagg_prefill/high_level_design.png
|
|
docs/assets/features/disagg_prefill/overview.jpg
|
|
docs/assets/features/disagg_prefill/workflow.png
|
|
docs/assets/logos/vllm-logo-only-light.ico
|
|
docs/assets/logos/vllm-logo-only-light.png
|
|
docs/assets/logos/vllm-logo-text-dark.png
|
|
docs/assets/logos/vllm-logo-text-light.png
|
|
docs/benchmarking/README.md
|
|
docs/benchmarking/cli.md
|
|
docs/benchmarking/dashboard.md
|
|
docs/benchmarking/sweeps.md
|
|
docs/cli/.meta.yml
|
|
docs/cli/.nav.yml
|
|
docs/cli/README.md
|
|
docs/cli/chat.md
|
|
docs/cli/complete.md
|
|
docs/cli/json_tip.inc.md
|
|
docs/cli/run-batch.md
|
|
docs/cli/serve.md
|
|
docs/cli/bench/latency.md
|
|
docs/cli/bench/serve.md
|
|
docs/cli/bench/throughput.md
|
|
docs/cli/bench/sweep/plot.md
|
|
docs/cli/bench/sweep/plot_pareto.md
|
|
docs/cli/bench/sweep/serve.md
|
|
docs/cli/bench/sweep/serve_sla.md
|
|
docs/community/contact_us.md
|
|
docs/community/meetups.md
|
|
docs/community/sponsors.md
|
|
docs/configuration/README.md
|
|
docs/configuration/conserving_memory.md
|
|
docs/configuration/engine_args.md
|
|
docs/configuration/env_vars.md
|
|
docs/configuration/model_resolution.md
|
|
docs/configuration/optimization.md
|
|
docs/configuration/serve_args.md
|
|
docs/contributing/README.md
|
|
docs/contributing/deprecation_policy.md
|
|
docs/contributing/incremental_build.md
|
|
docs/contributing/profiling.md
|
|
docs/contributing/vulnerability_management.md
|
|
docs/contributing/ci/failures.md
|
|
docs/contributing/ci/nightly_builds.md
|
|
docs/contributing/ci/update_pytorch_version.md
|
|
docs/contributing/dockerfile/dockerfile.md
|
|
docs/contributing/model/README.md
|
|
docs/contributing/model/basic.md
|
|
docs/contributing/model/multimodal.md
|
|
docs/contributing/model/registration.md
|
|
docs/contributing/model/tests.md
|
|
docs/contributing/model/transcription.md
|
|
docs/deployment/docker.md
|
|
docs/deployment/k8s.md
|
|
docs/deployment/nginx.md
|
|
docs/deployment/frameworks/anyscale.md
|
|
docs/deployment/frameworks/anything-llm.md
|
|
docs/deployment/frameworks/autogen.md
|
|
docs/deployment/frameworks/bentoml.md
|
|
docs/deployment/frameworks/cerebrium.md
|
|
docs/deployment/frameworks/chatbox.md
|
|
docs/deployment/frameworks/dify.md
|
|
docs/deployment/frameworks/dstack.md
|
|
docs/deployment/frameworks/haystack.md
|
|
docs/deployment/frameworks/helm.md
|
|
docs/deployment/frameworks/hf_inference_endpoints.md
|
|
docs/deployment/frameworks/litellm.md
|
|
docs/deployment/frameworks/lobe-chat.md
|
|
docs/deployment/frameworks/lws.md
|
|
docs/deployment/frameworks/modal.md
|
|
docs/deployment/frameworks/open-webui.md
|
|
docs/deployment/frameworks/retrieval_augmented_generation.md
|
|
docs/deployment/frameworks/skypilot.md
|
|
docs/deployment/frameworks/streamlit.md
|
|
docs/deployment/frameworks/triton.md
|
|
docs/deployment/integrations/kaito.md
|
|
docs/deployment/integrations/kserve.md
|
|
docs/deployment/integrations/kthena.md
|
|
docs/deployment/integrations/kubeai.md
|
|
docs/deployment/integrations/kuberay.md
|
|
docs/deployment/integrations/llamastack.md
|
|
docs/deployment/integrations/llmaz.md
|
|
docs/deployment/integrations/production-stack.md
|
|
docs/design/arch_overview.md
|
|
docs/design/cuda_graphs.md
|
|
docs/design/dbo.md
|
|
docs/design/debug_vllm_compile.md
|
|
docs/design/fused_moe_modular_kernel.md
|
|
docs/design/huggingface_integration.md
|
|
docs/design/hybrid_kv_cache_manager.md
|
|
docs/design/io_processor_plugins.md
|
|
docs/design/logits_processors.md
|
|
docs/design/lora_resolver_plugins.md
|
|
docs/design/metrics.md
|
|
docs/design/mm_processing.md
|
|
docs/design/moe_kernel_features.md
|
|
docs/design/multiprocessing.md
|
|
docs/design/optimization_levels.md
|
|
docs/design/p2p_nccl_connector.md
|
|
docs/design/paged_attention.md
|
|
docs/design/plugin_system.md
|
|
docs/design/prefix_caching.md
|
|
docs/design/torch_compile.md
|
|
docs/examples/README.md
|
|
docs/features/README.md
|
|
docs/features/automatic_prefix_caching.md
|
|
docs/features/batch_invariance.md
|
|
docs/features/custom_arguments.md
|
|
docs/features/custom_logitsprocs.md
|
|
docs/features/disagg_encoder.md
|
|
docs/features/disagg_prefill.md
|
|
docs/features/interleaved_thinking.md
|
|
docs/features/lora.md
|
|
docs/features/mooncake_connector_usage.md
|
|
docs/features/multimodal_inputs.md
|
|
docs/features/nixl_connector_usage.md
|
|
docs/features/prompt_embeds.md
|
|
docs/features/reasoning_outputs.md
|
|
docs/features/sleep_mode.md
|
|
docs/features/spec_decode.md
|
|
docs/features/structured_outputs.md
|
|
docs/features/tool_calling.md
|
|
docs/features/quantization/README.md
|
|
docs/features/quantization/auto_awq.md
|
|
docs/features/quantization/auto_round.md
|
|
docs/features/quantization/bitblas.md
|
|
docs/features/quantization/bnb.md
|
|
docs/features/quantization/fp8.md
|
|
docs/features/quantization/gguf.md
|
|
docs/features/quantization/gptqmodel.md
|
|
docs/features/quantization/inc.md
|
|
docs/features/quantization/int4.md
|
|
docs/features/quantization/int8.md
|
|
docs/features/quantization/modelopt.md
|
|
docs/features/quantization/quantized_kvcache.md
|
|
docs/features/quantization/quark.md
|
|
docs/features/quantization/torchao.md
|
|
docs/getting_started/quickstart.md
|
|
docs/getting_started/installation/.nav.yml
|
|
docs/getting_started/installation/README.md
|
|
docs/getting_started/installation/cpu.apple.inc.md
|
|
docs/getting_started/installation/cpu.arm.inc.md
|
|
docs/getting_started/installation/cpu.md
|
|
docs/getting_started/installation/cpu.s390x.inc.md
|
|
docs/getting_started/installation/cpu.x86.inc.md
|
|
docs/getting_started/installation/device.template.md
|
|
docs/getting_started/installation/gpu.cuda.inc.md
|
|
docs/getting_started/installation/gpu.md
|
|
docs/getting_started/installation/gpu.rocm.inc.md
|
|
docs/getting_started/installation/gpu.xpu.inc.md
|
|
docs/getting_started/installation/python_env_setup.inc.md
|
|
docs/governance/collaboration.md
|
|
docs/governance/committers.md
|
|
docs/governance/process.md
|
|
docs/mkdocs/hooks/generate_argparse.py
|
|
docs/mkdocs/hooks/generate_examples.py
|
|
docs/mkdocs/hooks/generate_metrics.py
|
|
docs/mkdocs/hooks/remove_announcement.py
|
|
docs/mkdocs/hooks/url_schemes.py
|
|
docs/mkdocs/javascript/edit_and_feedback.js
|
|
docs/mkdocs/javascript/mathjax.js
|
|
docs/mkdocs/javascript/run_llm_widget.js
|
|
docs/mkdocs/javascript/slack_and_forum.js
|
|
docs/mkdocs/overrides/main.html
|
|
docs/mkdocs/overrides/partials/toc-item.html
|
|
docs/mkdocs/stylesheets/extra.css
|
|
docs/models/generative_models.md
|
|
docs/models/pooling_models.md
|
|
docs/models/supported_models.md
|
|
docs/models/extensions/fastsafetensor.md
|
|
docs/models/extensions/runai_model_streamer.md
|
|
docs/models/extensions/tensorizer.md
|
|
docs/models/hardware_supported_models/cpu.md
|
|
docs/models/hardware_supported_models/xpu.md
|
|
docs/serving/context_parallel_deployment.md
|
|
docs/serving/data_parallel_deployment.md
|
|
docs/serving/distributed_troubleshooting.md
|
|
docs/serving/expert_parallel_deployment.md
|
|
docs/serving/offline_inference.md
|
|
docs/serving/openai_compatible_server.md
|
|
docs/serving/parallelism_scaling.md
|
|
docs/serving/integrations/langchain.md
|
|
docs/serving/integrations/llamaindex.md
|
|
docs/training/rlhf.md
|
|
docs/training/trl.md
|
|
docs/usage/README.md
|
|
docs/usage/faq.md
|
|
docs/usage/metrics.md
|
|
docs/usage/reproducibility.md
|
|
docs/usage/security.md
|
|
docs/usage/troubleshooting.md
|
|
docs/usage/usage_stats.md
|
|
docs/usage/v1_guide.md
|
|
examples/template_alpaca.jinja
|
|
examples/template_baichuan.jinja
|
|
examples/template_chatglm.jinja
|
|
examples/template_chatglm2.jinja
|
|
examples/template_chatml.jinja
|
|
examples/template_dse_qwen2_vl.jinja
|
|
examples/template_falcon.jinja
|
|
examples/template_falcon_180b.jinja
|
|
examples/template_inkbot.jinja
|
|
examples/template_teleflm.jinja
|
|
examples/template_vlm2vec_phi3v.jinja
|
|
examples/template_vlm2vec_qwen2vl.jinja
|
|
examples/tool_chat_template_deepseekr1.jinja
|
|
examples/tool_chat_template_deepseekv3.jinja
|
|
examples/tool_chat_template_deepseekv31.jinja
|
|
examples/tool_chat_template_gemma3_pythonic.jinja
|
|
examples/tool_chat_template_granite.jinja
|
|
examples/tool_chat_template_granite_20b_fc.jinja
|
|
examples/tool_chat_template_hermes.jinja
|
|
examples/tool_chat_template_hunyuan_a13b.jinja
|
|
examples/tool_chat_template_internlm2_tool.jinja
|
|
examples/tool_chat_template_llama3.1_json.jinja
|
|
examples/tool_chat_template_llama3.2_json.jinja
|
|
examples/tool_chat_template_llama3.2_pythonic.jinja
|
|
examples/tool_chat_template_llama4_json.jinja
|
|
examples/tool_chat_template_llama4_pythonic.jinja
|
|
examples/tool_chat_template_minimax_m1.jinja
|
|
examples/tool_chat_template_mistral.jinja
|
|
examples/tool_chat_template_mistral3.jinja
|
|
examples/tool_chat_template_mistral_parallel.jinja
|
|
examples/tool_chat_template_phi4_mini.jinja
|
|
examples/tool_chat_template_qwen3coder.jinja
|
|
examples/tool_chat_template_toolace.jinja
|
|
examples/tool_chat_template_xlam_llama.jinja
|
|
examples/tool_chat_template_xlam_qwen.jinja
|
|
examples/offline_inference/async_llm_streaming.py
|
|
examples/offline_inference/audio_language.py
|
|
examples/offline_inference/automatic_prefix_caching.py
|
|
examples/offline_inference/batch_llm_inference.py
|
|
examples/offline_inference/chat_with_tools.py
|
|
examples/offline_inference/context_extension.py
|
|
examples/offline_inference/data_parallel.py
|
|
examples/offline_inference/disaggregated_prefill.py
|
|
examples/offline_inference/encoder_decoder_multimodal.py
|
|
examples/offline_inference/llm_engine_example.py
|
|
examples/offline_inference/llm_engine_reset_kv.py
|
|
examples/offline_inference/load_sharded_state.py
|
|
examples/offline_inference/lora_with_quantization_inference.py
|
|
examples/offline_inference/metrics.py
|
|
examples/offline_inference/mistral-small.py
|
|
examples/offline_inference/mlpspeculator.py
|
|
examples/offline_inference/multilora_inference.py
|
|
examples/offline_inference/prefix_caching.py
|
|
examples/offline_inference/prompt_embed_inference.py
|
|
examples/offline_inference/qwen_1m.py
|
|
examples/offline_inference/reproducibility.py
|
|
examples/offline_inference/rlhf.py
|
|
examples/offline_inference/rlhf_colocate.py
|
|
examples/offline_inference/rlhf_online_quant.py
|
|
examples/offline_inference/rlhf_utils.py
|
|
examples/offline_inference/save_sharded_state.py
|
|
examples/offline_inference/simple_profiling.py
|
|
examples/offline_inference/skip_loading_weights_in_engine_init.py
|
|
examples/offline_inference/spec_decode.py
|
|
examples/offline_inference/structured_outputs.py
|
|
examples/offline_inference/torchrun_dp_example.py
|
|
examples/offline_inference/torchrun_example.py
|
|
examples/offline_inference/vision_language.py
|
|
examples/offline_inference/vision_language_multi_image.py
|
|
examples/offline_inference/basic/README.md
|
|
examples/offline_inference/basic/basic.py
|
|
examples/offline_inference/basic/chat.py
|
|
examples/offline_inference/basic/classify.py
|
|
examples/offline_inference/basic/embed.py
|
|
examples/offline_inference/basic/generate.py
|
|
examples/offline_inference/basic/reward.py
|
|
examples/offline_inference/basic/score.py
|
|
examples/offline_inference/disaggregated-prefill-v1/README.md
|
|
examples/offline_inference/disaggregated-prefill-v1/decode_example.py
|
|
examples/offline_inference/disaggregated-prefill-v1/prefill_example.py
|
|
examples/offline_inference/disaggregated-prefill-v1/run.sh
|
|
examples/offline_inference/kv_load_failure_recovery/README.md
|
|
examples/offline_inference/kv_load_failure_recovery/decode_example.py
|
|
examples/offline_inference/kv_load_failure_recovery/load_recovery_example_connector.py
|
|
examples/offline_inference/kv_load_failure_recovery/prefill_example.py
|
|
examples/offline_inference/kv_load_failure_recovery/run.sh
|
|
examples/offline_inference/logits_processor/custom.py
|
|
examples/offline_inference/logits_processor/custom_req.py
|
|
examples/offline_inference/logits_processor/custom_req_init.py
|
|
examples/offline_inference/openai_batch/README.md
|
|
examples/offline_inference/openai_batch/openai_example_batch.jsonl
|
|
examples/offline_inference/qwen2_5_omni/README.md
|
|
examples/offline_inference/qwen2_5_omni/only_thinker.py
|
|
examples/offline_inference/qwen3_omni/only_thinker.py
|
|
examples/online_serving/api_client.py
|
|
examples/online_serving/disaggregated_prefill.sh
|
|
examples/online_serving/gradio_openai_chatbot_webserver.py
|
|
examples/online_serving/gradio_webserver.py
|
|
examples/online_serving/kv_events_subscriber.py
|
|
examples/online_serving/multi-node-serving.sh
|
|
examples/online_serving/multi_instance_data_parallel.py
|
|
examples/online_serving/openai_chat_completion_client.py
|
|
examples/online_serving/openai_chat_completion_client_for_multimodal.py
|
|
examples/online_serving/openai_chat_completion_client_with_tools.py
|
|
examples/online_serving/openai_chat_completion_client_with_tools_required.py
|
|
examples/online_serving/openai_chat_completion_client_with_tools_xlam.py
|
|
examples/online_serving/openai_chat_completion_client_with_tools_xlam_streaming.py
|
|
examples/online_serving/openai_chat_completion_tool_calls_with_reasoning.py
|
|
examples/online_serving/openai_chat_completion_with_reasoning.py
|
|
examples/online_serving/openai_chat_completion_with_reasoning_streaming.py
|
|
examples/online_serving/openai_completion_client.py
|
|
examples/online_serving/openai_responses_client.py
|
|
examples/online_serving/openai_responses_client_with_mcp_tools.py
|
|
examples/online_serving/openai_responses_client_with_tools.py
|
|
examples/online_serving/openai_transcription_client.py
|
|
examples/online_serving/openai_translation_client.py
|
|
examples/online_serving/prompt_embed_inference_with_openai_client.py
|
|
examples/online_serving/ray_serve_deepseek.py
|
|
examples/online_serving/retrieval_augmented_generation_with_langchain.py
|
|
examples/online_serving/retrieval_augmented_generation_with_llamaindex.py
|
|
examples/online_serving/run_cluster.sh
|
|
examples/online_serving/sagemaker-entrypoint.sh
|
|
examples/online_serving/streamlit_openai_chatbot_webserver.py
|
|
examples/online_serving/token_generation_client.py
|
|
examples/online_serving/utils.py
|
|
examples/online_serving/chart-helm/.helmignore
|
|
examples/online_serving/chart-helm/Chart.yaml
|
|
examples/online_serving/chart-helm/README.md
|
|
examples/online_serving/chart-helm/ct.yaml
|
|
examples/online_serving/chart-helm/lintconf.yaml
|
|
examples/online_serving/chart-helm/values.schema.json
|
|
examples/online_serving/chart-helm/values.yaml
|
|
examples/online_serving/chart-helm/templates/_helpers.tpl
|
|
examples/online_serving/chart-helm/templates/configmap.yaml
|
|
examples/online_serving/chart-helm/templates/custom-objects.yaml
|
|
examples/online_serving/chart-helm/templates/deployment.yaml
|
|
examples/online_serving/chart-helm/templates/hpa.yaml
|
|
examples/online_serving/chart-helm/templates/job.yaml
|
|
examples/online_serving/chart-helm/templates/poddisruptionbudget.yaml
|
|
examples/online_serving/chart-helm/templates/pvc.yaml
|
|
examples/online_serving/chart-helm/templates/secrets.yaml
|
|
examples/online_serving/chart-helm/templates/service.yaml
|
|
examples/online_serving/chart-helm/tests/deployment_test.yaml
|
|
examples/online_serving/chart-helm/tests/job_test.yaml
|
|
examples/online_serving/chart-helm/tests/pvc_test.yaml
|
|
examples/online_serving/dashboards/README.md
|
|
examples/online_serving/dashboards/grafana/README.md
|
|
examples/online_serving/dashboards/grafana/performance_statistics.json
|
|
examples/online_serving/dashboards/grafana/query_statistics.json
|
|
examples/online_serving/dashboards/perses/README.md
|
|
examples/online_serving/dashboards/perses/performance_statistics.yaml
|
|
examples/online_serving/dashboards/perses/query_statistics.yaml
|
|
examples/online_serving/disaggregated_encoder/README.md
|
|
examples/online_serving/disaggregated_encoder/disagg_1e1p1d_example.sh
|
|
examples/online_serving/disaggregated_encoder/disagg_1e1pd_example.sh
|
|
examples/online_serving/disaggregated_encoder/disagg_epd_proxy.py
|
|
examples/online_serving/disaggregated_serving/README.md
|
|
examples/online_serving/disaggregated_serving/disagg_proxy_demo.py
|
|
examples/online_serving/disaggregated_serving/kv_events.sh
|
|
examples/online_serving/disaggregated_serving_p2p_nccl_xpyd/disagg_example_p2p_nccl_xpyd.sh
|
|
examples/online_serving/disaggregated_serving_p2p_nccl_xpyd/disagg_proxy_p2p_nccl_xpyd.py
|
|
examples/online_serving/elastic_ep/bench.sh
|
|
examples/online_serving/elastic_ep/scale.py
|
|
examples/online_serving/elastic_ep/serve_deepseek_v2.sh
|
|
examples/online_serving/opentelemetry/README.md
|
|
examples/online_serving/opentelemetry/dummy_client.py
|
|
examples/online_serving/prometheus_grafana/README.md
|
|
examples/online_serving/prometheus_grafana/docker-compose.yaml
|
|
examples/online_serving/prometheus_grafana/grafana.json
|
|
examples/online_serving/prometheus_grafana/prometheus.yaml
|
|
examples/online_serving/structured_outputs/README.md
|
|
examples/online_serving/structured_outputs/pyproject.toml
|
|
examples/online_serving/structured_outputs/structured_outputs.py
|
|
examples/others/logging_configuration.md
|
|
examples/others/tensorize_vllm_model.py
|
|
examples/others/lmcache/README.md
|
|
examples/others/lmcache/cpu_offload_lmcache.py
|
|
examples/others/lmcache/disagg_prefill_lmcache_v0.py
|
|
examples/others/lmcache/kv_cache_sharing_lmcache_v1.py
|
|
examples/others/lmcache/disagg_prefill_lmcache_v1/disagg_example_nixl.sh
|
|
examples/others/lmcache/disagg_prefill_lmcache_v1/disagg_proxy_server.py
|
|
examples/others/lmcache/disagg_prefill_lmcache_v1/disagg_vllm_launcher.sh
|
|
examples/others/lmcache/disagg_prefill_lmcache_v1/configs/lmcache-decoder-config.yaml
|
|
examples/others/lmcache/disagg_prefill_lmcache_v1/configs/lmcache-prefiller-config.yaml
|
|
examples/pooling/classify/openai_classification_client.py
|
|
examples/pooling/embed/embed_jina_embeddings_v3.py
|
|
examples/pooling/embed/embed_matryoshka_fy.py
|
|
examples/pooling/embed/embedding_requests_base64_client.py
|
|
examples/pooling/embed/embedding_requests_bytes_client.py
|
|
examples/pooling/embed/openai_chat_embedding_client_for_multimodal.py
|
|
examples/pooling/embed/openai_embedding_client.py
|
|
examples/pooling/embed/openai_embedding_matryoshka_fy.py
|
|
examples/pooling/embed/openai_embedding_long_text/README.md
|
|
examples/pooling/embed/openai_embedding_long_text/client.py
|
|
examples/pooling/embed/openai_embedding_long_text/service.sh
|
|
examples/pooling/plugin/prithvi_geospatial_mae_client.py
|
|
examples/pooling/plugin/prithvi_geospatial_mae_io_processor.py
|
|
examples/pooling/plugin/prithvi_geospatial_mae_offline.py
|
|
examples/pooling/pooling/openai_pooling_client.py
|
|
examples/pooling/pooling/vision_language_pooling.py
|
|
examples/pooling/score/cohere_rerank_client.py
|
|
examples/pooling/score/convert_model_to_seq_cls.py
|
|
examples/pooling/score/offline_reranker.py
|
|
examples/pooling/score/openai_cross_encoder_score.py
|
|
examples/pooling/score/openai_cross_encoder_score_for_multimodal.py
|
|
examples/pooling/score/openai_reranker.py
|
|
examples/pooling/token_classify/ner.py
|
|
examples/pooling/token_classify/ner_client.py
|
|
examples/pooling/token_embed/jina_embeddings_v4.py
|
|
examples/pooling/token_embed/multi_vector_retrieval.py
|
|
examples/pooling/token_embed/multi_vector_retrieval_client.py
|
|
requirements/build.txt
|
|
requirements/common.txt
|
|
requirements/cpu-build.txt
|
|
requirements/cpu.txt
|
|
requirements/cuda.txt
|
|
requirements/dev.txt
|
|
requirements/docs.txt
|
|
requirements/kv_connectors.txt
|
|
requirements/lint.txt
|
|
requirements/nightly_torch_test.txt
|
|
requirements/rocm-build.txt
|
|
requirements/rocm-test.txt
|
|
requirements/rocm.txt
|
|
requirements/test.in
|
|
requirements/test.txt
|
|
requirements/tpu.txt
|
|
requirements/xpu.txt
|
|
tests/__init__.py
|
|
tests/ci_envs.py
|
|
tests/conftest.py
|
|
tests/test_config.py
|
|
tests/test_embedded_commit.py
|
|
tests/test_envs.py
|
|
tests/test_inputs.py
|
|
tests/test_logger.py
|
|
tests/test_logprobs.py
|
|
tests/test_outputs.py
|
|
tests/test_pooling_params.py
|
|
tests/test_regression.py
|
|
tests/test_routing_simulator.py
|
|
tests/test_scalartype.py
|
|
tests/test_seed_behavior.py
|
|
tests/test_sequence.py
|
|
tests/test_triton_utils.py
|
|
tests/test_version.py
|
|
tests/test_vllm_port.py
|
|
tests/utils.py
|
|
tests/basic_correctness/__init__.py
|
|
tests/basic_correctness/test_basic_correctness.py
|
|
tests/basic_correctness/test_cpu_offload.py
|
|
tests/basic_correctness/test_cumem.py
|
|
tests/benchmarks/__init__.py
|
|
tests/benchmarks/test_latency_cli.py
|
|
tests/benchmarks/test_param_sweep.py
|
|
tests/benchmarks/test_plot_filters.py
|
|
tests/benchmarks/test_random_dataset.py
|
|
tests/benchmarks/test_random_multimodal_dataset_video.py
|
|
tests/benchmarks/test_serve_cli.py
|
|
tests/benchmarks/test_throughput_cli.py
|
|
tests/compile/README.md
|
|
tests/compile/__init__.py
|
|
tests/compile/backend.py
|
|
tests/compile/silly_attention.py
|
|
tests/compile/test_aot_compile.py
|
|
tests/compile/test_compile_ranges.py
|
|
tests/compile/test_config.py
|
|
tests/compile/test_decorator.py
|
|
tests/compile/test_dynamic_shapes_compilation.py
|
|
tests/compile/test_functionalization.py
|
|
tests/compile/test_fusion.py
|
|
tests/compile/test_fusion_attn.py
|
|
tests/compile/test_graph_partition.py
|
|
tests/compile/test_noop_elimination.py
|
|
tests/compile/test_pass_manager.py
|
|
tests/compile/test_qk_norm_rope_fusion.py
|
|
tests/compile/test_silu_mul_quant_fusion.py
|
|
tests/compile/test_wrapper.py
|
|
tests/compile/distributed/__init__.py
|
|
tests/compile/distributed/test_async_tp.py
|
|
tests/compile/distributed/test_fusion_all_reduce.py
|
|
tests/compile/distributed/test_fusions_e2e.py
|
|
tests/compile/distributed/test_sequence_parallelism.py
|
|
tests/compile/fullgraph/__init__.py
|
|
tests/compile/fullgraph/test_basic_correctness.py
|
|
tests/compile/fullgraph/test_full_cudagraph.py
|
|
tests/compile/fullgraph/test_full_graph.py
|
|
tests/compile/fullgraph/test_multimodal_compile.py
|
|
tests/compile/fullgraph/test_multiple_graphs.py
|
|
tests/compile/fullgraph/test_simple.py
|
|
tests/compile/fullgraph/test_toy_llama.py
|
|
tests/config/test_config.yaml
|
|
tests/config/test_config_generation.py
|
|
tests/config/test_config_utils.py
|
|
tests/config/test_config_with_model.yaml
|
|
tests/config/test_mp_reducer.py
|
|
tests/config/test_multimodal_config.py
|
|
tests/cuda/test_cuda_context.py
|
|
tests/detokenizer/__init__.py
|
|
tests/detokenizer/test_disable_detokenization.py
|
|
tests/detokenizer/test_min_tokens.py
|
|
tests/detokenizer/test_stop_reason.py
|
|
tests/detokenizer/test_stop_string_while_stop_model_terminates.py
|
|
tests/detokenizer/test_stop_strings.py
|
|
tests/distributed/__init__.py
|
|
tests/distributed/conftest.py
|
|
tests/distributed/eplb_utils.py
|
|
tests/distributed/test_ca_buffer_sharing.py
|
|
tests/distributed/test_comm_ops.py
|
|
tests/distributed/test_context_parallel.py
|
|
tests/distributed/test_custom_all_reduce.py
|
|
tests/distributed/test_distributed_oot.py
|
|
tests/distributed/test_eplb_algo.py
|
|
tests/distributed/test_eplb_execute.py
|
|
tests/distributed/test_eplb_fused_moe_layer.py
|
|
tests/distributed/test_eplb_fused_moe_layer_dep_nvfp4.py
|
|
tests/distributed/test_eplb_spec_decode.py
|
|
tests/distributed/test_events.py
|
|
tests/distributed/test_expert_parallel.py
|
|
tests/distributed/test_expert_placement.py
|
|
tests/distributed/test_kvlayout.py
|
|
tests/distributed/test_multi_node_assignment.py
|
|
tests/distributed/test_multiproc_executor.py
|
|
tests/distributed/test_nccl_symm_mem_allreduce.py
|
|
tests/distributed/test_node_count.py
|
|
tests/distributed/test_pipeline_parallel.py
|
|
tests/distributed/test_pipeline_partition.py
|
|
tests/distributed/test_pp_cudagraph.py
|
|
tests/distributed/test_pynccl.py
|
|
tests/distributed/test_quick_all_reduce.py
|
|
tests/distributed/test_same_node.py
|
|
tests/distributed/test_sequence_parallel.py
|
|
tests/distributed/test_shm_broadcast.py
|
|
tests/distributed/test_shm_buffer.py
|
|
tests/distributed/test_shm_storage.py
|
|
tests/distributed/test_symm_mem_allreduce.py
|
|
tests/distributed/test_torchrun_example.py
|
|
tests/distributed/test_torchrun_example_moe.py
|
|
tests/distributed/test_utils.py
|
|
tests/engine/__init__.py
|
|
tests/engine/test_arg_utils.py
|
|
tests/engine/test_short_mm_context.py
|
|
tests/entrypoints/__init__.py
|
|
tests/entrypoints/conftest.py
|
|
tests/entrypoints/test_api_server_process_manager.py
|
|
tests/entrypoints/test_chat_utils.py
|
|
tests/entrypoints/test_context.py
|
|
tests/entrypoints/test_renderer.py
|
|
tests/entrypoints/test_responses_utils.py
|
|
tests/entrypoints/test_ssl_cert_refresher.py
|
|
tests/entrypoints/llm/__init__.py
|
|
tests/entrypoints/llm/test_accuracy.py
|
|
tests/entrypoints/llm/test_chat.py
|
|
tests/entrypoints/llm/test_collective_rpc.py
|
|
tests/entrypoints/llm/test_generate.py
|
|
tests/entrypoints/llm/test_gpu_utilization.py
|
|
tests/entrypoints/llm/test_mm_cache_stats.py
|
|
tests/entrypoints/llm/test_prompt_validation.py
|
|
tests/entrypoints/offline_mode/__init__.py
|
|
tests/entrypoints/offline_mode/test_offline_mode.py
|
|
tests/entrypoints/openai/__init__.py
|
|
tests/entrypoints/openai/conftest.py
|
|
tests/entrypoints/openai/test_async_tokenization.py
|
|
tests/entrypoints/openai/test_audio.py
|
|
tests/entrypoints/openai/test_basic.py
|
|
tests/entrypoints/openai/test_chat.py
|
|
tests/entrypoints/openai/test_chat_echo.py
|
|
tests/entrypoints/openai/test_chat_error.py
|
|
tests/entrypoints/openai/test_chat_logit_bias_validation.py
|
|
tests/entrypoints/openai/test_chat_template.py
|
|
tests/entrypoints/openai/test_chat_with_tool_reasoning.py
|
|
tests/entrypoints/openai/test_chunked_prompt.py
|
|
tests/entrypoints/openai/test_cli_args.py
|
|
tests/entrypoints/openai/test_collective_rpc.py
|
|
tests/entrypoints/openai/test_completion_error.py
|
|
tests/entrypoints/openai/test_completion_with_function_calling.py
|
|
tests/entrypoints/openai/test_completion_with_prompt_embeds.py
|
|
tests/entrypoints/openai/test_default_mm_loras.py
|
|
tests/entrypoints/openai/test_enable_force_include_usage.py
|
|
tests/entrypoints/openai/test_gptoss_structural_tags_integration.py
|
|
tests/entrypoints/openai/test_lora_adapters.py
|
|
tests/entrypoints/openai/test_lora_resolvers.py
|
|
tests/entrypoints/openai/test_messages.py
|
|
tests/entrypoints/openai/test_metrics.py
|
|
tests/entrypoints/openai/test_models.py
|
|
tests/entrypoints/openai/test_oot_registration.py
|
|
tests/entrypoints/openai/test_openai_schema.py
|
|
tests/entrypoints/openai/test_optional_middleware.py
|
|
tests/entrypoints/openai/test_orca_metrics.py
|
|
tests/entrypoints/openai/test_prompt_validation.py
|
|
tests/entrypoints/openai/test_protocol.py
|
|
tests/entrypoints/openai/test_response_api_mcp_tools.py
|
|
tests/entrypoints/openai/test_response_api_parsable_context.py
|
|
tests/entrypoints/openai/test_response_api_simple.py
|
|
tests/entrypoints/openai/test_response_api_with_harmony.py
|
|
tests/entrypoints/openai/test_responses_error.py
|
|
tests/entrypoints/openai/test_responses_function_call_parsing.py
|
|
tests/entrypoints/openai/test_return_token_ids.py
|
|
tests/entrypoints/openai/test_return_tokens_as_ids.py
|
|
tests/entrypoints/openai/test_root_path.py
|
|
tests/entrypoints/openai/test_run_batch.py
|
|
tests/entrypoints/openai/test_serving_chat.py
|
|
tests/entrypoints/openai/test_serving_engine.py
|
|
tests/entrypoints/openai/test_serving_models.py
|
|
tests/entrypoints/openai/test_serving_responses.py
|
|
tests/entrypoints/openai/test_serving_tokens.py
|
|
tests/entrypoints/openai/test_shutdown.py
|
|
tests/entrypoints/openai/test_sleep.py
|
|
tests/entrypoints/openai/test_sparse_tensor_validation.py
|
|
tests/entrypoints/openai/test_tensorizer_entrypoint.py
|
|
tests/entrypoints/openai/test_token_in_token_out.py
|
|
tests/entrypoints/openai/test_tokenization.py
|
|
tests/entrypoints/openai/test_transcription_validation.py
|
|
tests/entrypoints/openai/test_transcription_validation_whisper.py
|
|
tests/entrypoints/openai/test_translation_validation.py
|
|
tests/entrypoints/openai/test_uds.py
|
|
tests/entrypoints/openai/test_video.py
|
|
tests/entrypoints/openai/test_vision.py
|
|
tests/entrypoints/openai/test_vision_embeds.py
|
|
tests/entrypoints/openai/utils.py
|
|
tests/entrypoints/openai/correctness/__init__.py
|
|
tests/entrypoints/openai/correctness/test_lmeval.py
|
|
tests/entrypoints/openai/correctness/test_transcription_api_correctness.py
|
|
tests/entrypoints/openai/parser/__init__.py
|
|
tests/entrypoints/openai/parser/test_harmony_utils.py
|
|
tests/entrypoints/openai/tool_parsers/__init__.py
|
|
tests/entrypoints/openai/tool_parsers/conftest.py
|
|
tests/entrypoints/openai/tool_parsers/test_gigachat3_tool_parser.py
|
|
tests/entrypoints/openai/tool_parsers/test_hermes_tool_parser.py
|
|
tests/entrypoints/openai/tool_parsers/test_hunyuan_a13b_tool_parser.py
|
|
tests/entrypoints/openai/tool_parsers/test_llama3_json_tool_parser.py
|
|
tests/entrypoints/openai/tool_parsers/test_llama4_pythonic_tool_parser.py
|
|
tests/entrypoints/openai/tool_parsers/test_olmo3_tool_parser.py
|
|
tests/entrypoints/openai/tool_parsers/test_openai_tool_parser.py
|
|
tests/entrypoints/openai/tool_parsers/test_pythonic_tool_parser.py
|
|
tests/entrypoints/openai/tool_parsers/utils.py
|
|
tests/entrypoints/pooling/__init__.py
|
|
tests/entrypoints/pooling/basic/__init__.py
|
|
tests/entrypoints/pooling/basic/test_encode.py
|
|
tests/entrypoints/pooling/basic/test_truncation.py
|
|
tests/entrypoints/pooling/classify/__init__.py
|
|
tests/entrypoints/pooling/classify/test_offline.py
|
|
tests/entrypoints/pooling/classify/test_online.py
|
|
tests/entrypoints/pooling/classify/test_online_vision.py
|
|
tests/entrypoints/pooling/embed/__init__.py
|
|
tests/entrypoints/pooling/embed/test_correctness_mteb.py
|
|
tests/entrypoints/pooling/embed/test_offline.py
|
|
tests/entrypoints/pooling/embed/test_online.py
|
|
tests/entrypoints/pooling/embed/test_online_dimensions.py
|
|
tests/entrypoints/pooling/embed/test_online_long_text.py
|
|
tests/entrypoints/pooling/embed/test_online_vision.py
|
|
tests/entrypoints/pooling/pooling/__init__.py
|
|
tests/entrypoints/pooling/pooling/test_online.py
|
|
tests/entrypoints/pooling/reward/__init__.py
|
|
tests/entrypoints/pooling/reward/test_offline.py
|
|
tests/entrypoints/pooling/score/__init__.py
|
|
tests/entrypoints/pooling/score/test_correctness_mteb.py
|
|
tests/entrypoints/pooling/score/test_offline.py
|
|
tests/entrypoints/pooling/score/test_online_rerank.py
|
|
tests/entrypoints/pooling/score/test_online_score.py
|
|
tests/entrypoints/sagemaker/__init__.py
|
|
tests/entrypoints/sagemaker/conftest.py
|
|
tests/entrypoints/sagemaker/test_sagemaker_handler_overrides.py
|
|
tests/entrypoints/sagemaker/test_sagemaker_lora_adapters.py
|
|
tests/entrypoints/sagemaker/test_sagemaker_middleware_integration.py
|
|
tests/entrypoints/sagemaker/test_sagemaker_stateful_sessions.py
|
|
tests/evals/gpt_oss/__init__.py
|
|
tests/evals/gpt_oss/conftest.py
|
|
tests/evals/gpt_oss/test_gpqa_correctness.py
|
|
tests/evals/gsm8k/README.md
|
|
tests/evals/gsm8k/__init__.py
|
|
tests/evals/gsm8k/conftest.py
|
|
tests/evals/gsm8k/gsm8k_eval.py
|
|
tests/evals/gsm8k/test_gsm8k_correctness.py
|
|
tests/evals/gsm8k/configs/DeepSeek-V2-Lite-Instruct-FP8.yaml
|
|
tests/evals/gsm8k/configs/Llama-3-8B-Instruct-nonuniform-CT.yaml
|
|
tests/evals/gsm8k/configs/Llama-3.2-1B-Instruct-INT8-CT.yaml
|
|
tests/evals/gsm8k/configs/Qwen1.5-MoE-W4A16-CT.yaml
|
|
tests/evals/gsm8k/configs/Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
|
|
tests/evals/gsm8k/configs/Qwen3-0.6B-FP8.yaml
|
|
tests/evals/gsm8k/configs/Qwen3-30B-A3B-NVFP4.yaml
|
|
tests/evals/gsm8k/configs/models-blackwell.txt
|
|
tests/evals/gsm8k/configs/models-small.txt
|
|
tests/kernels/__init__.py
|
|
tests/kernels/allclose_default.py
|
|
tests/kernels/quant_utils.py
|
|
tests/kernels/test_apply_repetition_penalties.py
|
|
tests/kernels/test_cache_kernels.py
|
|
tests/kernels/test_fla_layernorm_guard.py
|
|
tests/kernels/test_flex_attention.py
|
|
tests/kernels/test_fused_quant_activation.py
|
|
tests/kernels/test_onednn.py
|
|
tests/kernels/test_shuffle_rows.py
|
|
tests/kernels/test_top_k_per_row.py
|
|
tests/kernels/utils.py
|
|
tests/kernels/attention/conftest.py
|
|
tests/kernels/attention/test_aiter_flash_attn.py
|
|
tests/kernels/attention/test_attention.py
|
|
tests/kernels/attention/test_attention_selector.py
|
|
tests/kernels/attention/test_cache.py
|
|
tests/kernels/attention/test_cascade_flash_attn.py
|
|
tests/kernels/attention/test_cpu_attn.py
|
|
tests/kernels/attention/test_cutlass_mla_decode.py
|
|
tests/kernels/attention/test_deepgemm_attention.py
|
|
tests/kernels/attention/test_flash_attn.py
|
|
tests/kernels/attention/test_flashinfer.py
|
|
tests/kernels/attention/test_flashinfer_mla_decode.py
|
|
tests/kernels/attention/test_flashinfer_trtllm_attention.py
|
|
tests/kernels/attention/test_flashmla.py
|
|
tests/kernels/attention/test_flashmla_sparse.py
|
|
tests/kernels/attention/test_lightning_attn.py
|
|
tests/kernels/attention/test_merge_attn_states.py
|
|
tests/kernels/attention/test_mha_attn.py
|
|
tests/kernels/attention/test_mla_decode_cpu.py
|
|
tests/kernels/attention/test_pack_unpack_triton.py
|
|
tests/kernels/attention/test_prefix_prefill.py
|
|
tests/kernels/attention/test_rocm_attention_selector.py
|
|
tests/kernels/attention/test_triton_decode_attention.py
|
|
tests/kernels/attention/test_triton_unified_attention.py
|
|
tests/kernels/core/test_activation.py
|
|
tests/kernels/core/test_apply_rotary_emb.py
|
|
tests/kernels/core/test_fused_qk_norm_rope.py
|
|
tests/kernels/core/test_fused_quant_layernorm.py
|
|
tests/kernels/core/test_layernorm.py
|
|
tests/kernels/core/test_mrope.py
|
|
tests/kernels/core/test_opcheck.py
|
|
tests/kernels/core/test_permute_cols.py
|
|
tests/kernels/core/test_pos_encoding.py
|
|
tests/kernels/core/test_rotary_embedding.py
|
|
tests/kernels/core/test_uva.py
|
|
tests/kernels/mamba/test_causal_conv1d.py
|
|
tests/kernels/mamba/test_mamba_mixer2.py
|
|
tests/kernels/mamba/test_mamba_ssm.py
|
|
tests/kernels/mamba/test_mamba_ssm_ssd.py
|
|
tests/kernels/moe/__init__.py
|
|
tests/kernels/moe/parallel_utils.py
|
|
tests/kernels/moe/test_batched_deepgemm.py
|
|
tests/kernels/moe/test_batched_moe.py
|
|
tests/kernels/moe/test_block_fp8.py
|
|
tests/kernels/moe/test_block_int8.py
|
|
tests/kernels/moe/test_count_expert_num_tokens.py
|
|
tests/kernels/moe/test_cutedsl_moe.py
|
|
tests/kernels/moe/test_cutlass_grouped_gemm.py
|
|
tests/kernels/moe/test_cutlass_moe.py
|
|
tests/kernels/moe/test_deepep_deepgemm_moe.py
|
|
tests/kernels/moe/test_deepep_moe.py
|
|
tests/kernels/moe/test_deepgemm.py
|
|
tests/kernels/moe/test_flashinfer.py
|
|
tests/kernels/moe/test_flashinfer_moe.py
|
|
tests/kernels/moe/test_gpt_oss_triton_kernels.py
|
|
tests/kernels/moe/test_grouped_topk.py
|
|
tests/kernels/moe/test_modular_kernel_combinations.py
|
|
tests/kernels/moe/test_modular_oai_triton_moe.py
|
|
tests/kernels/moe/test_moe.py
|
|
tests/kernels/moe/test_moe_align_block_size.py
|
|
tests/kernels/moe/test_moe_permute_unpermute.py
|
|
tests/kernels/moe/test_nvfp4_moe.py
|
|
tests/kernels/moe/test_ocp_mx_moe.py
|
|
tests/kernels/moe/test_pplx_cutlass_moe.py
|
|
tests/kernels/moe/test_pplx_moe.py
|
|
tests/kernels/moe/test_rocm_aiter_topk.py
|
|
tests/kernels/moe/test_silu_mul_fp8_quant_deep_gemm.py
|
|
tests/kernels/moe/test_silu_mul_per_token_group_quant_fp8_colmajor.py
|
|
tests/kernels/moe/test_triton_moe_ptpc_fp8.py
|
|
tests/kernels/moe/utils.py
|
|
tests/kernels/moe/modular_kernel_tools/__init__.py
|
|
tests/kernels/moe/modular_kernel_tools/cli_args.py
|
|
tests/kernels/moe/modular_kernel_tools/common.py
|
|
tests/kernels/moe/modular_kernel_tools/make_feature_matrix.py
|
|
tests/kernels/moe/modular_kernel_tools/mk_objects.py
|
|
tests/kernels/moe/modular_kernel_tools/parallel_utils.py
|
|
tests/kernels/moe/modular_kernel_tools/profile_modular_kernel.py
|
|
tests/kernels/quantization/nvfp4_utils.py
|
|
tests/kernels/quantization/test_allspark_gemm.py
|
|
tests/kernels/quantization/test_awq.py
|
|
tests/kernels/quantization/test_awq_triton.py
|
|
tests/kernels/quantization/test_block_fp8.py
|
|
tests/kernels/quantization/test_block_int8.py
|
|
tests/kernels/quantization/test_cutlass_2of4_sparse.py
|
|
tests/kernels/quantization/test_cutlass_scaled_mm.py
|
|
tests/kernels/quantization/test_cutlass_w4a8.py
|
|
tests/kernels/quantization/test_cutlass_w4a8_moe.py
|
|
tests/kernels/quantization/test_flashinfer_nvfp4_scaled_mm.py
|
|
tests/kernels/quantization/test_flashinfer_scaled_mm.py
|
|
tests/kernels/quantization/test_fp8_quant.py
|
|
tests/kernels/quantization/test_fp8_quant_group.py
|
|
tests/kernels/quantization/test_ggml.py
|
|
tests/kernels/quantization/test_gguf.py
|
|
tests/kernels/quantization/test_gptq.py
|
|
tests/kernels/quantization/test_hadacore.py
|
|
tests/kernels/quantization/test_int8_kernel.py
|
|
tests/kernels/quantization/test_int8_quant.py
|
|
tests/kernels/quantization/test_machete_mm.py
|
|
tests/kernels/quantization/test_marlin_gemm.py
|
|
tests/kernels/quantization/test_mxfp4_qutlass.py
|
|
tests/kernels/quantization/test_nvfp4_quant.py
|
|
tests/kernels/quantization/test_nvfp4_qutlass.py
|
|
tests/kernels/quantization/test_nvfp4_scaled_mm.py
|
|
tests/kernels/quantization/test_per_token_group_quant.py
|
|
tests/kernels/quantization/test_rocm_skinny_gemms.py
|
|
tests/kernels/quantization/test_scaled_mm_kernel_selection.py
|
|
tests/kernels/quantization/test_silu_mul_nvfp4_quant.py
|
|
tests/kernels/quantization/test_triton_scaled_mm.py
|
|
tests/lora/__init__.py
|
|
tests/lora/conftest.py
|
|
tests/lora/test_add_lora.py
|
|
tests/lora/test_chatglm3_tp.py
|
|
tests/lora/test_deepseekv2_tp.py
|
|
tests/lora/test_default_mm_loras.py
|
|
tests/lora/test_fused_moe_lora_kernel.py
|
|
tests/lora/test_gptoss_tp.py
|
|
tests/lora/test_layers.py
|
|
tests/lora/test_llama_tp.py
|
|
tests/lora/test_llm_with_multi_loras.py
|
|
tests/lora/test_lora_checkpoints.py
|
|
tests/lora/test_lora_functions.py
|
|
tests/lora/test_lora_huggingface.py
|
|
tests/lora/test_lora_manager.py
|
|
tests/lora/test_minicpmv_tp.py
|
|
tests/lora/test_mixtral.py
|
|
tests/lora/test_moe_lora_align_sum.py
|
|
tests/lora/test_olmoe_tp.py
|
|
tests/lora/test_peft_helper.py
|
|
tests/lora/test_punica_ops.py
|
|
tests/lora/test_quant_model.py
|
|
tests/lora/test_qwen2vl.py
|
|
tests/lora/test_qwen3moe_tp.py
|
|
tests/lora/test_resolver.py
|
|
tests/lora/test_transformers_model.py
|
|
tests/lora/test_utils.py
|
|
tests/lora/test_worker.py
|
|
tests/lora/utils.py
|
|
tests/model_executor/__init__.py
|
|
tests/model_executor/test_eagle_quantization.py
|
|
tests/model_executor/test_enabled_custom_ops.py
|
|
tests/model_executor/test_model_load_with_params.py
|
|
tests/model_executor/test_qwen3_omni.py
|
|
tests/model_executor/test_weight_utils.py
|
|
tests/model_executor/model_loader/__init__.py
|
|
tests/model_executor/model_loader/test_registry.py
|
|
tests/model_executor/model_loader/test_sharded_state_loader.py
|
|
tests/model_executor/model_loader/fastsafetensors_loader/__init__.py
|
|
tests/model_executor/model_loader/fastsafetensors_loader/test_fastsafetensors_loader.py
|
|
tests/model_executor/model_loader/fastsafetensors_loader/test_weight_utils.py
|
|
tests/model_executor/model_loader/runai_streamer_loader/__init__.py
|
|
tests/model_executor/model_loader/runai_streamer_loader/conftest.py
|
|
tests/model_executor/model_loader/runai_streamer_loader/test_runai_model_streamer_loader.py
|
|
tests/model_executor/model_loader/runai_streamer_loader/test_runai_model_streamer_s3.py
|
|
tests/model_executor/model_loader/runai_streamer_loader/test_runai_utils.py
|
|
tests/model_executor/model_loader/runai_streamer_loader/test_weight_utils.py
|
|
tests/model_executor/model_loader/tensorizer_loader/__init__.py
|
|
tests/model_executor/model_loader/tensorizer_loader/conftest.py
|
|
tests/model_executor/model_loader/tensorizer_loader/test_tensorizer.py
|
|
tests/models/__init__.py
|
|
tests/models/registry.py
|
|
tests/models/test_gguf_download.py
|
|
tests/models/test_initialization.py
|
|
tests/models/test_oot_registration.py
|
|
tests/models/test_registry.py
|
|
tests/models/test_terratorch.py
|
|
tests/models/test_transformers.py
|
|
tests/models/test_utils.py
|
|
tests/models/test_vision.py
|
|
tests/models/utils.py
|
|
tests/models/fixtures/mistral_small_3_chat.json
|
|
tests/models/fixtures/pixtral_chat.json
|
|
tests/models/fixtures/audioflamingo3/expected_results_batched.json
|
|
tests/models/fixtures/audioflamingo3/expected_results_single.json
|
|
tests/models/language/__init__.py
|
|
tests/models/language/generation/__init__.py
|
|
tests/models/language/generation/test_common.py
|
|
tests/models/language/generation/test_gemma.py
|
|
tests/models/language/generation/test_granite.py
|
|
tests/models/language/generation/test_hybrid.py
|
|
tests/models/language/generation/test_mistral.py
|
|
tests/models/language/generation/test_phimoe.py
|
|
tests/models/language/generation_ppl_test/__init__.py
|
|
tests/models/language/generation_ppl_test/ppl_utils.py
|
|
tests/models/language/generation_ppl_test/test_gemma.py
|
|
tests/models/language/generation_ppl_test/test_gpt.py
|
|
tests/models/language/generation_ppl_test/test_qwen.py
|
|
tests/models/language/pooling/__init__.py
|
|
tests/models/language/pooling/embed_utils.py
|
|
tests/models/language/pooling/test_all_pooling_plus_chunked_prefill.py
|
|
tests/models/language/pooling/test_auto_prefix_cache_support.py
|
|
tests/models/language/pooling/test_classification.py
|
|
tests/models/language/pooling/test_embedding.py
|
|
tests/models/language/pooling/test_extract_hidden_states.py
|
|
tests/models/language/pooling/test_gritlm.py
|
|
tests/models/language/pooling/test_head_dtype.py
|
|
tests/models/language/pooling/test_mm_classifier_conversion.py
|
|
tests/models/language/pooling/test_multi_vector_retrieval.py
|
|
tests/models/language/pooling/test_multilabel_classification_support.py
|
|
tests/models/language/pooling/test_nomic_max_model_len.py
|
|
tests/models/language/pooling/test_pooler_config_init_behaviour.py
|
|
tests/models/language/pooling/test_reward.py
|
|
tests/models/language/pooling/test_scoring.py
|
|
tests/models/language/pooling/test_splade_sparse_pooler.py
|
|
tests/models/language/pooling/test_token_classification.py
|
|
tests/models/language/pooling/test_truncation_control.py
|
|
tests/models/language/pooling_mteb_test/__init__.py
|
|
tests/models/language/pooling_mteb_test/mteb_utils.py
|
|
tests/models/language/pooling_mteb_test/test_baai.py
|
|
tests/models/language/pooling_mteb_test/test_bge_reranker_v2_gemma.py
|
|
tests/models/language/pooling_mteb_test/test_cross_encoder.py
|
|
tests/models/language/pooling_mteb_test/test_gte.py
|
|
tests/models/language/pooling_mteb_test/test_intfloat.py
|
|
tests/models/language/pooling_mteb_test/test_jina.py
|
|
tests/models/language/pooling_mteb_test/test_mxbai_rerank.py
|
|
tests/models/language/pooling_mteb_test/test_nomic.py
|
|
tests/models/language/pooling_mteb_test/test_qwen3_reranker.py
|
|
tests/models/language/pooling_mteb_test/test_snowflake_arctic_embed.py
|
|
tests/models/language/pooling_mteb_test/test_st_projector.py
|
|
tests/models/multimodal/__init__.py
|
|
tests/models/multimodal/test_mapping.py
|
|
tests/models/multimodal/generation/__init__.py
|
|
tests/models/multimodal/generation/conftest.py
|
|
tests/models/multimodal/generation/test_audioflamingo3.py
|
|
tests/models/multimodal/generation/test_common.py
|
|
tests/models/multimodal/generation/test_granite_speech.py
|
|
tests/models/multimodal/generation/test_interleaved.py
|
|
tests/models/multimodal/generation/test_keye.py
|
|
tests/models/multimodal/generation/test_maverick.py
|
|
tests/models/multimodal/generation/test_multimodal_gguf.py
|
|
tests/models/multimodal/generation/test_phi4mm.py
|
|
tests/models/multimodal/generation/test_pixtral.py
|
|
tests/models/multimodal/generation/test_qwen2_5_vl.py
|
|
tests/models/multimodal/generation/test_qwen2_vl.py
|
|
tests/models/multimodal/generation/test_ultravox.py
|
|
tests/models/multimodal/generation/test_vit_backend_functionality.py
|
|
tests/models/multimodal/generation/test_voxtral.py
|
|
tests/models/multimodal/generation/test_whisper.py
|
|
tests/models/multimodal/generation/vlm_utils/__init__.py
|
|
tests/models/multimodal/generation/vlm_utils/builders.py
|
|
tests/models/multimodal/generation/vlm_utils/case_filtering.py
|
|
tests/models/multimodal/generation/vlm_utils/core.py
|
|
tests/models/multimodal/generation/vlm_utils/custom_inputs.py
|
|
tests/models/multimodal/generation/vlm_utils/model_utils.py
|
|
tests/models/multimodal/generation/vlm_utils/runners.py
|
|
tests/models/multimodal/generation/vlm_utils/types.py
|
|
tests/models/multimodal/pooling/__init__.py
|
|
tests/models/multimodal/pooling/conftest.py
|
|
tests/models/multimodal/pooling/test_clip.py
|
|
tests/models/multimodal/pooling/test_dse_qwen2_vl.py
|
|
tests/models/multimodal/pooling/test_intern_vit.py
|
|
tests/models/multimodal/pooling/test_jinavl_reranker.py
|
|
tests/models/multimodal/pooling/test_llava_next.py
|
|
tests/models/multimodal/pooling/test_phi3v.py
|
|
tests/models/multimodal/pooling/test_prithvi_mae.py
|
|
tests/models/multimodal/pooling/test_radio.py
|
|
tests/models/multimodal/pooling/test_siglip.py
|
|
tests/models/multimodal/processing/__init__.py
|
|
tests/models/multimodal/processing/test_audioflamingo3.py
|
|
tests/models/multimodal/processing/test_common.py
|
|
tests/models/multimodal/processing/test_gemma3.py
|
|
tests/models/multimodal/processing/test_glm4_1v.py
|
|
tests/models/multimodal/processing/test_h2ovl.py
|
|
tests/models/multimodal/processing/test_idefics3.py
|
|
tests/models/multimodal/processing/test_internvl.py
|
|
tests/models/multimodal/processing/test_llama4.py
|
|
tests/models/multimodal/processing/test_llava_next.py
|
|
tests/models/multimodal/processing/test_llava_onevision.py
|
|
tests/models/multimodal/processing/test_minimax_vl_01.py
|
|
tests/models/multimodal/processing/test_mllama4.py
|
|
tests/models/multimodal/processing/test_nemotron_vl.py
|
|
tests/models/multimodal/processing/test_phi3v.py
|
|
tests/models/multimodal/processing/test_phi4mm.py
|
|
tests/models/multimodal/processing/test_qwen2_vl.py
|
|
tests/models/multimodal/processing/test_smolvlm.py
|
|
tests/models/multimodal/processing/test_tensor_schema.py
|
|
tests/models/multimodal/processing/test_transformers.py
|
|
tests/models/quantization/__init__.py
|
|
tests/models/quantization/test_awq.py
|
|
tests/models/quantization/test_bitblas.py
|
|
tests/models/quantization/test_bitsandbytes.py
|
|
tests/models/quantization/test_fp8.py
|
|
tests/models/quantization/test_gguf.py
|
|
tests/models/quantization/test_gpt_oss_attn_quantization.py
|
|
tests/models/quantization/test_gptq_bitblas.py
|
|
tests/models/quantization/test_gptq_marlin.py
|
|
tests/models/quantization/test_gptq_marlin_24.py
|
|
tests/models/quantization/test_modelopt.py
|
|
tests/models/quantization/test_mxfp4.py
|
|
tests/models/quantization/test_nvfp4.py
|
|
tests/multimodal/__init__.py
|
|
tests/multimodal/test_audio.py
|
|
tests/multimodal/test_cache.py
|
|
tests/multimodal/test_hasher.py
|
|
tests/multimodal/test_image.py
|
|
tests/multimodal/test_processing.py
|
|
tests/multimodal/test_registry.py
|
|
tests/multimodal/test_sparse_tensor_validation_unit.py
|
|
tests/multimodal/test_utils.py
|
|
tests/multimodal/test_video.py
|
|
tests/multimodal/utils.py
|
|
tests/multimodal/assets/corrupted.mp4
|
|
tests/multimodal/assets/image1.png
|
|
tests/multimodal/assets/image2.png
|
|
tests/multimodal/assets/rgba.png
|
|
tests/plugins/lora_resolvers/__init__.py
|
|
tests/plugins/lora_resolvers/test_filesystem_resolver.py
|
|
tests/plugins/prithvi_io_processor_plugin/setup.py
|
|
tests/plugins/prithvi_io_processor_plugin/prithvi_io_processor/__init__.py
|
|
tests/plugins/prithvi_io_processor_plugin/prithvi_io_processor/prithvi_processor.py
|
|
tests/plugins/prithvi_io_processor_plugin/prithvi_io_processor/types.py
|
|
tests/plugins/vllm_add_dummy_model/setup.py
|
|
tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/__init__.py
|
|
tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_gemma_embedding.py
|
|
tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_llava.py
|
|
tests/plugins/vllm_add_dummy_model/vllm_add_dummy_model/my_opt.py
|
|
tests/plugins/vllm_add_dummy_platform/setup.py
|
|
tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/__init__.py
|
|
tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_attention_backend.py
|
|
tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_custom_ops.py
|
|
tests/plugins/vllm_add_dummy_platform/vllm_add_dummy_platform/dummy_platform.py
|
|
tests/plugins/vllm_add_dummy_stat_logger/setup.py
|
|
tests/plugins/vllm_add_dummy_stat_logger/dummy_stat_logger/dummy_stat_logger.py
|
|
tests/plugins_tests/test_io_processor_plugins.py
|
|
tests/plugins_tests/test_platform_plugins.py
|
|
tests/plugins_tests/test_scheduler_plugins.py
|
|
tests/plugins_tests/test_stats_logger_plugins.py
|
|
tests/prompts/example.txt
|
|
tests/prompts/summary.txt
|
|
tests/quantization/__init__.py
|
|
tests/quantization/fp_quant.py
|
|
tests/quantization/reference_mxfp4.py
|
|
tests/quantization/test_auto_round.py
|
|
tests/quantization/test_blackwell_moe.py
|
|
tests/quantization/test_compressed_tensors.py
|
|
tests/quantization/test_configs.py
|
|
tests/quantization/test_cpu_offload.py
|
|
tests/quantization/test_cpu_wna16.py
|
|
tests/quantization/test_experts_int8.py
|
|
tests/quantization/test_fp8.py
|
|
tests/quantization/test_gptq_dynamic.py
|
|
tests/quantization/test_gptq_v2.py
|
|
tests/quantization/test_ipex_quant.py
|
|
tests/quantization/test_lm_head.py
|
|
tests/quantization/test_mixed_precision.py
|
|
tests/quantization/test_modelopt.py
|
|
tests/quantization/test_ptpc_fp8.py
|
|
tests/quantization/test_quark.py
|
|
tests/quantization/test_register_quantization_config.py
|
|
tests/quantization/test_rtn.py
|
|
tests/quantization/test_torchao.py
|
|
tests/quantization/utils.py
|
|
tests/reasoning/__init__.py
|
|
tests/reasoning/test_base_thinking_reasoning_parser.py
|
|
tests/reasoning/test_deepseekr1_reasoning_parser.py
|
|
tests/reasoning/test_deepseekv3_reasoning_parser.py
|
|
tests/reasoning/test_ernie45_reasoning_parser.py
|
|
tests/reasoning/test_glm4_moe_reasoning_parser.py
|
|
tests/reasoning/test_gptoss_reasoning_parser.py
|
|
tests/reasoning/test_granite_reasoning_parser.py
|
|
tests/reasoning/test_holo2_reasoning_parser.py
|
|
tests/reasoning/test_hunyuan_reasoning_parser.py
|
|
tests/reasoning/test_minimax_m2_append_reasoning_parser.py
|
|
tests/reasoning/test_minimax_m2_reasoning_parser.py
|
|
tests/reasoning/test_mistral_reasoning_parser.py
|
|
tests/reasoning/test_olmo3_reasoning_parser.py
|
|
tests/reasoning/test_qwen3_reasoning_parser.py
|
|
tests/reasoning/test_seedoss_reasoning_parser.py
|
|
tests/reasoning/utils.py
|
|
tests/rocm/aiter/test_grouped_quant.py
|
|
tests/samplers/__init__.py
|
|
tests/samplers/test_beam_search.py
|
|
tests/samplers/test_ignore_eos.py
|
|
tests/samplers/test_logprobs.py
|
|
tests/samplers/test_no_bad_words.py
|
|
tests/standalone_tests/lazy_imports.py
|
|
tests/standalone_tests/python_only_compile.sh
|
|
tests/standalone_tests/pytorch_nightly_dependency.sh
|
|
tests/system_messages/sonnet3.5_nov2024.txt
|
|
tests/tokenizers_/__init__.py
|
|
tests/tokenizers_/test_basic.py
|
|
tests/tokenizers_/test_detokenize.py
|
|
tests/tokenizers_/test_hf.py
|
|
tests/tokenizers_/test_mistral.py
|
|
tests/tokenizers_/test_registry.py
|
|
tests/tool_parsers/__init__.py
|
|
tests/tool_parsers/test_deepseekv31_tool_parser.py
|
|
tests/tool_parsers/test_ernie45_moe_tool_parser.py
|
|
tests/tool_parsers/test_glm4_moe_tool_parser.py
|
|
tests/tool_parsers/test_jamba_tool_parser.py
|
|
tests/tool_parsers/test_kimi_k2_tool_parser.py
|
|
tests/tool_parsers/test_minimax_tool_parser.py
|
|
tests/tool_parsers/test_mistral_tool_parser.py
|
|
tests/tool_parsers/test_openai_tool_parser.py
|
|
tests/tool_parsers/test_qwen3coder_tool_parser.py
|
|
tests/tool_parsers/test_seed_oss_tool_parser.py
|
|
tests/tool_parsers/test_xlam_tool_parser.py
|
|
tests/tool_use/__init__.py
|
|
tests/tool_use/conftest.py
|
|
tests/tool_use/test_chat_completion_request_validations.py
|
|
tests/tool_use/test_chat_completions.py
|
|
tests/tool_use/test_parallel_tool_calls.py
|
|
tests/tool_use/test_tool_calls.py
|
|
tests/tool_use/test_tool_choice_required.py
|
|
tests/tool_use/utils.py
|
|
tests/tool_use/mistral/__init__.py
|
|
tests/tool_use/mistral/conftest.py
|
|
tests/tool_use/mistral/test_mistral_tool_calls.py
|
|
tests/tool_use/mistral/utils.py
|
|
tests/tools/__init__.py
|
|
tests/tools/test_config_validator.py
|
|
tests/tpu/__init__.py
|
|
tests/tpu/test_compilation.py
|
|
tests/tpu/test_custom_dispatcher.py
|
|
tests/tpu/test_moe_pallas.py
|
|
tests/tpu/test_quantization_accuracy.py
|
|
tests/tpu/lora/__init__.py
|
|
tests/tpu/lora/test_lora.py
|
|
tests/transformers_utils/__init__.py
|
|
tests/transformers_utils/test_config.py
|
|
tests/transformers_utils/test_config_parser_registry.py
|
|
tests/transformers_utils/test_processor.py
|
|
tests/transformers_utils/test_repo_utils.py
|
|
tests/transformers_utils/test_utils.py
|
|
tests/utils_/__init__.py
|
|
tests/utils_/test_argparse_utils.py
|
|
tests/utils_/test_async_utils.py
|
|
tests/utils_/test_cache.py
|
|
tests/utils_/test_collection_utils.py
|
|
tests/utils_/test_func_utils.py
|
|
tests/utils_/test_gc_utils.py
|
|
tests/utils_/test_hashing.py
|
|
tests/utils_/test_import_utils.py
|
|
tests/utils_/test_jsontree.py
|
|
tests/utils_/test_mem_utils.py
|
|
tests/utils_/test_network_utils.py
|
|
tests/utils_/test_serial_utils.py
|
|
tests/utils_/test_system_utils.py
|
|
tests/utils_/test_tensor_schema.py
|
|
tests/utils_/test_torch_utils.py
|
|
tests/v1/__init__.py
|
|
tests/v1/test_oracle.py
|
|
tests/v1/test_outputs.py
|
|
tests/v1/test_request.py
|
|
tests/v1/test_serial_utils.py
|
|
tests/v1/utils.py
|
|
tests/v1/attention/test_attention_backends.py
|
|
tests/v1/attention/test_attention_backends_selection.py
|
|
tests/v1/attention/test_attention_splitting.py
|
|
tests/v1/attention/test_batch_reordering.py
|
|
tests/v1/attention/test_chunked_local_attention.py
|
|
tests/v1/attention/test_mla_backends.py
|
|
tests/v1/attention/test_rocm_attention_backends_selection.py
|
|
tests/v1/attention/test_sparse_mla_backends.py
|
|
tests/v1/attention/utils.py
|
|
tests/v1/core/__init__.py
|
|
tests/v1/core/test_async_scheduler.py
|
|
tests/v1/core/test_encoder_cache_manager.py
|
|
tests/v1/core/test_kv_cache_metrics.py
|
|
tests/v1/core/test_kv_cache_utils.py
|
|
tests/v1/core/test_kv_sharing.py
|
|
tests/v1/core/test_output.py
|
|
tests/v1/core/test_prefix_caching.py
|
|
tests/v1/core/test_priority_scheduler_random.py
|
|
tests/v1/core/test_reset_prefix_cache_e2e.py
|
|
tests/v1/core/test_scheduler.py
|
|
tests/v1/core/test_scheduler_e2e.py
|
|
tests/v1/core/test_single_type_kv_cache_manager.py
|
|
tests/v1/core/utils.py
|
|
tests/v1/cudagraph/__init__.py
|
|
tests/v1/cudagraph/test_cudagraph_dispatch.py
|
|
tests/v1/cudagraph/test_cudagraph_mode.py
|
|
tests/v1/determinism/conftest.py
|
|
tests/v1/determinism/test_batch_invariance.py
|
|
tests/v1/determinism/test_online_batch_invariance.py
|
|
tests/v1/determinism/test_rms_norm_batch_invariant.py
|
|
tests/v1/determinism/utils.py
|
|
tests/v1/distributed/__init__.py
|
|
tests/v1/distributed/test_async_llm_dp.py
|
|
tests/v1/distributed/test_dbo.py
|
|
tests/v1/distributed/test_eagle_dp.py
|
|
tests/v1/distributed/test_external_lb_dp.py
|
|
tests/v1/distributed/test_hybrid_lb_dp.py
|
|
tests/v1/distributed/test_internal_lb_dp.py
|
|
tests/v1/e2e/__init__.py
|
|
tests/v1/e2e/test_async_scheduling.py
|
|
tests/v1/e2e/test_async_spec_decode.py
|
|
tests/v1/e2e/test_cascade_attention.py
|
|
tests/v1/e2e/test_context_length.py
|
|
tests/v1/e2e/test_correctness_sliding_window.py
|
|
tests/v1/e2e/test_kv_sharing_fast_prefill.py
|
|
tests/v1/e2e/test_lora_with_spec_decode.py
|
|
tests/v1/e2e/test_min_tokens.py
|
|
tests/v1/e2e/test_pooling_chunked_prefill.py
|
|
tests/v1/e2e/test_spec_decode.py
|
|
tests/v1/ec_connector/integration/README.md
|
|
tests/v1/ec_connector/integration/hato.jpg
|
|
tests/v1/ec_connector/integration/run_epd_correctness_test.sh
|
|
tests/v1/ec_connector/integration/test_epd_correctness.py
|
|
tests/v1/ec_connector/unit/test_ec_example_connector.py
|
|
tests/v1/engine/__init__.py
|
|
tests/v1/engine/conftest.py
|
|
tests/v1/engine/test_abort_final_step.py
|
|
tests/v1/engine/test_async_llm.py
|
|
tests/v1/engine/test_engine_args.py
|
|
tests/v1/engine/test_engine_core.py
|
|
tests/v1/engine/test_engine_core_client.py
|
|
tests/v1/engine/test_fast_incdec_prefix_err.py
|
|
tests/v1/engine/test_init_error_messaging.py
|
|
tests/v1/engine/test_llm_engine.py
|
|
tests/v1/engine/test_output_processor.py
|
|
tests/v1/engine/test_parallel_sampling.py
|
|
tests/v1/engine/test_process_multi_modal_uuids.py
|
|
tests/v1/engine/utils.py
|
|
tests/v1/entrypoints/__init__.py
|
|
tests/v1/entrypoints/conftest.py
|
|
tests/v1/entrypoints/llm/__init__.py
|
|
tests/v1/entrypoints/llm/test_struct_output_generate.py
|
|
tests/v1/entrypoints/openai/test_chat_completion.py
|
|
tests/v1/entrypoints/openai/test_completion.py
|
|
tests/v1/entrypoints/openai/test_completion_with_image_embeds.py
|
|
tests/v1/entrypoints/openai/test_multi_api_servers.py
|
|
tests/v1/entrypoints/openai/serving_responses/__init__.py
|
|
tests/v1/entrypoints/openai/serving_responses/conftest.py
|
|
tests/v1/entrypoints/openai/serving_responses/test_basic.py
|
|
tests/v1/entrypoints/openai/serving_responses/test_function_call.py
|
|
tests/v1/entrypoints/openai/serving_responses/test_image.py
|
|
tests/v1/entrypoints/openai/serving_responses/test_stateful.py
|
|
tests/v1/entrypoints/openai/serving_responses/test_structured_output.py
|
|
tests/v1/executor/__init__.py
|
|
tests/v1/executor/test_executor.py
|
|
tests/v1/kv_connector/__init__.py
|
|
tests/v1/kv_connector/nixl_integration/run_accuracy_test.sh
|
|
tests/v1/kv_connector/nixl_integration/run_edge_case_test.sh
|
|
tests/v1/kv_connector/nixl_integration/run_tpu_disagg_accuracy_test.sh
|
|
tests/v1/kv_connector/nixl_integration/run_tpu_edge_case_test.sh
|
|
tests/v1/kv_connector/nixl_integration/test_accuracy.py
|
|
tests/v1/kv_connector/nixl_integration/test_disagg_accuracy.py
|
|
tests/v1/kv_connector/nixl_integration/test_edge_cases.py
|
|
tests/v1/kv_connector/nixl_integration/toy_proxy_server.py
|
|
tests/v1/kv_connector/nixl_integration/tp_config_sweep_accuracy_test.sh
|
|
tests/v1/kv_connector/unit/__init__.py
|
|
tests/v1/kv_connector/unit/test_backwards_compatibility.py
|
|
tests/v1/kv_connector/unit/test_cache_pollution_prevention.py
|
|
tests/v1/kv_connector/unit/test_config.py
|
|
tests/v1/kv_connector/unit/test_decode_bench_connector.py
|
|
tests/v1/kv_connector/unit/test_error_propagation.py
|
|
tests/v1/kv_connector/unit/test_example_connector.py
|
|
tests/v1/kv_connector/unit/test_invalid_blocks_correctness.py
|
|
tests/v1/kv_connector/unit/test_kv_connector_lifecyle.py
|
|
tests/v1/kv_connector/unit/test_kv_load_failure_recovery.py
|
|
tests/v1/kv_connector/unit/test_lmcache_connector.py
|
|
tests/v1/kv_connector/unit/test_lmcache_integration.py
|
|
tests/v1/kv_connector/unit/test_multi_connector.py
|
|
tests/v1/kv_connector/unit/test_nixl_connector.py
|
|
tests/v1/kv_connector/unit/test_offloading_connector.py
|
|
tests/v1/kv_connector/unit/test_output_aggregator.py
|
|
tests/v1/kv_connector/unit/test_remote_decode_lifecycle.py
|
|
tests/v1/kv_connector/unit/test_remote_prefill_lifecycle.py
|
|
tests/v1/kv_connector/unit/utils.py
|
|
tests/v1/kv_offload/test_cpu_gpu.py
|
|
tests/v1/kv_offload/test_cpu_manager.py
|
|
tests/v1/kv_offload/test_cpu_offloading.py
|
|
tests/v1/kv_offload/test_worker.py
|
|
tests/v1/logits_processors/__init__.py
|
|
tests/v1/logits_processors/test_correctness.py
|
|
tests/v1/logits_processors/test_custom_offline.py
|
|
tests/v1/logits_processors/test_custom_online.py
|
|
tests/v1/logits_processors/utils.py
|
|
tests/v1/metrics/test_engine_logger_apis.py
|
|
tests/v1/metrics/test_metrics_reader.py
|
|
tests/v1/metrics/test_ray_metrics.py
|
|
tests/v1/metrics/test_stats.py
|
|
tests/v1/sample/__init__.py
|
|
tests/v1/sample/test_logprobs.py
|
|
tests/v1/sample/test_logprobs_e2e.py
|
|
tests/v1/sample/test_rejection_sampler.py
|
|
tests/v1/sample/test_sampler.py
|
|
tests/v1/sample/test_sampling_params_e2e.py
|
|
tests/v1/sample/test_topk_topp_sampler.py
|
|
tests/v1/sample/utils.py
|
|
tests/v1/shutdown/test_delete.py
|
|
tests/v1/shutdown/test_forward_error.py
|
|
tests/v1/shutdown/test_processor_error.py
|
|
tests/v1/shutdown/test_startup_error.py
|
|
tests/v1/shutdown/utils.py
|
|
tests/v1/spec_decode/test_eagle.py
|
|
tests/v1/spec_decode/test_max_len.py
|
|
tests/v1/spec_decode/test_mtp.py
|
|
tests/v1/spec_decode/test_ngram.py
|
|
tests/v1/spec_decode/test_speculators_eagle3.py
|
|
tests/v1/spec_decode/test_tree_attention.py
|
|
tests/v1/structured_output/__init__.py
|
|
tests/v1/structured_output/test_backend_guidance.py
|
|
tests/v1/structured_output/test_gptoss_structural_tags.py
|
|
tests/v1/structured_output/test_reasoning_structured_output.py
|
|
tests/v1/structured_output/test_utils.py
|
|
tests/v1/tpu/__init__.py
|
|
tests/v1/tpu/test_basic.py
|
|
tests/v1/tpu/test_kv_cache_update_kernel.py
|
|
tests/v1/tpu/test_mha_attn.py
|
|
tests/v1/tpu/test_multimodal.py
|
|
tests/v1/tpu/test_pallas.py
|
|
tests/v1/tpu/test_perf.py
|
|
tests/v1/tpu/test_sampler.py
|
|
tests/v1/tpu/test_spmd_model_weight_loading.py
|
|
tests/v1/tpu/test_topk_topp_sampler.py
|
|
tests/v1/tpu/test_tpu_int8.py
|
|
tests/v1/tpu/test_tpu_qkv_linear.py
|
|
tests/v1/tpu/worker/__init__.py
|
|
tests/v1/tpu/worker/test_tpu_model_runner.py
|
|
tests/v1/tracing/__init__.py
|
|
tests/v1/tracing/test_tracing.py
|
|
tests/v1/worker/__init__.py
|
|
tests/v1/worker/test_gpu_input_batch.py
|
|
tests/v1/worker/test_gpu_model_runner.py
|
|
tests/v1/worker/test_gpu_profiler.py
|
|
tests/v1/worker/test_utils.py
|
|
tests/v1/worker/test_worker_memory_snapshot.py
|
|
tests/vllm_test_utils/setup.py
|
|
tests/vllm_test_utils/vllm_test_utils/__init__.py
|
|
tests/vllm_test_utils/vllm_test_utils/blame.py
|
|
tests/vllm_test_utils/vllm_test_utils/monitor.py
|
|
tests/weight_loading/models-amd.txt
|
|
tests/weight_loading/models-large-amd.txt
|
|
tests/weight_loading/models-large.txt
|
|
tests/weight_loading/models.txt
|
|
tests/weight_loading/run_model_weight_loading_test.sh
|
|
tests/weight_loading/test_weight_loading.py
|
|
tools/check_repo.sh
|
|
tools/flashinfer-build.sh
|
|
tools/generate_cmake_presets.py
|
|
tools/install_deepgemm.sh
|
|
tools/install_gdrcopy.sh
|
|
tools/install_nixl_from_source_ubuntu.py
|
|
tools/report_build_time_ninja.py
|
|
tools/ep_kernels/README.md
|
|
tools/ep_kernels/configure_system_drivers.sh
|
|
tools/ep_kernels/install_python_libraries.sh
|
|
tools/ep_kernels/elastic_ep/eep_nvshmem.patch
|
|
tools/ep_kernels/elastic_ep/install_eep_libraries.sh
|
|
tools/pre_commit/check_init_lazy_imports.py
|
|
tools/pre_commit/check_pickle_imports.py
|
|
tools/pre_commit/check_spdx_header.py
|
|
tools/pre_commit/check_triton_import.py
|
|
tools/pre_commit/enforce_regex_import.py
|
|
tools/pre_commit/generate_nightly_torch_test.py
|
|
tools/pre_commit/mypy.py
|
|
tools/pre_commit/png-lint.sh
|
|
tools/pre_commit/shellcheck.sh
|
|
tools/pre_commit/update-dockerfile-graph.sh
|
|
tools/pre_commit/validate_config.py
|
|
tools/profiler/print_layerwise_table.py
|
|
tools/profiler/visualize_layerwise_profile.py
|
|
tools/profiler/nsys_profile_tools/README.md
|
|
tools/profiler/nsys_profile_tools/gputrc2graph.py
|
|
tools/profiler/nsys_profile_tools/vllm_engine_model.json
|
|
tools/profiler/nsys_profile_tools/images/csv1.png
|
|
tools/profiler/nsys_profile_tools/images/html.png
|
|
tools/profiler/nsys_profile_tools/images/html_tbl.png
|
|
tools/vllm-tpu/build.sh
|
|
vllm/__init__.py
|
|
vllm/_aiter_ops.py
|
|
vllm/_bc_linter.py
|
|
vllm/_custom_ops.py
|
|
vllm/_ipex_ops.py
|
|
vllm/_version.py
|
|
vllm/beam_search.py
|
|
vllm/collect_env.py
|
|
vllm/connections.py
|
|
vllm/env_override.py
|
|
vllm/envs.py
|
|
vllm/forward_context.py
|
|
vllm/logger.py
|
|
vllm/logits_process.py
|
|
vllm/logprobs.py
|
|
vllm/outputs.py
|
|
vllm/pooling_params.py
|
|
vllm/py.typed
|
|
vllm/sampling_params.py
|
|
vllm/scalar_type.py
|
|
vllm/scripts.py
|
|
vllm/sequence.py
|
|
vllm/tasks.py
|
|
vllm/tracing.py
|
|
vllm/version.py
|
|
vllm.egg-info/PKG-INFO
|
|
vllm.egg-info/SOURCES.txt
|
|
vllm.egg-info/dependency_links.txt
|
|
vllm.egg-info/entry_points.txt
|
|
vllm.egg-info/requires.txt
|
|
vllm.egg-info/top_level.txt
|
|
vllm/assets/__init__.py
|
|
vllm/assets/audio.py
|
|
vllm/assets/base.py
|
|
vllm/assets/image.py
|
|
vllm/assets/video.py
|
|
vllm/attention/__init__.py
|
|
vllm/attention/layer.py
|
|
vllm/attention/selector.py
|
|
vllm/attention/backends/__init__.py
|
|
vllm/attention/backends/abstract.py
|
|
vllm/attention/backends/registry.py
|
|
vllm/attention/backends/utils.py
|
|
vllm/attention/layers/__init__.py
|
|
vllm/attention/layers/chunked_local_attention.py
|
|
vllm/attention/layers/cross_attention.py
|
|
vllm/attention/layers/encoder_only_attention.py
|
|
vllm/attention/layers/mm_encoder_attention.py
|
|
vllm/attention/ops/__init__.py
|
|
vllm/attention/ops/chunked_prefill_paged_decode.py
|
|
vllm/attention/ops/common.py
|
|
vllm/attention/ops/flashmla.py
|
|
vllm/attention/ops/merge_attn_states.py
|
|
vllm/attention/ops/paged_attn.py
|
|
vllm/attention/ops/pallas_kv_cache_update.py
|
|
vllm/attention/ops/prefix_prefill.py
|
|
vllm/attention/ops/rocm_aiter_mla_sparse.py
|
|
vllm/attention/ops/triton_decode_attention.py
|
|
vllm/attention/ops/triton_merge_attn_states.py
|
|
vllm/attention/ops/triton_reshape_and_cache_flash.py
|
|
vllm/attention/ops/triton_unified_attention.py
|
|
vllm/attention/ops/vit_attn_wrappers.py
|
|
vllm/attention/utils/__init__.py
|
|
vllm/attention/utils/fa_utils.py
|
|
vllm/attention/utils/kv_sharing_utils.py
|
|
vllm/attention/utils/kv_transfer_utils.py
|
|
vllm/benchmarks/__init__.py
|
|
vllm/benchmarks/datasets.py
|
|
vllm/benchmarks/latency.py
|
|
vllm/benchmarks/serve.py
|
|
vllm/benchmarks/startup.py
|
|
vllm/benchmarks/throughput.py
|
|
vllm/benchmarks/lib/__init__.py
|
|
vllm/benchmarks/lib/endpoint_request_func.py
|
|
vllm/benchmarks/lib/ready_checker.py
|
|
vllm/benchmarks/lib/utils.py
|
|
vllm/benchmarks/sweep/__init__.py
|
|
vllm/benchmarks/sweep/cli.py
|
|
vllm/benchmarks/sweep/param_sweep.py
|
|
vllm/benchmarks/sweep/plot.py
|
|
vllm/benchmarks/sweep/plot_pareto.py
|
|
vllm/benchmarks/sweep/serve.py
|
|
vllm/benchmarks/sweep/serve_sla.py
|
|
vllm/benchmarks/sweep/server.py
|
|
vllm/benchmarks/sweep/sla_sweep.py
|
|
vllm/benchmarks/sweep/utils.py
|
|
vllm/compilation/__init__.py
|
|
vllm/compilation/activation_quant_fusion.py
|
|
vllm/compilation/backends.py
|
|
vllm/compilation/base_static_graph.py
|
|
vllm/compilation/caching.py
|
|
vllm/compilation/collective_fusion.py
|
|
vllm/compilation/compiler_interface.py
|
|
vllm/compilation/counter.py
|
|
vllm/compilation/cuda_graph.py
|
|
vllm/compilation/decorators.py
|
|
vllm/compilation/fix_functionalization.py
|
|
vllm/compilation/fusion.py
|
|
vllm/compilation/fusion_attn.py
|
|
vllm/compilation/fx_utils.py
|
|
vllm/compilation/inductor_pass.py
|
|
vllm/compilation/matcher_utils.py
|
|
vllm/compilation/monitor.py
|
|
vllm/compilation/noop_elimination.py
|
|
vllm/compilation/partition_rules.py
|
|
vllm/compilation/pass_manager.py
|
|
vllm/compilation/piecewise_backend.py
|
|
vllm/compilation/post_cleanup.py
|
|
vllm/compilation/qk_norm_rope_fusion.py
|
|
vllm/compilation/rocm_aiter_fusion.py
|
|
vllm/compilation/sequence_parallelism.py
|
|
vllm/compilation/torch25_custom_graph_pass.py
|
|
vllm/compilation/vllm_inductor_pass.py
|
|
vllm/compilation/wrapper.py
|
|
vllm/config/__init__.py
|
|
vllm/config/attention.py
|
|
vllm/config/cache.py
|
|
vllm/config/compilation.py
|
|
vllm/config/device.py
|
|
vllm/config/ec_transfer.py
|
|
vllm/config/kv_events.py
|
|
vllm/config/kv_transfer.py
|
|
vllm/config/load.py
|
|
vllm/config/lora.py
|
|
vllm/config/model.py
|
|
vllm/config/multimodal.py
|
|
vllm/config/observability.py
|
|
vllm/config/parallel.py
|
|
vllm/config/pooler.py
|
|
vllm/config/profiler.py
|
|
vllm/config/scheduler.py
|
|
vllm/config/speculative.py
|
|
vllm/config/speech_to_text.py
|
|
vllm/config/structured_outputs.py
|
|
vllm/config/utils.py
|
|
vllm/config/vllm.py
|
|
vllm/device_allocator/__init__.py
|
|
vllm/device_allocator/cumem.py
|
|
vllm/distributed/__init__.py
|
|
vllm/distributed/communication_op.py
|
|
vllm/distributed/kv_events.py
|
|
vllm/distributed/parallel_state.py
|
|
vllm/distributed/tpu_distributed_utils.py
|
|
vllm/distributed/utils.py
|
|
vllm/distributed/device_communicators/__init__.py
|
|
vllm/distributed/device_communicators/all2all.py
|
|
vllm/distributed/device_communicators/all_reduce_utils.py
|
|
vllm/distributed/device_communicators/base_device_communicator.py
|
|
vllm/distributed/device_communicators/cpu_communicator.py
|
|
vllm/distributed/device_communicators/cuda_communicator.py
|
|
vllm/distributed/device_communicators/cuda_wrapper.py
|
|
vllm/distributed/device_communicators/custom_all_reduce.py
|
|
vllm/distributed/device_communicators/mnnvl_compat.py
|
|
vllm/distributed/device_communicators/pynccl.py
|
|
vllm/distributed/device_communicators/pynccl_allocator.py
|
|
vllm/distributed/device_communicators/pynccl_wrapper.py
|
|
vllm/distributed/device_communicators/quick_all_reduce.py
|
|
vllm/distributed/device_communicators/ray_communicator.py
|
|
vllm/distributed/device_communicators/shm_broadcast.py
|
|
vllm/distributed/device_communicators/shm_object_storage.py
|
|
vllm/distributed/device_communicators/symm_mem.py
|
|
vllm/distributed/device_communicators/tpu_communicator.py
|
|
vllm/distributed/device_communicators/xpu_communicator.py
|
|
vllm/distributed/ec_transfer/__init__.py
|
|
vllm/distributed/ec_transfer/ec_transfer_state.py
|
|
vllm/distributed/ec_transfer/ec_connector/__init__.py
|
|
vllm/distributed/ec_transfer/ec_connector/base.py
|
|
vllm/distributed/ec_transfer/ec_connector/example_connector.py
|
|
vllm/distributed/ec_transfer/ec_connector/factory.py
|
|
vllm/distributed/eplb/__init__.py
|
|
vllm/distributed/eplb/async_worker.py
|
|
vllm/distributed/eplb/eplb_state.py
|
|
vllm/distributed/eplb/rebalance_execute.py
|
|
vllm/distributed/eplb/policy/__init__.py
|
|
vllm/distributed/eplb/policy/abstract.py
|
|
vllm/distributed/eplb/policy/default.py
|
|
vllm/distributed/kv_transfer/README.md
|
|
vllm/distributed/kv_transfer/__init__.py
|
|
vllm/distributed/kv_transfer/disagg_prefill_workflow.jpg
|
|
vllm/distributed/kv_transfer/kv_transfer_state.py
|
|
vllm/distributed/kv_transfer/kv_connector/__init__.py
|
|
vllm/distributed/kv_transfer/kv_connector/base.py
|
|
vllm/distributed/kv_transfer/kv_connector/factory.py
|
|
vllm/distributed/kv_transfer/kv_connector/utils.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/__init__.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/base.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/decode_bench_connector.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/example_connector.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_connector.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_mp_connector.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/metrics.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/mooncake_connector.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/multi_connector.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/nixl_connector.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/offloading_connector.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/__init__.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/multi_process_adapter.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/utils.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/lmcache_integration/vllm_v1_adapter.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/p2p/__init__.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_connector.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/p2p/p2p_nccl_engine.py
|
|
vllm/distributed/kv_transfer/kv_connector/v1/p2p/tensor_memory_pool.py
|
|
vllm/engine/__init__.py
|
|
vllm/engine/arg_utils.py
|
|
vllm/engine/async_llm_engine.py
|
|
vllm/engine/llm_engine.py
|
|
vllm/engine/protocol.py
|
|
vllm/entrypoints/__init__.py
|
|
vllm/entrypoints/api_server.py
|
|
vllm/entrypoints/chat_utils.py
|
|
vllm/entrypoints/constants.py
|
|
vllm/entrypoints/context.py
|
|
vllm/entrypoints/launcher.py
|
|
vllm/entrypoints/llm.py
|
|
vllm/entrypoints/logger.py
|
|
vllm/entrypoints/renderer.py
|
|
vllm/entrypoints/responses_utils.py
|
|
vllm/entrypoints/score_utils.py
|
|
vllm/entrypoints/ssl.py
|
|
vllm/entrypoints/tool.py
|
|
vllm/entrypoints/tool_server.py
|
|
vllm/entrypoints/utils.py
|
|
vllm/entrypoints/anthropic/__init__.py
|
|
vllm/entrypoints/anthropic/protocol.py
|
|
vllm/entrypoints/anthropic/serving_messages.py
|
|
vllm/entrypoints/cli/__init__.py
|
|
vllm/entrypoints/cli/collect_env.py
|
|
vllm/entrypoints/cli/main.py
|
|
vllm/entrypoints/cli/openai.py
|
|
vllm/entrypoints/cli/run_batch.py
|
|
vllm/entrypoints/cli/serve.py
|
|
vllm/entrypoints/cli/types.py
|
|
vllm/entrypoints/cli/benchmark/__init__.py
|
|
vllm/entrypoints/cli/benchmark/base.py
|
|
vllm/entrypoints/cli/benchmark/latency.py
|
|
vllm/entrypoints/cli/benchmark/main.py
|
|
vllm/entrypoints/cli/benchmark/serve.py
|
|
vllm/entrypoints/cli/benchmark/startup.py
|
|
vllm/entrypoints/cli/benchmark/sweep.py
|
|
vllm/entrypoints/cli/benchmark/throughput.py
|
|
vllm/entrypoints/openai/__init__.py
|
|
vllm/entrypoints/openai/api_server.py
|
|
vllm/entrypoints/openai/cli_args.py
|
|
vllm/entrypoints/openai/orca_metrics.py
|
|
vllm/entrypoints/openai/protocol.py
|
|
vllm/entrypoints/openai/run_batch.py
|
|
vllm/entrypoints/openai/serving_chat.py
|
|
vllm/entrypoints/openai/serving_completion.py
|
|
vllm/entrypoints/openai/serving_engine.py
|
|
vllm/entrypoints/openai/serving_models.py
|
|
vllm/entrypoints/openai/serving_responses.py
|
|
vllm/entrypoints/openai/serving_transcription.py
|
|
vllm/entrypoints/openai/speech_to_text.py
|
|
vllm/entrypoints/openai/utils.py
|
|
vllm/entrypoints/openai/parser/__init__.py
|
|
vllm/entrypoints/openai/parser/harmony_utils.py
|
|
vllm/entrypoints/openai/parser/responses_parser.py
|
|
vllm/entrypoints/openai/tool_parsers/__init__.py
|
|
vllm/entrypoints/pooling/__init__.py
|
|
vllm/entrypoints/pooling/classify/__init__.py
|
|
vllm/entrypoints/pooling/classify/api_router.py
|
|
vllm/entrypoints/pooling/classify/protocol.py
|
|
vllm/entrypoints/pooling/classify/serving.py
|
|
vllm/entrypoints/pooling/embed/__init__.py
|
|
vllm/entrypoints/pooling/embed/api_router.py
|
|
vllm/entrypoints/pooling/embed/protocol.py
|
|
vllm/entrypoints/pooling/embed/serving.py
|
|
vllm/entrypoints/pooling/pooling/__init__.py
|
|
vllm/entrypoints/pooling/pooling/api_router.py
|
|
vllm/entrypoints/pooling/pooling/protocol.py
|
|
vllm/entrypoints/pooling/pooling/serving.py
|
|
vllm/entrypoints/pooling/score/__init__.py
|
|
vllm/entrypoints/pooling/score/api_router.py
|
|
vllm/entrypoints/pooling/score/protocol.py
|
|
vllm/entrypoints/pooling/score/serving.py
|
|
vllm/entrypoints/sagemaker/__init__.py
|
|
vllm/entrypoints/sagemaker/routes.py
|
|
vllm/entrypoints/serve/__init__.py
|
|
vllm/entrypoints/serve/disagg/__init__.py
|
|
vllm/entrypoints/serve/disagg/api_router.py
|
|
vllm/entrypoints/serve/disagg/protocol.py
|
|
vllm/entrypoints/serve/disagg/serving.py
|
|
vllm/entrypoints/serve/elastic_ep/__init__.py
|
|
vllm/entrypoints/serve/elastic_ep/api_router.py
|
|
vllm/entrypoints/serve/elastic_ep/middleware.py
|
|
vllm/entrypoints/serve/instrumentator/__init__.py
|
|
vllm/entrypoints/serve/instrumentator/health.py
|
|
vllm/entrypoints/serve/instrumentator/metrics.py
|
|
vllm/entrypoints/serve/lora/__init__.py
|
|
vllm/entrypoints/serve/lora/api_router.py
|
|
vllm/entrypoints/serve/profile/__init__.py
|
|
vllm/entrypoints/serve/profile/api_router.py
|
|
vllm/entrypoints/serve/rlhf/__init__.py
|
|
vllm/entrypoints/serve/rlhf/api_router.py
|
|
vllm/entrypoints/serve/sleep/__init__.py
|
|
vllm/entrypoints/serve/sleep/api_router.py
|
|
vllm/entrypoints/serve/tokenize/__init__.py
|
|
vllm/entrypoints/serve/tokenize/api_router.py
|
|
vllm/entrypoints/serve/tokenize/serving.py
|
|
vllm/inputs/__init__.py
|
|
vllm/inputs/data.py
|
|
vllm/inputs/parse.py
|
|
vllm/inputs/preprocess.py
|
|
vllm/logging_utils/__init__.py
|
|
vllm/logging_utils/dump_input.py
|
|
vllm/logging_utils/formatter.py
|
|
vllm/logging_utils/lazy.py
|
|
vllm/logging_utils/log_time.py
|
|
vllm/lora/__init__.py
|
|
vllm/lora/lora_model.py
|
|
vllm/lora/lora_weights.py
|
|
vllm/lora/model_manager.py
|
|
vllm/lora/peft_helper.py
|
|
vllm/lora/request.py
|
|
vllm/lora/resolver.py
|
|
vllm/lora/utils.py
|
|
vllm/lora/worker_manager.py
|
|
vllm/lora/layers/__init__.py
|
|
vllm/lora/layers/base.py
|
|
vllm/lora/layers/base_linear.py
|
|
vllm/lora/layers/column_parallel_linear.py
|
|
vllm/lora/layers/fused_moe.py
|
|
vllm/lora/layers/logits_processor.py
|
|
vllm/lora/layers/replicated_linear.py
|
|
vllm/lora/layers/row_parallel_linear.py
|
|
vllm/lora/layers/utils.py
|
|
vllm/lora/layers/vocal_parallel_embedding.py
|
|
vllm/lora/ops/__init__.py
|
|
vllm/lora/ops/ipex_ops/__init__.py
|
|
vllm/lora/ops/ipex_ops/lora_ops.py
|
|
vllm/lora/ops/torch_ops/__init__.py
|
|
vllm/lora/ops/torch_ops/lora_ops.py
|
|
vllm/lora/ops/triton_ops/README_TUNING.md
|
|
vllm/lora/ops/triton_ops/__init__.py
|
|
vllm/lora/ops/triton_ops/fused_moe_lora_op.py
|
|
vllm/lora/ops/triton_ops/kernel_utils.py
|
|
vllm/lora/ops/triton_ops/lora_expand_op.py
|
|
vllm/lora/ops/triton_ops/lora_kernel_metadata.py
|
|
vllm/lora/ops/triton_ops/lora_shrink_op.py
|
|
vllm/lora/ops/triton_ops/utils.py
|
|
vllm/lora/ops/xla_ops/__init__.py
|
|
vllm/lora/ops/xla_ops/lora_ops.py
|
|
vllm/lora/punica_wrapper/__init__.py
|
|
vllm/lora/punica_wrapper/punica_base.py
|
|
vllm/lora/punica_wrapper/punica_cpu.py
|
|
vllm/lora/punica_wrapper/punica_gpu.py
|
|
vllm/lora/punica_wrapper/punica_selector.py
|
|
vllm/lora/punica_wrapper/punica_tpu.py
|
|
vllm/lora/punica_wrapper/punica_xpu.py
|
|
vllm/lora/punica_wrapper/utils.py
|
|
vllm/model_executor/__init__.py
|
|
vllm/model_executor/custom_op.py
|
|
vllm/model_executor/parameter.py
|
|
vllm/model_executor/utils.py
|
|
vllm/model_executor/layers/__init__.py
|
|
vllm/model_executor/layers/activation.py
|
|
vllm/model_executor/layers/attention_layer_base.py
|
|
vllm/model_executor/layers/batch_invariant.py
|
|
vllm/model_executor/layers/conv.py
|
|
vllm/model_executor/layers/kda.py
|
|
vllm/model_executor/layers/layernorm.py
|
|
vllm/model_executor/layers/lightning_attn.py
|
|
vllm/model_executor/layers/linear.py
|
|
vllm/model_executor/layers/logits_processor.py
|
|
vllm/model_executor/layers/mla.py
|
|
vllm/model_executor/layers/pooler.py
|
|
vllm/model_executor/layers/resampler.py
|
|
vllm/model_executor/layers/utils.py
|
|
vllm/model_executor/layers/vocab_parallel_embedding.py
|
|
vllm/model_executor/layers/fla/__init__.py
|
|
vllm/model_executor/layers/fla/ops/__init__.py
|
|
vllm/model_executor/layers/fla/ops/chunk.py
|
|
vllm/model_executor/layers/fla/ops/chunk_delta_h.py
|
|
vllm/model_executor/layers/fla/ops/chunk_o.py
|
|
vllm/model_executor/layers/fla/ops/chunk_scaled_dot_kkt.py
|
|
vllm/model_executor/layers/fla/ops/cumsum.py
|
|
vllm/model_executor/layers/fla/ops/fused_recurrent.py
|
|
vllm/model_executor/layers/fla/ops/index.py
|
|
vllm/model_executor/layers/fla/ops/kda.py
|
|
vllm/model_executor/layers/fla/ops/l2norm.py
|
|
vllm/model_executor/layers/fla/ops/layernorm_guard.py
|
|
vllm/model_executor/layers/fla/ops/op.py
|
|
vllm/model_executor/layers/fla/ops/solve_tril.py
|
|
vllm/model_executor/layers/fla/ops/utils.py
|
|
vllm/model_executor/layers/fla/ops/wy_fast.py
|
|
vllm/model_executor/layers/fused_moe/__init__.py
|
|
vllm/model_executor/layers/fused_moe/all2all_utils.py
|
|
vllm/model_executor/layers/fused_moe/batched_deep_gemm_moe.py
|
|
vllm/model_executor/layers/fused_moe/config.py
|
|
vllm/model_executor/layers/fused_moe/cpu_fused_moe.py
|
|
vllm/model_executor/layers/fused_moe/cutlass_moe.py
|
|
vllm/model_executor/layers/fused_moe/deep_gemm_moe.py
|
|
vllm/model_executor/layers/fused_moe/deep_gemm_utils.py
|
|
vllm/model_executor/layers/fused_moe/deepep_ht_prepare_finalize.py
|
|
vllm/model_executor/layers/fused_moe/deepep_ll_prepare_finalize.py
|
|
vllm/model_executor/layers/fused_moe/flashinfer_cutedsl_moe.py
|
|
vllm/model_executor/layers/fused_moe/flashinfer_cutlass_moe.py
|
|
vllm/model_executor/layers/fused_moe/flashinfer_cutlass_prepare_finalize.py
|
|
vllm/model_executor/layers/fused_moe/flashinfer_trtllm_moe.py
|
|
vllm/model_executor/layers/fused_moe/fused_batched_moe.py
|
|
vllm/model_executor/layers/fused_moe/fused_marlin_moe.py
|
|
vllm/model_executor/layers/fused_moe/fused_moe.py
|
|
vllm/model_executor/layers/fused_moe/fused_moe_method_base.py
|
|
vllm/model_executor/layers/fused_moe/fused_moe_modular_method.py
|
|
vllm/model_executor/layers/fused_moe/gpt_oss_triton_kernels_moe.py
|
|
vllm/model_executor/layers/fused_moe/layer.py
|
|
vllm/model_executor/layers/fused_moe/modular_kernel.py
|
|
vllm/model_executor/layers/fused_moe/moe_align_block_size.py
|
|
vllm/model_executor/layers/fused_moe/moe_pallas.py
|
|
vllm/model_executor/layers/fused_moe/moe_permute_unpermute.py
|
|
vllm/model_executor/layers/fused_moe/moe_torch_iterative.py
|
|
vllm/model_executor/layers/fused_moe/pplx_prepare_finalize.py
|
|
vllm/model_executor/layers/fused_moe/prepare_finalize.py
|
|
vllm/model_executor/layers/fused_moe/rocm_aiter_fused_moe.py
|
|
vllm/model_executor/layers/fused_moe/routing_simulator.py
|
|
vllm/model_executor/layers/fused_moe/shared_fused_moe.py
|
|
vllm/model_executor/layers/fused_moe/topk_weight_and_reduce.py
|
|
vllm/model_executor/layers/fused_moe/triton_deep_gemm_moe.py
|
|
vllm/model_executor/layers/fused_moe/trtllm_moe.py
|
|
vllm/model_executor/layers/fused_moe/unquantized_fused_moe_method.py
|
|
vllm/model_executor/layers/fused_moe/utils.py
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=1792,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=3072,device_name=NVIDIA_H200,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=1,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H100,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=1024,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=1856,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=1856,device_name=NVIDIA_L40S.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20-3e.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H20.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=192,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=352,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20-3e.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H20.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=384,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=512,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_B200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=704,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=AMD_Instinct_MI308X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H20.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=768,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=bf16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=928,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=928,device_name=NVIDIA_L40S.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=128,N=96,device_name=NVIDIA_H20.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_B200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H100.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1024,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-40GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1344,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=2048,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=2688,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=3072,device_name=NVIDIA_H200,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=3200,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=6400,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=float8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=int8_w8a16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=16,N=800,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=AMD_Instinct_MI350_OAM,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_A800-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H20-3e.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=320,device_name=NVIDIA_H20-3e.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI350_OAM,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=384,device_name=AMD_Instinct_MI355_OAM,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=160,N=640,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=20,N=1536,device_name=NVIDIA_RTX_PRO_6000_Blackwell_Server_Edition,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=20,N=2560,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=1024,device_name=AMD_Instinct_MI325X,block_shape=[128,128].json
|
|
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
|
|
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
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A100-SXM4-80GB,dtype=int8_w8a8.json
|
|
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
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_A800-SXM4-80GB,dtype=int8_w8a8.json
|
|
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
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H20-3e,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=384,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=512,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=256,N=64,device_name=NVIDIA_A800-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=32,N=1408,device_name=NVIDIA_B200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=32,N=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=32,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=384,N=128,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=384,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=40,N=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_GB200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=40,N=2560,device_name=NVIDIA_H100,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_B200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H20-3e.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=128,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_B200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H20-3e.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=256,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_B200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_GB200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H20-3e.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=512,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_B200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H20-3e.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=512,N=64,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=60,N=1408,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=60,N=176,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=60,N=352,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=60,N=704,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=62,N=128,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=62,N=256,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=62,N=512,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_A800-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=1280,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=1408,device_name=NVIDIA_B200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=2560,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=3072,device_name=NVIDIA_H20.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=320,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=384,device_name=NVIDIA_H20.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_A800-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=640,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H100_PCIe,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=768,device_name=NVIDIA_H20.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=896,device_name=NVIDIA_H20.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=bf16.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=64,N=8960,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=72,N=192,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=72,N=384,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=72,N=768,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=AMD_Instinct_MI325X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=14336,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=16384,device_name=AMD_Instinct_MI325X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=AMD_Instinct_MI325X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-40GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=1792,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=AMD_Instinct_MI325X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=2048,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=AMD_Instinct_MI325X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-40GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_GeForce_RTX_4090,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=3584,device_name=NVIDIA_L40S.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=AMD_Instinct_MI325X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=4096,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=AMD_Instinct_MI325X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_A100-SXM4-80GB.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H100_80GB_HBM3.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=7168,device_name=NVIDIA_H200.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI300X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=AMD_Instinct_MI325X.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/E=8,N=8192,device_name=NVIDIA_H200,dtype=fp8_w8a8.json
|
|
vllm/model_executor/layers/fused_moe/configs/README
|
|
vllm/model_executor/layers/mamba/__init__.py
|
|
vllm/model_executor/layers/mamba/abstract.py
|
|
vllm/model_executor/layers/mamba/linear_attn.py
|
|
vllm/model_executor/layers/mamba/mamba_mixer.py
|
|
vllm/model_executor/layers/mamba/mamba_mixer2.py
|
|
vllm/model_executor/layers/mamba/mamba_utils.py
|
|
vllm/model_executor/layers/mamba/short_conv.py
|
|
vllm/model_executor/layers/mamba/ops/__init__.py
|
|
vllm/model_executor/layers/mamba/ops/causal_conv1d.py
|
|
vllm/model_executor/layers/mamba/ops/layernorm_gated.py
|
|
vllm/model_executor/layers/mamba/ops/mamba_ssm.py
|
|
vllm/model_executor/layers/mamba/ops/ssd_bmm.py
|
|
vllm/model_executor/layers/mamba/ops/ssd_chunk_scan.py
|
|
vllm/model_executor/layers/mamba/ops/ssd_chunk_state.py
|
|
vllm/model_executor/layers/mamba/ops/ssd_combined.py
|
|
vllm/model_executor/layers/mamba/ops/ssd_state_passing.py
|
|
vllm/model_executor/layers/quantization/__init__.py
|
|
vllm/model_executor/layers/quantization/auto_round.py
|
|
vllm/model_executor/layers/quantization/awq.py
|
|
vllm/model_executor/layers/quantization/awq_marlin.py
|
|
vllm/model_executor/layers/quantization/awq_triton.py
|
|
vllm/model_executor/layers/quantization/base_config.py
|
|
vllm/model_executor/layers/quantization/bitblas.py
|
|
vllm/model_executor/layers/quantization/bitsandbytes.py
|
|
vllm/model_executor/layers/quantization/cpu_wna16.py
|
|
vllm/model_executor/layers/quantization/deepspeedfp.py
|
|
vllm/model_executor/layers/quantization/experts_int8.py
|
|
vllm/model_executor/layers/quantization/fbgemm_fp8.py
|
|
vllm/model_executor/layers/quantization/fp8.py
|
|
vllm/model_executor/layers/quantization/fp_quant.py
|
|
vllm/model_executor/layers/quantization/gguf.py
|
|
vllm/model_executor/layers/quantization/gptq.py
|
|
vllm/model_executor/layers/quantization/gptq_bitblas.py
|
|
vllm/model_executor/layers/quantization/gptq_marlin.py
|
|
vllm/model_executor/layers/quantization/gptq_marlin_24.py
|
|
vllm/model_executor/layers/quantization/hqq_marlin.py
|
|
vllm/model_executor/layers/quantization/inc.py
|
|
vllm/model_executor/layers/quantization/input_quant_fp8.py
|
|
vllm/model_executor/layers/quantization/ipex_quant.py
|
|
vllm/model_executor/layers/quantization/kv_cache.py
|
|
vllm/model_executor/layers/quantization/modelopt.py
|
|
vllm/model_executor/layers/quantization/moe_wna16.py
|
|
vllm/model_executor/layers/quantization/mxfp4.py
|
|
vllm/model_executor/layers/quantization/petit.py
|
|
vllm/model_executor/layers/quantization/ptpc_fp8.py
|
|
vllm/model_executor/layers/quantization/qutlass_utils.py
|
|
vllm/model_executor/layers/quantization/rtn.py
|
|
vllm/model_executor/layers/quantization/schema.py
|
|
vllm/model_executor/layers/quantization/torchao.py
|
|
vllm/model_executor/layers/quantization/tpu_int8.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/__init__.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/triton_scaled_mm.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/utils.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/__init__.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_24.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_scheme.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_24.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a16_nvfp4.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a4_nvfp4.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_fp8.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w4a8_int.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a16_fp8.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_fp8.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_wNa16.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/transform/__init__.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/transform/linear.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/transform/module.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/transform/utils.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/__init__.py
|
|
vllm/model_executor/layers/quantization/compressed_tensors/transform/schemes/linear_qutlass_nvfp4.py
|
|
vllm/model_executor/layers/quantization/kernels/__init__.py
|
|
vllm/model_executor/layers/quantization/kernels/mixed_precision/MPLinearKernel.py
|
|
vllm/model_executor/layers/quantization/kernels/mixed_precision/__init__.py
|
|
vllm/model_executor/layers/quantization/kernels/mixed_precision/allspark.py
|
|
vllm/model_executor/layers/quantization/kernels/mixed_precision/bitblas.py
|
|
vllm/model_executor/layers/quantization/kernels/mixed_precision/conch.py
|
|
vllm/model_executor/layers/quantization/kernels/mixed_precision/cutlass.py
|
|
vllm/model_executor/layers/quantization/kernels/mixed_precision/dynamic_4bit.py
|
|
vllm/model_executor/layers/quantization/kernels/mixed_precision/exllama.py
|
|
vllm/model_executor/layers/quantization/kernels/mixed_precision/machete.py
|
|
vllm/model_executor/layers/quantization/kernels/mixed_precision/marlin.py
|
|
vllm/model_executor/layers/quantization/kernels/mixed_precision/xpu.py
|
|
vllm/model_executor/layers/quantization/kernels/scaled_mm/ScaledMMLinearKernel.py
|
|
vllm/model_executor/layers/quantization/kernels/scaled_mm/__init__.py
|
|
vllm/model_executor/layers/quantization/kernels/scaled_mm/aiter.py
|
|
vllm/model_executor/layers/quantization/kernels/scaled_mm/cpu.py
|
|
vllm/model_executor/layers/quantization/kernels/scaled_mm/cutlass.py
|
|
vllm/model_executor/layers/quantization/kernels/scaled_mm/triton.py
|
|
vllm/model_executor/layers/quantization/kernels/scaled_mm/xla.py
|
|
vllm/model_executor/layers/quantization/quark/__init__.py
|
|
vllm/model_executor/layers/quantization/quark/quark.py
|
|
vllm/model_executor/layers/quantization/quark/quark_moe.py
|
|
vllm/model_executor/layers/quantization/quark/utils.py
|
|
vllm/model_executor/layers/quantization/quark/schemes/__init__.py
|
|
vllm/model_executor/layers/quantization/quark/schemes/quark_ocp_mx.py
|
|
vllm/model_executor/layers/quantization/quark/schemes/quark_scheme.py
|
|
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_fp8.py
|
|
vllm/model_executor/layers/quantization/quark/schemes/quark_w8a8_int8.py
|
|
vllm/model_executor/layers/quantization/utils/__init__.py
|
|
vllm/model_executor/layers/quantization/utils/allspark_utils.py
|
|
vllm/model_executor/layers/quantization/utils/bitblas_utils.py
|
|
vllm/model_executor/layers/quantization/utils/flashinfer_fp4_moe.py
|
|
vllm/model_executor/layers/quantization/utils/flashinfer_utils.py
|
|
vllm/model_executor/layers/quantization/utils/fp8_utils.py
|
|
vllm/model_executor/layers/quantization/utils/gptq_utils.py
|
|
vllm/model_executor/layers/quantization/utils/int8_utils.py
|
|
vllm/model_executor/layers/quantization/utils/layer_utils.py
|
|
vllm/model_executor/layers/quantization/utils/machete_utils.py
|
|
vllm/model_executor/layers/quantization/utils/marlin_utils.py
|
|
vllm/model_executor/layers/quantization/utils/marlin_utils_fp4.py
|
|
vllm/model_executor/layers/quantization/utils/marlin_utils_fp8.py
|
|
vllm/model_executor/layers/quantization/utils/marlin_utils_test.py
|
|
vllm/model_executor/layers/quantization/utils/marlin_utils_test_24.py
|
|
vllm/model_executor/layers/quantization/utils/mxfp4_utils.py
|
|
vllm/model_executor/layers/quantization/utils/mxfp6_utils.py
|
|
vllm/model_executor/layers/quantization/utils/mxfp8_utils.py
|
|
vllm/model_executor/layers/quantization/utils/nvfp4_emulation_utils.py
|
|
vllm/model_executor/layers/quantization/utils/nvfp4_moe_support.py
|
|
vllm/model_executor/layers/quantization/utils/ocp_mx_utils.py
|
|
vllm/model_executor/layers/quantization/utils/petit_utils.py
|
|
vllm/model_executor/layers/quantization/utils/quant_utils.py
|
|
vllm/model_executor/layers/quantization/utils/w8a8_utils.py
|
|
vllm/model_executor/layers/quantization/utils/configs/N=10240,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=12288,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=1536,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=1536,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2048,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2112,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=2304,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=24576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=256,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=1536,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=3072,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=32768,K=512,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=36864,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4096,K=512,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H100_80GB_HBM3,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4096,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=4608,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=512,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=5120,K=25600,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=5120,K=8192,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=51200,K=5120,device_name=NVIDIA_L40S,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=576,K=7168,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1024,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=1152,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=128,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=16384,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
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
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=18432,device_name=NVIDIA_L20Y,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2048,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=2304,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_B200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H20,dtype=int8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_H200,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=256,device_name=NVIDIA_L20,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=7168,K=8192,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI300X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
vllm/model_executor/layers/quantization/utils/configs/N=8192,K=1536,device_name=AMD_Instinct_MI325X,dtype=fp8_w8a8,block_shape=[128,128].json
|
|
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
|
|
vllm/model_executor/layers/quantization/utils/configs/README.md
|
|
vllm/model_executor/layers/rotary_embedding/__init__.py
|
|
vllm/model_executor/layers/rotary_embedding/base.py
|
|
vllm/model_executor/layers/rotary_embedding/common.py
|
|
vllm/model_executor/layers/rotary_embedding/deepseek_scaling_rope.py
|
|
vllm/model_executor/layers/rotary_embedding/dual_chunk_rope.py
|
|
vllm/model_executor/layers/rotary_embedding/dynamic_ntk_alpha_rope.py
|
|
vllm/model_executor/layers/rotary_embedding/dynamic_ntk_scaling_rope.py
|
|
vllm/model_executor/layers/rotary_embedding/ernie45_vl_rope.py
|
|
vllm/model_executor/layers/rotary_embedding/linear_scaling_rope.py
|
|
vllm/model_executor/layers/rotary_embedding/llama3_rope.py
|
|
vllm/model_executor/layers/rotary_embedding/llama4_vision_rope.py
|
|
vllm/model_executor/layers/rotary_embedding/mrope.py
|
|
vllm/model_executor/layers/rotary_embedding/ntk_scaling_rope.py
|
|
vllm/model_executor/layers/rotary_embedding/phi3_long_rope_scaled_rope.py
|
|
vllm/model_executor/layers/rotary_embedding/xdrope.py
|
|
vllm/model_executor/layers/rotary_embedding/yarn_scaling_rope.py
|
|
vllm/model_executor/model_loader/__init__.py
|
|
vllm/model_executor/model_loader/base_loader.py
|
|
vllm/model_executor/model_loader/bitsandbytes_loader.py
|
|
vllm/model_executor/model_loader/default_loader.py
|
|
vllm/model_executor/model_loader/dummy_loader.py
|
|
vllm/model_executor/model_loader/gguf_loader.py
|
|
vllm/model_executor/model_loader/online_quantization.py
|
|
vllm/model_executor/model_loader/runai_streamer_loader.py
|
|
vllm/model_executor/model_loader/sharded_state_loader.py
|
|
vllm/model_executor/model_loader/tensorizer.py
|
|
vllm/model_executor/model_loader/tensorizer_loader.py
|
|
vllm/model_executor/model_loader/tpu.py
|
|
vllm/model_executor/model_loader/utils.py
|
|
vllm/model_executor/model_loader/weight_utils.py
|
|
vllm/model_executor/models/__init__.py
|
|
vllm/model_executor/models/adapters.py
|
|
vllm/model_executor/models/afmoe.py
|
|
vllm/model_executor/models/aimv2.py
|
|
vllm/model_executor/models/apertus.py
|
|
vllm/model_executor/models/arcee.py
|
|
vllm/model_executor/models/arctic.py
|
|
vllm/model_executor/models/aria.py
|
|
vllm/model_executor/models/audioflamingo3.py
|
|
vllm/model_executor/models/aya_vision.py
|
|
vllm/model_executor/models/bagel.py
|
|
vllm/model_executor/models/baichuan.py
|
|
vllm/model_executor/models/bailing_moe.py
|
|
vllm/model_executor/models/bamba.py
|
|
vllm/model_executor/models/bee.py
|
|
vllm/model_executor/models/bert.py
|
|
vllm/model_executor/models/bert_with_rope.py
|
|
vllm/model_executor/models/blip.py
|
|
vllm/model_executor/models/blip2.py
|
|
vllm/model_executor/models/bloom.py
|
|
vllm/model_executor/models/chameleon.py
|
|
vllm/model_executor/models/chatglm.py
|
|
vllm/model_executor/models/clip.py
|
|
vllm/model_executor/models/cohere2_vision.py
|
|
vllm/model_executor/models/commandr.py
|
|
vllm/model_executor/models/config.py
|
|
vllm/model_executor/models/dbrx.py
|
|
vllm/model_executor/models/deepencoder.py
|
|
vllm/model_executor/models/deepseek_eagle.py
|
|
vllm/model_executor/models/deepseek_mtp.py
|
|
vllm/model_executor/models/deepseek_ocr.py
|
|
vllm/model_executor/models/deepseek_v2.py
|
|
vllm/model_executor/models/deepseek_vl2.py
|
|
vllm/model_executor/models/dots1.py
|
|
vllm/model_executor/models/dots_ocr.py
|
|
vllm/model_executor/models/ernie45.py
|
|
vllm/model_executor/models/ernie45_moe.py
|
|
vllm/model_executor/models/ernie45_vl.py
|
|
vllm/model_executor/models/ernie45_vl_moe.py
|
|
vllm/model_executor/models/ernie_mtp.py
|
|
vllm/model_executor/models/exaone.py
|
|
vllm/model_executor/models/exaone4.py
|
|
vllm/model_executor/models/fairseq2_llama.py
|
|
vllm/model_executor/models/falcon.py
|
|
vllm/model_executor/models/falcon_h1.py
|
|
vllm/model_executor/models/flex_olmo.py
|
|
vllm/model_executor/models/fuyu.py
|
|
vllm/model_executor/models/gemma.py
|
|
vllm/model_executor/models/gemma2.py
|
|
vllm/model_executor/models/gemma3.py
|
|
vllm/model_executor/models/gemma3_mm.py
|
|
vllm/model_executor/models/gemma3n.py
|
|
vllm/model_executor/models/gemma3n_mm.py
|
|
vllm/model_executor/models/glm.py
|
|
vllm/model_executor/models/glm4.py
|
|
vllm/model_executor/models/glm4_1v.py
|
|
vllm/model_executor/models/glm4_moe.py
|
|
vllm/model_executor/models/glm4_moe_mtp.py
|
|
vllm/model_executor/models/glm4v.py
|
|
vllm/model_executor/models/gpt2.py
|
|
vllm/model_executor/models/gpt_bigcode.py
|
|
vllm/model_executor/models/gpt_j.py
|
|
vllm/model_executor/models/gpt_neox.py
|
|
vllm/model_executor/models/gpt_oss.py
|
|
vllm/model_executor/models/granite.py
|
|
vllm/model_executor/models/granite_speech.py
|
|
vllm/model_executor/models/granitemoe.py
|
|
vllm/model_executor/models/granitemoehybrid.py
|
|
vllm/model_executor/models/granitemoeshared.py
|
|
vllm/model_executor/models/gritlm.py
|
|
vllm/model_executor/models/grok1.py
|
|
vllm/model_executor/models/h2ovl.py
|
|
vllm/model_executor/models/hunyuan_v1.py
|
|
vllm/model_executor/models/hunyuan_vision.py
|
|
vllm/model_executor/models/hyperclovax_vision.py
|
|
vllm/model_executor/models/idefics2_vision_model.py
|
|
vllm/model_executor/models/idefics3.py
|
|
vllm/model_executor/models/interfaces.py
|
|
vllm/model_executor/models/interfaces_base.py
|
|
vllm/model_executor/models/intern_vit.py
|
|
vllm/model_executor/models/internlm2.py
|
|
vllm/model_executor/models/internlm2_ve.py
|
|
vllm/model_executor/models/interns1.py
|
|
vllm/model_executor/models/interns1_vit.py
|
|
vllm/model_executor/models/internvl.py
|
|
vllm/model_executor/models/jais.py
|
|
vllm/model_executor/models/jais2.py
|
|
vllm/model_executor/models/jamba.py
|
|
vllm/model_executor/models/jina_vl.py
|
|
vllm/model_executor/models/keye.py
|
|
vllm/model_executor/models/keye_vl1_5.py
|
|
vllm/model_executor/models/kimi_linear.py
|
|
vllm/model_executor/models/kimi_vl.py
|
|
vllm/model_executor/models/lfm2.py
|
|
vllm/model_executor/models/lfm2_moe.py
|
|
vllm/model_executor/models/lightonocr.py
|
|
vllm/model_executor/models/llama.py
|
|
vllm/model_executor/models/llama4.py
|
|
vllm/model_executor/models/llama4_eagle.py
|
|
vllm/model_executor/models/llama_eagle.py
|
|
vllm/model_executor/models/llama_eagle3.py
|
|
vllm/model_executor/models/llava.py
|
|
vllm/model_executor/models/llava_next.py
|
|
vllm/model_executor/models/llava_next_video.py
|
|
vllm/model_executor/models/llava_onevision.py
|
|
vllm/model_executor/models/longcat_flash.py
|
|
vllm/model_executor/models/longcat_flash_mtp.py
|
|
vllm/model_executor/models/mamba.py
|
|
vllm/model_executor/models/mamba2.py
|
|
vllm/model_executor/models/medusa.py
|
|
vllm/model_executor/models/midashenglm.py
|
|
vllm/model_executor/models/mimo.py
|
|
vllm/model_executor/models/mimo_mtp.py
|
|
vllm/model_executor/models/minicpm.py
|
|
vllm/model_executor/models/minicpm3.py
|
|
vllm/model_executor/models/minicpm_eagle.py
|
|
vllm/model_executor/models/minicpmo.py
|
|
vllm/model_executor/models/minicpmv.py
|
|
vllm/model_executor/models/minimax_m2.py
|
|
vllm/model_executor/models/minimax_text_01.py
|
|
vllm/model_executor/models/minimax_vl_01.py
|
|
vllm/model_executor/models/mistral3.py
|
|
vllm/model_executor/models/mistral_large_3.py
|
|
vllm/model_executor/models/mistral_large_3_eagle.py
|
|
vllm/model_executor/models/mixtral.py
|
|
vllm/model_executor/models/mllama4.py
|
|
vllm/model_executor/models/mlp_speculator.py
|
|
vllm/model_executor/models/modernbert.py
|
|
vllm/model_executor/models/module_mapping.py
|
|
vllm/model_executor/models/molmo.py
|
|
vllm/model_executor/models/moonvit.py
|
|
vllm/model_executor/models/mpt.py
|
|
vllm/model_executor/models/nano_nemotron_vl.py
|
|
vllm/model_executor/models/nemotron.py
|
|
vllm/model_executor/models/nemotron_h.py
|
|
vllm/model_executor/models/nemotron_nas.py
|
|
vllm/model_executor/models/nemotron_vl.py
|
|
vllm/model_executor/models/nvlm_d.py
|
|
vllm/model_executor/models/olmo.py
|
|
vllm/model_executor/models/olmo2.py
|
|
vllm/model_executor/models/olmoe.py
|
|
vllm/model_executor/models/opencua.py
|
|
vllm/model_executor/models/openpangu.py
|
|
vllm/model_executor/models/openpangu_mtp.py
|
|
vllm/model_executor/models/opt.py
|
|
vllm/model_executor/models/orion.py
|
|
vllm/model_executor/models/ouro.py
|
|
vllm/model_executor/models/ovis.py
|
|
vllm/model_executor/models/ovis2_5.py
|
|
vllm/model_executor/models/paddleocr_vl.py
|
|
vllm/model_executor/models/paligemma.py
|
|
vllm/model_executor/models/persimmon.py
|
|
vllm/model_executor/models/phi.py
|
|
vllm/model_executor/models/phi3.py
|
|
vllm/model_executor/models/phi3v.py
|
|
vllm/model_executor/models/phi4mm.py
|
|
vllm/model_executor/models/phi4mm_audio.py
|
|
vllm/model_executor/models/phi4mm_utils.py
|
|
vllm/model_executor/models/phimoe.py
|
|
vllm/model_executor/models/pixtral.py
|
|
vllm/model_executor/models/plamo2.py
|
|
vllm/model_executor/models/plamo3.py
|
|
vllm/model_executor/models/qwen.py
|
|
vllm/model_executor/models/qwen2.py
|
|
vllm/model_executor/models/qwen2_5_omni_thinker.py
|
|
vllm/model_executor/models/qwen2_5_vl.py
|
|
vllm/model_executor/models/qwen2_audio.py
|
|
vllm/model_executor/models/qwen2_moe.py
|
|
vllm/model_executor/models/qwen2_rm.py
|
|
vllm/model_executor/models/qwen2_vl.py
|
|
vllm/model_executor/models/qwen3.py
|
|
vllm/model_executor/models/qwen3_moe.py
|
|
vllm/model_executor/models/qwen3_next.py
|
|
vllm/model_executor/models/qwen3_next_mtp.py
|
|
vllm/model_executor/models/qwen3_omni_moe_thinker.py
|
|
vllm/model_executor/models/qwen3_vl.py
|
|
vllm/model_executor/models/qwen3_vl_moe.py
|
|
vllm/model_executor/models/qwen_vl.py
|
|
vllm/model_executor/models/radio.py
|
|
vllm/model_executor/models/registry.py
|
|
vllm/model_executor/models/roberta.py
|
|
vllm/model_executor/models/rvl.py
|
|
vllm/model_executor/models/seed_oss.py
|
|
vllm/model_executor/models/siglip.py
|
|
vllm/model_executor/models/siglip2navit.py
|
|
vllm/model_executor/models/skyworkr1v.py
|
|
vllm/model_executor/models/smolvlm.py
|
|
vllm/model_executor/models/solar.py
|
|
vllm/model_executor/models/stablelm.py
|
|
vllm/model_executor/models/starcoder2.py
|
|
vllm/model_executor/models/step3_text.py
|
|
vllm/model_executor/models/step3_vl.py
|
|
vllm/model_executor/models/swin.py
|
|
vllm/model_executor/models/tarsier.py
|
|
vllm/model_executor/models/telechat2.py
|
|
vllm/model_executor/models/teleflm.py
|
|
vllm/model_executor/models/terratorch.py
|
|
vllm/model_executor/models/ultravox.py
|
|
vllm/model_executor/models/utils.py
|
|
vllm/model_executor/models/vision.py
|
|
vllm/model_executor/models/voxtral.py
|
|
vllm/model_executor/models/whisper.py
|
|
vllm/model_executor/models/zamba2.py
|
|
vllm/model_executor/models/transformers/__init__.py
|
|
vllm/model_executor/models/transformers/base.py
|
|
vllm/model_executor/models/transformers/causal.py
|
|
vllm/model_executor/models/transformers/legacy.py
|
|
vllm/model_executor/models/transformers/moe.py
|
|
vllm/model_executor/models/transformers/multimodal.py
|
|
vllm/model_executor/models/transformers/pooling.py
|
|
vllm/model_executor/models/transformers/utils.py
|
|
vllm/model_executor/warmup/__init__.py
|
|
vllm/model_executor/warmup/deep_gemm_warmup.py
|
|
vllm/model_executor/warmup/kernel_warmup.py
|
|
vllm/multimodal/__init__.py
|
|
vllm/multimodal/audio.py
|
|
vllm/multimodal/base.py
|
|
vllm/multimodal/cache.py
|
|
vllm/multimodal/evs.py
|
|
vllm/multimodal/hasher.py
|
|
vllm/multimodal/image.py
|
|
vllm/multimodal/inputs.py
|
|
vllm/multimodal/parse.py
|
|
vllm/multimodal/processing.py
|
|
vllm/multimodal/profiling.py
|
|
vllm/multimodal/registry.py
|
|
vllm/multimodal/utils.py
|
|
vllm/multimodal/video.py
|
|
vllm/platforms/__init__.py
|
|
vllm/platforms/cpu.py
|
|
vllm/platforms/cuda.py
|
|
vllm/platforms/interface.py
|
|
vllm/platforms/rocm.py
|
|
vllm/platforms/tpu.py
|
|
vllm/platforms/xpu.py
|
|
vllm/plugins/__init__.py
|
|
vllm/plugins/io_processors/__init__.py
|
|
vllm/plugins/io_processors/interface.py
|
|
vllm/plugins/lora_resolvers/__init__.py
|
|
vllm/plugins/lora_resolvers/filesystem_resolver.py
|
|
vllm/profiler/__init__.py
|
|
vllm/profiler/layerwise_profile.py
|
|
vllm/profiler/utils.py
|
|
vllm/profiler/wrapper.py
|
|
vllm/ray/__init__.py
|
|
vllm/ray/lazy_utils.py
|
|
vllm/ray/ray_env.py
|
|
vllm/reasoning/__init__.py
|
|
vllm/reasoning/abs_reasoning_parsers.py
|
|
vllm/reasoning/basic_parsers.py
|
|
vllm/reasoning/deepseek_r1_reasoning_parser.py
|
|
vllm/reasoning/deepseek_v3_reasoning_parser.py
|
|
vllm/reasoning/ernie45_reasoning_parser.py
|
|
vllm/reasoning/glm4_moe_reasoning_parser.py
|
|
vllm/reasoning/gptoss_reasoning_parser.py
|
|
vllm/reasoning/granite_reasoning_parser.py
|
|
vllm/reasoning/holo2_reasoning_parser.py
|
|
vllm/reasoning/hunyuan_a13b_reasoning_parser.py
|
|
vllm/reasoning/identity_reasoning_parser.py
|
|
vllm/reasoning/minimax_m2_reasoning_parser.py
|
|
vllm/reasoning/mistral_reasoning_parser.py
|
|
vllm/reasoning/olmo3_reasoning_parser.py
|
|
vllm/reasoning/qwen3_reasoning_parser.py
|
|
vllm/reasoning/seedoss_reasoning_parser.py
|
|
vllm/reasoning/step3_reasoning_parser.py
|
|
vllm/third_party/__init__.py
|
|
vllm/third_party/pynvml.py
|
|
vllm/tokenizers/__init__.py
|
|
vllm/tokenizers/deepseek_v32.py
|
|
vllm/tokenizers/deepseek_v32_encoding.py
|
|
vllm/tokenizers/detokenizer_utils.py
|
|
vllm/tokenizers/hf.py
|
|
vllm/tokenizers/mistral.py
|
|
vllm/tokenizers/protocol.py
|
|
vllm/tokenizers/registry.py
|
|
vllm/tool_parsers/__init__.py
|
|
vllm/tool_parsers/abstract_tool_parser.py
|
|
vllm/tool_parsers/deepseekv31_tool_parser.py
|
|
vllm/tool_parsers/deepseekv32_tool_parser.py
|
|
vllm/tool_parsers/deepseekv3_tool_parser.py
|
|
vllm/tool_parsers/ernie45_tool_parser.py
|
|
vllm/tool_parsers/gigachat3_tool_parser.py
|
|
vllm/tool_parsers/glm4_moe_tool_parser.py
|
|
vllm/tool_parsers/granite_20b_fc_tool_parser.py
|
|
vllm/tool_parsers/granite_tool_parser.py
|
|
vllm/tool_parsers/hermes_tool_parser.py
|
|
vllm/tool_parsers/hunyuan_a13b_tool_parser.py
|
|
vllm/tool_parsers/internlm2_tool_parser.py
|
|
vllm/tool_parsers/jamba_tool_parser.py
|
|
vllm/tool_parsers/kimi_k2_tool_parser.py
|
|
vllm/tool_parsers/llama4_pythonic_tool_parser.py
|
|
vllm/tool_parsers/llama_tool_parser.py
|
|
vllm/tool_parsers/longcat_tool_parser.py
|
|
vllm/tool_parsers/minimax_m2_tool_parser.py
|
|
vllm/tool_parsers/minimax_tool_parser.py
|
|
vllm/tool_parsers/mistral_tool_parser.py
|
|
vllm/tool_parsers/olmo3_tool_parser.py
|
|
vllm/tool_parsers/openai_tool_parser.py
|
|
vllm/tool_parsers/phi4mini_tool_parser.py
|
|
vllm/tool_parsers/pythonic_tool_parser.py
|
|
vllm/tool_parsers/qwen3coder_tool_parser.py
|
|
vllm/tool_parsers/qwen3xml_tool_parser.py
|
|
vllm/tool_parsers/seed_oss_tool_parser.py
|
|
vllm/tool_parsers/step3_tool_parser.py
|
|
vllm/tool_parsers/utils.py
|
|
vllm/tool_parsers/xlam_tool_parser.py
|
|
vllm/transformers_utils/__init__.py
|
|
vllm/transformers_utils/config.py
|
|
vllm/transformers_utils/config_parser_base.py
|
|
vllm/transformers_utils/dynamic_module.py
|
|
vllm/transformers_utils/gguf_utils.py
|
|
vllm/transformers_utils/processor.py
|
|
vllm/transformers_utils/repo_utils.py
|
|
vllm/transformers_utils/runai_utils.py
|
|
vllm/transformers_utils/s3_utils.py
|
|
vllm/transformers_utils/tokenizer.py
|
|
vllm/transformers_utils/tokenizer_base.py
|
|
vllm/transformers_utils/utils.py
|
|
vllm/transformers_utils/chat_templates/__init__.py
|
|
vllm/transformers_utils/chat_templates/registry.py
|
|
vllm/transformers_utils/chat_templates/template_basic.jinja
|
|
vllm/transformers_utils/chat_templates/template_blip2.jinja
|
|
vllm/transformers_utils/chat_templates/template_chatml.jinja
|
|
vllm/transformers_utils/chat_templates/template_deepseek_ocr.jinja
|
|
vllm/transformers_utils/chat_templates/template_deepseek_vl2.jinja
|
|
vllm/transformers_utils/chat_templates/template_fuyu.jinja
|
|
vllm/transformers_utils/chat_templates/template_minicpmv45.jinja
|
|
vllm/transformers_utils/configs/__init__.py
|
|
vllm/transformers_utils/configs/afmoe.py
|
|
vllm/transformers_utils/configs/arctic.py
|
|
vllm/transformers_utils/configs/bagel.py
|
|
vllm/transformers_utils/configs/chatglm.py
|
|
vllm/transformers_utils/configs/deepseek_vl2.py
|
|
vllm/transformers_utils/configs/dotsocr.py
|
|
vllm/transformers_utils/configs/eagle.py
|
|
vllm/transformers_utils/configs/falcon.py
|
|
vllm/transformers_utils/configs/flex_olmo.py
|
|
vllm/transformers_utils/configs/hunyuan_vl.py
|
|
vllm/transformers_utils/configs/jais.py
|
|
vllm/transformers_utils/configs/kimi_linear.py
|
|
vllm/transformers_utils/configs/kimi_vl.py
|
|
vllm/transformers_utils/configs/lfm2_moe.py
|
|
vllm/transformers_utils/configs/medusa.py
|
|
vllm/transformers_utils/configs/midashenglm.py
|
|
vllm/transformers_utils/configs/mistral.py
|
|
vllm/transformers_utils/configs/mlp_speculator.py
|
|
vllm/transformers_utils/configs/moonvit.py
|
|
vllm/transformers_utils/configs/nemotron.py
|
|
vllm/transformers_utils/configs/nemotron_h.py
|
|
vllm/transformers_utils/configs/olmo3.py
|
|
vllm/transformers_utils/configs/ovis.py
|
|
vllm/transformers_utils/configs/qwen3_next.py
|
|
vllm/transformers_utils/configs/radio.py
|
|
vllm/transformers_utils/configs/step3_vl.py
|
|
vllm/transformers_utils/configs/tarsier2.py
|
|
vllm/transformers_utils/configs/ultravox.py
|
|
vllm/transformers_utils/configs/speculators/__init__.py
|
|
vllm/transformers_utils/configs/speculators/algos.py
|
|
vllm/transformers_utils/configs/speculators/base.py
|
|
vllm/transformers_utils/processors/__init__.py
|
|
vllm/transformers_utils/processors/bagel.py
|
|
vllm/transformers_utils/processors/deepseek_ocr.py
|
|
vllm/transformers_utils/processors/deepseek_vl2.py
|
|
vllm/transformers_utils/processors/hunyuan_vl.py
|
|
vllm/transformers_utils/processors/hunyuan_vl_image.py
|
|
vllm/transformers_utils/processors/ovis.py
|
|
vllm/transformers_utils/processors/ovis2_5.py
|
|
vllm/triton_utils/__init__.py
|
|
vllm/triton_utils/importing.py
|
|
vllm/usage/__init__.py
|
|
vllm/usage/usage_lib.py
|
|
vllm/utils/__init__.py
|
|
vllm/utils/argparse_utils.py
|
|
vllm/utils/async_utils.py
|
|
vllm/utils/cache.py
|
|
vllm/utils/collection_utils.py
|
|
vllm/utils/counter.py
|
|
vllm/utils/deep_gemm.py
|
|
vllm/utils/flashinfer.py
|
|
vllm/utils/func_utils.py
|
|
vllm/utils/gc_utils.py
|
|
vllm/utils/hashing.py
|
|
vllm/utils/import_utils.py
|
|
vllm/utils/jsontree.py
|
|
vllm/utils/math_utils.py
|
|
vllm/utils/mem_constants.py
|
|
vllm/utils/mem_utils.py
|
|
vllm/utils/nccl.py
|
|
vllm/utils/network_utils.py
|
|
vllm/utils/nvtx_pytorch_hooks.py
|
|
vllm/utils/platform_utils.py
|
|
vllm/utils/profiling.py
|
|
vllm/utils/registry.py
|
|
vllm/utils/serial_utils.py
|
|
vllm/utils/system_utils.py
|
|
vllm/utils/tensor_schema.py
|
|
vllm/utils/torch_utils.py
|
|
vllm/v1/__init__.py
|
|
vllm/v1/cudagraph_dispatcher.py
|
|
vllm/v1/kv_cache_interface.py
|
|
vllm/v1/outputs.py
|
|
vllm/v1/request.py
|
|
vllm/v1/serial_utils.py
|
|
vllm/v1/utils.py
|
|
vllm/v1/attention/__init__.py
|
|
vllm/v1/attention/backends/__init__.py
|
|
vllm/v1/attention/backends/cpu_attn.py
|
|
vllm/v1/attention/backends/flash_attn.py
|
|
vllm/v1/attention/backends/flashinfer.py
|
|
vllm/v1/attention/backends/flex_attention.py
|
|
vllm/v1/attention/backends/gdn_attn.py
|
|
vllm/v1/attention/backends/linear_attn.py
|
|
vllm/v1/attention/backends/mamba1_attn.py
|
|
vllm/v1/attention/backends/mamba2_attn.py
|
|
vllm/v1/attention/backends/mamba_attn.py
|
|
vllm/v1/attention/backends/pallas.py
|
|
vllm/v1/attention/backends/rocm_aiter_fa.py
|
|
vllm/v1/attention/backends/rocm_aiter_unified_attn.py
|
|
vllm/v1/attention/backends/rocm_attn.py
|
|
vllm/v1/attention/backends/short_conv_attn.py
|
|
vllm/v1/attention/backends/tree_attn.py
|
|
vllm/v1/attention/backends/triton_attn.py
|
|
vllm/v1/attention/backends/utils.py
|
|
vllm/v1/attention/backends/mla/__init__.py
|
|
vllm/v1/attention/backends/mla/aiter_triton_mla.py
|
|
vllm/v1/attention/backends/mla/common.py
|
|
vllm/v1/attention/backends/mla/cutlass_mla.py
|
|
vllm/v1/attention/backends/mla/flashattn_mla.py
|
|
vllm/v1/attention/backends/mla/flashinfer_mla.py
|
|
vllm/v1/attention/backends/mla/flashmla.py
|
|
vllm/v1/attention/backends/mla/flashmla_sparse.py
|
|
vllm/v1/attention/backends/mla/indexer.py
|
|
vllm/v1/attention/backends/mla/rocm_aiter_mla.py
|
|
vllm/v1/attention/backends/mla/rocm_aiter_mla_sparse.py
|
|
vllm/v1/attention/backends/mla/triton_mla.py
|
|
vllm/v1/core/__init__.py
|
|
vllm/v1/core/block_pool.py
|
|
vllm/v1/core/encoder_cache_manager.py
|
|
vllm/v1/core/kv_cache_coordinator.py
|
|
vllm/v1/core/kv_cache_manager.py
|
|
vllm/v1/core/kv_cache_metrics.py
|
|
vllm/v1/core/kv_cache_utils.py
|
|
vllm/v1/core/single_type_kv_cache_manager.py
|
|
vllm/v1/core/sched/__init__.py
|
|
vllm/v1/core/sched/async_scheduler.py
|
|
vllm/v1/core/sched/interface.py
|
|
vllm/v1/core/sched/output.py
|
|
vllm/v1/core/sched/request_queue.py
|
|
vllm/v1/core/sched/scheduler.py
|
|
vllm/v1/core/sched/utils.py
|
|
vllm/v1/engine/__init__.py
|
|
vllm/v1/engine/async_llm.py
|
|
vllm/v1/engine/coordinator.py
|
|
vllm/v1/engine/core.py
|
|
vllm/v1/engine/core_client.py
|
|
vllm/v1/engine/detokenizer.py
|
|
vllm/v1/engine/exceptions.py
|
|
vllm/v1/engine/input_processor.py
|
|
vllm/v1/engine/llm_engine.py
|
|
vllm/v1/engine/logprobs.py
|
|
vllm/v1/engine/output_processor.py
|
|
vllm/v1/engine/parallel_sampling.py
|
|
vllm/v1/engine/processor.py
|
|
vllm/v1/engine/utils.py
|
|
vllm/v1/executor/__init__.py
|
|
vllm/v1/executor/abstract.py
|
|
vllm/v1/executor/multiproc_executor.py
|
|
vllm/v1/executor/ray_distributed_executor.py
|
|
vllm/v1/executor/ray_executor.py
|
|
vllm/v1/executor/ray_utils.py
|
|
vllm/v1/executor/uniproc_executor.py
|
|
vllm/v1/kv_offload/__init__.py
|
|
vllm/v1/kv_offload/abstract.py
|
|
vllm/v1/kv_offload/arc_manager.py
|
|
vllm/v1/kv_offload/backend.py
|
|
vllm/v1/kv_offload/cpu.py
|
|
vllm/v1/kv_offload/factory.py
|
|
vllm/v1/kv_offload/lru_manager.py
|
|
vllm/v1/kv_offload/mediums.py
|
|
vllm/v1/kv_offload/spec.py
|
|
vllm/v1/kv_offload/backends/__init__.py
|
|
vllm/v1/kv_offload/backends/cpu.py
|
|
vllm/v1/kv_offload/worker/__init__.py
|
|
vllm/v1/kv_offload/worker/cpu_gpu.py
|
|
vllm/v1/kv_offload/worker/worker.py
|
|
vllm/v1/metrics/__init__.py
|
|
vllm/v1/metrics/loggers.py
|
|
vllm/v1/metrics/prometheus.py
|
|
vllm/v1/metrics/ray_wrappers.py
|
|
vllm/v1/metrics/reader.py
|
|
vllm/v1/metrics/stats.py
|
|
vllm/v1/pool/__init__.py
|
|
vllm/v1/pool/metadata.py
|
|
vllm/v1/sample/__init__.py
|
|
vllm/v1/sample/metadata.py
|
|
vllm/v1/sample/rejection_sampler.py
|
|
vllm/v1/sample/sampler.py
|
|
vllm/v1/sample/logits_processor/__init__.py
|
|
vllm/v1/sample/logits_processor/builtin.py
|
|
vllm/v1/sample/logits_processor/interface.py
|
|
vllm/v1/sample/logits_processor/state.py
|
|
vllm/v1/sample/ops/__init__.py
|
|
vllm/v1/sample/ops/bad_words.py
|
|
vllm/v1/sample/ops/logprobs.py
|
|
vllm/v1/sample/ops/penalties.py
|
|
vllm/v1/sample/ops/topk_topp_sampler.py
|
|
vllm/v1/sample/tpu/__init__.py
|
|
vllm/v1/sample/tpu/metadata.py
|
|
vllm/v1/sample/tpu/sampler.py
|
|
vllm/v1/spec_decode/__init__.py
|
|
vllm/v1/spec_decode/eagle.py
|
|
vllm/v1/spec_decode/medusa.py
|
|
vllm/v1/spec_decode/metadata.py
|
|
vllm/v1/spec_decode/metrics.py
|
|
vllm/v1/spec_decode/ngram_proposer.py
|
|
vllm/v1/spec_decode/suffix_decoding.py
|
|
vllm/v1/spec_decode/utils.py
|
|
vllm/v1/structured_output/__init__.py
|
|
vllm/v1/structured_output/backend_guidance.py
|
|
vllm/v1/structured_output/backend_lm_format_enforcer.py
|
|
vllm/v1/structured_output/backend_outlines.py
|
|
vllm/v1/structured_output/backend_types.py
|
|
vllm/v1/structured_output/backend_xgrammar.py
|
|
vllm/v1/structured_output/request.py
|
|
vllm/v1/structured_output/utils.py
|
|
vllm/v1/worker/__init__.py
|
|
vllm/v1/worker/block_table.py
|
|
vllm/v1/worker/cp_utils.py
|
|
vllm/v1/worker/cpu_model_runner.py
|
|
vllm/v1/worker/cpu_worker.py
|
|
vllm/v1/worker/dp_utils.py
|
|
vllm/v1/worker/ec_connector_model_runner_mixin.py
|
|
vllm/v1/worker/gpu_input_batch.py
|
|
vllm/v1/worker/gpu_model_runner.py
|
|
vllm/v1/worker/gpu_ubatch_wrapper.py
|
|
vllm/v1/worker/gpu_worker.py
|
|
vllm/v1/worker/kv_connector_model_runner_mixin.py
|
|
vllm/v1/worker/lora_model_runner_mixin.py
|
|
vllm/v1/worker/tpu_input_batch.py
|
|
vllm/v1/worker/tpu_model_runner.py
|
|
vllm/v1/worker/tpu_worker.py
|
|
vllm/v1/worker/ubatch_utils.py
|
|
vllm/v1/worker/ubatching.py
|
|
vllm/v1/worker/utils.py
|
|
vllm/v1/worker/worker_base.py
|
|
vllm/v1/worker/workspace.py
|
|
vllm/v1/worker/xpu_model_runner.py
|
|
vllm/v1/worker/xpu_worker.py
|
|
vllm/v1/worker/gpu/README.md
|
|
vllm/v1/worker/gpu/__init__.py
|
|
vllm/v1/worker/gpu/async_utils.py
|
|
vllm/v1/worker/gpu/attn_utils.py
|
|
vllm/v1/worker/gpu/block_table.py
|
|
vllm/v1/worker/gpu/cudagraph_utils.py
|
|
vllm/v1/worker/gpu/dp_utils.py
|
|
vllm/v1/worker/gpu/input_batch.py
|
|
vllm/v1/worker/gpu/model_runner.py
|
|
vllm/v1/worker/gpu/states.py
|
|
vllm/v1/worker/gpu/structured_outputs.py
|
|
vllm/v1/worker/gpu/metrics/__init__.py
|
|
vllm/v1/worker/gpu/metrics/logits.py
|
|
vllm/v1/worker/gpu/sample/__init__.py
|
|
vllm/v1/worker/gpu/sample/gumbel.py
|
|
vllm/v1/worker/gpu/sample/logprob.py
|
|
vllm/v1/worker/gpu/sample/metadata.py
|
|
vllm/v1/worker/gpu/sample/min_p.py
|
|
vllm/v1/worker/gpu/sample/output.py
|
|
vllm/v1/worker/gpu/sample/penalties.py
|
|
vllm/v1/worker/gpu/sample/sampler.py
|
|
vllm/v1/worker/gpu/spec_decode/__init__.py
|
|
vllm/v1/worker/gpu/spec_decode/eagle.py
|
|
vllm/v1/worker/gpu/spec_decode/eagle_cudagraph.py
|
|
vllm/v1/worker/gpu/spec_decode/rejection_sample.py
|
|
vllm/vllm_flash_attn/.gitkeep |