.clang-format
.gitignore
.gitmodules
.markdownlint.yaml
.pre-commit-config.yaml
.readthedocs.yaml
AGENTS.md
CLAUDE.md
CMakeLists.txt
CODE_OF_CONDUCT.md
CONTRIBUTING.md
DCO
Dockerfile
Dockerfile.310p
Dockerfile.310p.openEuler
Dockerfile.a3
Dockerfile.a3.openEuler
Dockerfile.a5
Dockerfile.a5.openEuler
Dockerfile.openEuler
LICENSE
README.md
README.zh.md
codecov.yml
collect_env.py
format.sh
mypy.ini
packages.txt
pyproject.toml
requirements-dev.txt
requirements-lint.txt
requirements.txt
setup.py
typos.toml
.agents/README.md
.agents/skills/vllm-ascend-model-adapter/SKILL.md
.agents/skills/vllm-ascend-model-adapter/references/deliverables.md
.agents/skills/vllm-ascend-model-adapter/references/fp8-on-npu-lessons.md
.agents/skills/vllm-ascend-model-adapter/references/multimodal-ep-aclgraph-lessons.md
.agents/skills/vllm-ascend-model-adapter/references/troubleshooting.md
.agents/skills/vllm-ascend-model-adapter/references/workflow-checklist.md
.agents/skills/vllm-ascend-release/SKILL.md
.agents/skills/vllm-ascend-release/references/ref-past-release-notes-highlight.md
.agents/skills/vllm-ascend-release/references/version-files.yaml
.agents/skills/vllm-ascend-release/scripts/fetch_commits.py
.agents/skills/vllm-ascend-release/scripts/generate_announcement.py
.agents/skills/vllm-ascend-release/scripts/generate_checklist.py
.agents/skills/vllm-ascend-release/scripts/scan_nightly_status.py
.agents/skills/vllm-ascend-release/scripts/scan_release_bugs.py
.agents/skills/vllm-ascend-release/scripts/scan_test_coverage.py
.agents/skills/vllm-ascend-release/scripts/update_checklist_section.py
.agents/skills/vllm-ascend-release/scripts/update_version_references.py
.agents/skills/vllm-ascend-release/templates/feedback-issue-template.md
.agents/skills/vllm-ascend-release/templates/release-checklist-template.md
.claude/README.md
.gemini/config.yaml
.gemini/styleguide.md
.github/CODEOWNERS
.github/PULL_REQUEST_TEMPLATE.md
.github/TEST_README.md
.github/actionlint.yaml
.github/dependabot.yml
.github/issue-labeler.yml
.github/labeler.yml
.github/vllm-main-verified.commit
.github/vllm-release-tag.commit
.github/ISSUE_TEMPLATE/100-documentation.yml
.github/ISSUE_TEMPLATE/110-user-story.yml
.github/ISSUE_TEMPLATE/200-installation.yml
.github/ISSUE_TEMPLATE/300-usage.yml
.github/ISSUE_TEMPLATE/400-bug-report.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/800-others.yml
.github/ISSUE_TEMPLATE/900-release-checklist.yml
.github/ISSUE_TEMPLATE/config.yml
.github/actions/read-vllm-release-tag/action.yml
.github/workflows/_e2e_nightly_multi_node.yaml
.github/workflows/_e2e_nightly_single_node.yaml
.github/workflows/_e2e_nightly_single_node_models.yaml
.github/workflows/_nightly_image_build.yaml
.github/workflows/_schedule_image_build.yaml
.github/workflows/_selected_tests.yaml
.github/workflows/bot_issue_manage.yaml
.github/workflows/bot_merge_conflict.yaml
.github/workflows/bot_pr_create.yaml
.github/workflows/labeled_doctest.yaml
.github/workflows/labled_download_model_dataset.yaml
.github/workflows/nightly_image_build.yaml
.github/workflows/pr_cherry_pick_command.yml
.github/workflows/pr_close_cancel_job.yaml
.github/workflows/pr_e2e_command.yml
.github/workflows/pr_nightly_command.yml
.github/workflows/pr_rerun_command.yml
.github/workflows/pr_revert_command.yml
.github/workflows/pr_test.yaml
.github/workflows/push_build_csrc_cache.yaml
.github/workflows/schedule_doc_linkcheck.yaml
.github/workflows/schedule_doc_translate.yaml
.github/workflows/schedule_image_build_and_push.yaml
.github/workflows/schedule_lint_image_build.yaml
.github/workflows/schedule_main2main.yaml
.github/workflows/schedule_nightly_test_a2.yaml
.github/workflows/schedule_nightly_test_a3.yaml
.github/workflows/schedule_nightly_test_a5.yaml
.github/workflows/schedule_release_code_and_wheel.yml
.github/workflows/schedule_stale_manage.yaml
.github/workflows/schedule_update_estimated_times.yaml
.github/workflows/schedule_vllm_e2e_test.yaml
.github/workflows/schedule_weekly_test_a2.yaml
.github/workflows/schedule_weekly_test_a3.yaml
.github/workflows/slash_command_dispatch.yml
.github/workflows/configs/nightly_config.yaml
.github/workflows/configs/weekly_config.yaml
.github/workflows/dockerfiles/Dockerfile.buildwheel.310p
.github/workflows/dockerfiles/Dockerfile.buildwheel.a2
.github/workflows/dockerfiles/Dockerfile.buildwheel.a3
.github/workflows/dockerfiles/Dockerfile.buildwheel.a5
.github/workflows/dockerfiles/Dockerfile.lint
.github/workflows/dockerfiles/Dockerfile.nightly.a2
.github/workflows/dockerfiles/Dockerfile.nightly.a3
.github/workflows/dockerfiles/Dockerfile.nightly.a5
.github/workflows/matchers/actionlint.json
.github/workflows/matchers/markdownlint.json
.github/workflows/matchers/mypy.json
.github/workflows/misc/model_dataset_list.json
.github/workflows/scripts/conftest.py
.github/workflows/scripts/coverage.py
.github/workflows/scripts/main2main_tests.json
.github/workflows/scripts/po_translate.py
.github/workflows/scripts/resolve_nightly_tests.py
.github/workflows/scripts/run_selected_tests.sh
.github/workflows/scripts/run_suite.py
.github/workflows/scripts/runner_label.json
.github/workflows/scripts/select_tests.py
.github/workflows/scripts/test_config.yaml
.github/workflows/scripts/test_select_tests.py
.github/workflows/scripts/update_estimated_times.py
.github/workflows/scripts/upstream_config.yaml
.github/workflows/scripts/wheel/auto_exclude.py
.github/workflows/scripts/wheel/config.json
.github/workflows/scripts/wheel/make_variant.py
.github/workflows/scripts/wheel/pyproject.toml
benchmarks/README.md
benchmarks/requirements-bench.txt
benchmarks/ops/ben_vocabparallelembedding.py
benchmarks/scripts/convert_json_to_markdown.py
benchmarks/scripts/perf_result_template.md
benchmarks/scripts/run-performance-benchmarks.sh
benchmarks/tests/latency-tests.json
benchmarks/tests/serving-tests.json
benchmarks/tests/throughput-tests.json
cmake/utils.cmake
csrc/CMakeLists.txt
csrc/build.sh
csrc/build_aclnn.sh
csrc/build_batch_invariant_ops.sh
csrc/camem_allocator.cpp
csrc/ops.h
csrc/torch_binding.cpp
csrc/torch_binding_meta.cpp
csrc/utils.h
csrc/version.info
csrc/aclnn_torch_adapter/NPUBridge.cpp
csrc/aclnn_torch_adapter/NPUBridge.h
csrc/aclnn_torch_adapter/NPUStorageImpl.cpp
csrc/aclnn_torch_adapter/NPUStorageImpl.h
csrc/aclnn_torch_adapter/op_api_common.h
csrc/attention/CMakeLists.txt
csrc/attention/common/op_kernel/CopyInL1.h
csrc/attention/common/op_kernel/FixpipeOut.h
csrc/attention/common/op_kernel/buffer.h
csrc/attention/common/op_kernel/buffer_manager.h
csrc/attention/common/op_kernel/buffer_mix_core.h
csrc/attention/common/op_kernel/buffers_policy.h
csrc/attention/common/op_kernel/matmul.h
csrc/attention/common/op_kernel/offset_calculator.h
csrc/attention/common/op_kernel/arch35/vf/vf_basic_block_aligned128_no_update_sfa.h
csrc/attention/common/op_kernel/arch35/vf/vf_basic_block_aligned128_update_sfa.h
csrc/attention/common/op_kernel/arch35/vf/vf_basic_block_unaligned128_no_update_sfa.h
csrc/attention/common/op_kernel/arch35/vf/vf_basic_block_unaligned128_update_sfa.h
csrc/attention/common/op_kernel/arch35/vf/vf_basic_block_unaligned64_no_update_sfa.h
csrc/attention/common/op_kernel/arch35/vf/vf_basic_block_unaligned64_update_sfa.h
csrc/attention/common/op_kernel/arch35/vf/vf_basic_block_utils.h
csrc/attention/common/op_kernel/arch35/vf/vf_flashupdate_new.h
csrc/attention/common/op_kernel/arch35/vf/vf_mul_sel_softmaxflashv2_cast_nz_sfa.h
csrc/attention/common/op_kernel/memcopy/fa_gm_tensor.h
csrc/attention/common/op_kernel/memcopy/fa_l1_tensor.h
csrc/attention/common/op_kernel/memcopy/gm_coord.h
csrc/attention/common/op_kernel/memcopy/gm_layout.h
csrc/attention/common/op_kernel/memcopy/offset_calculator_v2.h
csrc/attention/common/op_kernel/memcopy/parser.h
csrc/attention/compressor/CMakeLists.txt
csrc/attention/compressor/README.md
csrc/attention/compressor/op_host/CMakeLists.txt
csrc/attention/compressor/op_host/compressor_def.cpp
csrc/attention/compressor/op_host/compressor_proto.cpp
csrc/attention/compressor/op_host/arch32/compressor_tiling.cpp
csrc/attention/compressor/op_host/arch32/compressor_tiling.h
csrc/attention/compressor/op_host/arch35/compressor_tiling.cpp
csrc/attention/compressor/op_host/arch35/compressor_tiling.h
csrc/attention/compressor/op_kernel/compressor.cpp
csrc/attention/compressor/op_kernel/arch32/compressor_block_cube_perf.h
csrc/attention/compressor/op_kernel/arch32/compressor_block_vec_perf.h
csrc/attention/compressor/op_kernel/arch32/compressor_comm.h
csrc/attention/compressor/op_kernel/arch32/compressor_kernel.h
csrc/attention/compressor/op_kernel/arch32/compressor_kernel_perf.h
csrc/attention/compressor/op_kernel/arch32/compressor_template_tiling_key.h
csrc/attention/compressor/op_kernel/arch32/compressor_tiling_data.h
csrc/attention/compressor/op_kernel/arch32/compressor_tools.h
csrc/attention/compressor/op_kernel/arch32/compressor_vector_comm.h
csrc/attention/compressor/op_kernel/arch32/rms_norm.h
csrc/attention/compressor/op_kernel/arch32/rope.h
csrc/attention/compressor/op_kernel/arch32/soft_max.h
csrc/attention/compressor/op_kernel/arch35/compressor_block_cube.h
csrc/attention/compressor/op_kernel/arch35/compressor_block_cube_full_load.h
csrc/attention/compressor/op_kernel/arch35/compressor_block_vec.h
csrc/attention/compressor/op_kernel/arch35/compressor_block_vec_full_load.h
csrc/attention/compressor/op_kernel/arch35/compressor_comm.h
csrc/attention/compressor/op_kernel/arch35/compressor_kernel.h
csrc/attention/compressor/op_kernel/arch35/compressor_kernel_full_load.h
csrc/attention/compressor/op_kernel/arch35/compressor_template_tiling_key.h
csrc/attention/compressor/op_kernel/arch35/compressor_tiling_data.h
csrc/attention/compressor/op_kernel/arch35/compressor_tools.h
csrc/attention/compressor/op_kernel/arch35/vf/vf_add.h
csrc/attention/compressor/op_kernel/arch35/vf/vf_mul.h
csrc/attention/compressor/op_kernel/arch35/vf/vf_rms_norm.h
csrc/attention/compressor/op_kernel/arch35/vf/vf_rope.h
csrc/attention/compressor/op_kernel/arch35/vf/vf_softmax.h
csrc/attention/compressor_metadata/CMakeLists.txt
csrc/attention/compressor_metadata/op_host/CMakeLists.txt
csrc/attention/compressor_metadata/op_host/compressor_metadata_def.cpp
csrc/attention/compressor_metadata/op_host/compressor_metadata_tiling.cpp
csrc/attention/compressor_metadata/op_host/compressor_metadata_tiling.h
csrc/attention/compressor_metadata/op_kernel/compressor_metadata.cpp
csrc/attention/compressor_metadata/op_kernel/compressor_metadata.h
csrc/attention/fused_gdn_gating/fused_gdn_gating_torch_adpt.h
csrc/attention/fused_gdn_gating/op_host/CMakeLists.txt
csrc/attention/fused_gdn_gating/op_host/fused_gdn_gating_def.cpp
csrc/attention/fused_gdn_gating/op_host/fused_gdn_gating_infershape.cpp
csrc/attention/fused_gdn_gating/op_host/fused_gdn_gating_tiling.cpp
csrc/attention/fused_gdn_gating/op_host/fused_gdn_gating_tiling.h
csrc/attention/fused_gdn_gating/op_host/fused_gdn_gating_tiling_utils.h
csrc/attention/fused_gdn_gating/op_host/op_api/aclnn_fused_gdn_gating.cpp
csrc/attention/fused_gdn_gating/op_host/op_api/aclnn_fused_gdn_gating.h
csrc/attention/fused_gdn_gating/op_host/op_api/fused_gdn_gating.cpp
csrc/attention/fused_gdn_gating/op_host/op_api/fused_gdn_gating.h
csrc/attention/fused_gdn_gating/op_kernel/fused_gdn_gating.cpp
csrc/attention/fused_gdn_gating/op_kernel/fused_gdn_gating.h
csrc/attention/fused_gdn_gating/op_kernel/fused_gdn_gating_tiling_data.h
csrc/attention/indexer_compress_epilog/CMakeLists.txt
csrc/attention/indexer_compress_epilog/op_host/CMakeLists.txt
csrc/attention/indexer_compress_epilog/op_host/indexer_compress_epilog_def.cpp
csrc/attention/indexer_compress_epilog/op_host/indexer_compress_epilog_proto.cpp
csrc/attention/indexer_compress_epilog/op_host/indexer_compress_epilog_tiling.cpp
csrc/attention/indexer_compress_epilog/op_host/indexer_compress_epilog_tiling.h
csrc/attention/indexer_compress_epilog/op_kernel/indexer_compress_epilog.cpp
csrc/attention/indexer_compress_epilog/op_kernel/indexer_compress_epilog_base.h
csrc/attention/indexer_compress_epilog/op_kernel/indexer_compress_epilog_multi_row.h
csrc/attention/indexer_compress_epilog/op_kernel/indexer_compress_epilog_multi_row_mx_fp8.h
csrc/attention/indexer_compress_epilog/op_kernel/indexer_compress_epilog_single_row.h
csrc/attention/indexer_compress_epilog/op_kernel/indexer_compress_epilog_single_row_mx_fp8.h
csrc/attention/indexer_compress_epilog_v2/CMakeLists.txt
csrc/attention/indexer_compress_epilog_v2/op_host/CMakeLists.txt
csrc/attention/indexer_compress_epilog_v2/op_host/indexer_compress_epilog_v2_def.cpp
csrc/attention/indexer_compress_epilog_v2/op_host/indexer_compress_epilog_v2_proto.cpp
csrc/attention/indexer_compress_epilog_v2/op_host/indexer_compress_epilog_v2_tiling.cpp
csrc/attention/indexer_compress_epilog_v2/op_host/indexer_compress_epilog_v2_tiling.h
csrc/attention/indexer_compress_epilog_v2/op_kernel/indexer_compress_epilog_v2.cpp
csrc/attention/indexer_compress_epilog_v2/op_kernel/indexer_compress_epilog_v2_base.h
csrc/attention/indexer_compress_epilog_v2/op_kernel/indexer_compress_epilog_v2_multi_row.h
csrc/attention/indexer_compress_epilog_v2/op_kernel/indexer_compress_epilog_v2_single_row.h
csrc/attention/inplace_partial_rotary_mul/CMakeLists.txt
csrc/attention/inplace_partial_rotary_mul/op_host/CMakeLists.txt
csrc/attention/inplace_partial_rotary_mul/op_host/inplace_partial_rotary_mul_a3_tiling.cpp
csrc/attention/inplace_partial_rotary_mul/op_host/inplace_partial_rotary_mul_def.cpp
csrc/attention/inplace_partial_rotary_mul/op_host/inplace_partial_rotary_mul_proto.cpp
csrc/attention/inplace_partial_rotary_mul/op_host/inplace_partial_rotary_mul_tiling.cpp
csrc/attention/inplace_partial_rotary_mul/op_host/inplace_partial_rotary_mul_tiling.h
csrc/attention/inplace_partial_rotary_mul/op_host/rope_regbase_tiling_a_and_b.cpp
csrc/attention/inplace_partial_rotary_mul/op_host/rope_regbase_tiling_ab.cpp
csrc/attention/inplace_partial_rotary_mul/op_host/rope_regbase_tiling_aba_and_ba.cpp
csrc/attention/inplace_partial_rotary_mul/op_host/rope_regbase_tiling_bab.cpp
csrc/attention/inplace_partial_rotary_mul/op_host/rope_regbase_tiling_base.cpp
csrc/attention/inplace_partial_rotary_mul/op_kernel/apply_rotary_pos_emb_common.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/inplace_partial_rotary_mul.cpp
csrc/attention/inplace_partial_rotary_mul/op_kernel/inplace_partial_rotary_mul.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/inplace_partial_rotary_mul_common.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotary_position_embedding_reg_a_and_b.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotary_position_embedding_reg_a_and_b_mixed.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotary_position_embedding_reg_ab.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotary_position_embedding_reg_ab_mixed.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotary_position_embedding_reg_aba_and_ba.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotary_position_embedding_reg_aba_and_ba_mixed.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotary_position_embedding_reg_bab.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotary_position_embedding_reg_bab_mixed.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotate_half.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotate_half_base.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotate_half_bf16.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotate_interleaved_common.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotate_interleaved_split_bs.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotate_interleaved_split_bs_pad.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotate_interleaved_split_bsn.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotate_interleaved_split_bsn_pad.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotate_interleaved_split_s.h
csrc/attention/inplace_partial_rotary_mul/op_kernel/rotate_interleaved_split_s_pad.h
csrc/attention/kv_compress_epilog/CMakeLists.txt
csrc/attention/kv_compress_epilog/op_host/CMakeLists.txt
csrc/attention/kv_compress_epilog/op_host/kv_compress_epilog_def.cpp
csrc/attention/kv_compress_epilog/op_host/kv_compress_epilog_tiling_arch35.cpp
csrc/attention/kv_compress_epilog/op_host/kv_compress_epilog_tiling_arch35.h
csrc/attention/kv_compress_epilog/op_kernel/kv_compress_epilog.cpp
csrc/attention/kv_compress_epilog/op_kernel/kv_compress_epilog.h
csrc/attention/kv_compress_epilog/op_kernel/kv_compress_epilog_common.h
csrc/attention/kv_quant_sparse_attn_sharedkv/CMakeLists.txt
csrc/attention/kv_quant_sparse_attn_sharedkv/README.md
csrc/attention/kv_quant_sparse_attn_sharedkv/op_host/CMakeLists.txt
csrc/attention/kv_quant_sparse_attn_sharedkv/op_host/kv_quant_sparse_attn_sharedkv_check.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv/op_host/kv_quant_sparse_attn_sharedkv_check.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_host/kv_quant_sparse_attn_sharedkv_check_consistancy.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv/op_host/kv_quant_sparse_attn_sharedkv_check_existance.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv/op_host/kv_quant_sparse_attn_sharedkv_check_feature.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv/op_host/kv_quant_sparse_attn_sharedkv_check_single_para.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv/op_host/kv_quant_sparse_attn_sharedkv_def.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv/op_host/kv_quant_sparse_attn_sharedkv_proto.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv/op_host/kv_quant_sparse_attn_sharedkv_tiling.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv/op_host/kv_quant_sparse_attn_sharedkv_tiling.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/kv_quant_sparse_attn_sharedkv.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/kv_quant_sparse_attn_sharedkv_common.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/kv_quant_sparse_attn_sharedkv_metadata.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/kv_quant_sparse_attn_sharedkv_template_tiling_key.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/kv_quant_sparse_attn_sharedkv_common_arch35.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/kv_quant_sparse_attn_sharedkv_kvcache.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/kv_quant_sparse_attn_sharedkv_scfa_block_cube.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/kv_quant_sparse_attn_sharedkv_scfa_block_vector.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/kv_quant_sparse_attn_sharedkv_scfa_kernel.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/util_regbase.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/common/CopyInL1.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/common/FixpipeOut.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/common/buffer.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/common/buffer_manager.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/common/buffers_policy.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/common/matmul.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/common/offset_calculator.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/vf/vf_basic_block_aligned128_no_update_scfa.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/vf/vf_basic_block_aligned128_update_scfa.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/vf/vf_basic_block_unaligned128_no_update_scfa.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/vf/vf_basic_block_unaligned128_update_scfa.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/vf/vf_basic_block_unaligned64_no_update_scfa.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/vf/vf_basic_block_unaligned64_update_scfa.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/vf/vf_basic_block_utils.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/vf/vf_flashupdate_new_scfa.h
csrc/attention/kv_quant_sparse_attn_sharedkv/op_kernel/arch35/vf/vf_mul_sel_softmaxflashv2_cast_nz_scfa.h
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/CMakeLists.txt
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/README.md
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/op_graph/kv_quant_sparse_attn_sharedkv_metadata_proto.h
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/op_host/CMakeLists.txt
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/op_host/kv_quant_sparse_attn_sharedkv_metadata_infershape.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/op_host/op_api/aclnn_kv_quant_sparse_attn_sharedkv_metadata.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/op_host/op_api/aclnn_kv_quant_sparse_attn_sharedkv_metadata.h
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/op_host/op_api/l0_kv_quant_sparse_attn_sharedkv_metadata.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/op_host/op_api/l0_kv_quant_sparse_attn_sharedkv_metadata.h
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/op_kernel_aicpu/CMakeLists.txt
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/op_kernel_aicpu/kv_quant_sparse_attn_sharedkv_metadata_aicpu.cpp
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/op_kernel_aicpu/kv_quant_sparse_attn_sharedkv_metadata_aicpu.h
csrc/attention/kv_quant_sparse_attn_sharedkv_metadata/op_kernel_aicpu/kv_quant_sparse_attn_sharedkv_metadata_aicpu.json
csrc/attention/kv_quant_sparse_flash_attention/CMakeLists.txt
csrc/attention/kv_quant_sparse_flash_attention/README.md
csrc/attention/kv_quant_sparse_flash_attention/kv_quant_sparse_flash_attention_torch_adpt.h
csrc/attention/kv_quant_sparse_flash_attention/op_host/CMakeLists.txt
csrc/attention/kv_quant_sparse_flash_attention/op_host/kv_quant_sparse_flash_attention_def.cpp
csrc/attention/kv_quant_sparse_flash_attention/op_host/kv_quant_sparse_flash_attention_infershape.cpp
csrc/attention/kv_quant_sparse_flash_attention/op_host/kv_quant_sparse_flash_attention_tiling.cpp
csrc/attention/kv_quant_sparse_flash_attention/op_host/kv_quant_sparse_flash_attention_tiling.h
csrc/attention/kv_quant_sparse_flash_attention/op_kernel/kv_quant_sparse_flash_attention.cpp
csrc/attention/kv_quant_sparse_flash_attention/op_kernel/kv_quant_sparse_flash_attention_common.h
csrc/attention/kv_quant_sparse_flash_attention/op_kernel/kv_quant_sparse_flash_attention_kernel_mla.h
csrc/attention/kv_quant_sparse_flash_attention/op_kernel/kv_quant_sparse_flash_attention_service_cube_mla.h
csrc/attention/kv_quant_sparse_flash_attention/op_kernel/kv_quant_sparse_flash_attention_service_vector_mla.h
csrc/attention/kv_quant_sparse_flash_attention/op_kernel/kv_quant_sparse_flash_attention_template_tiling_key.h
csrc/attention/kv_quant_sparse_flash_attention/op_kernel/arch35/kv_quant_sparse_flash_attention_common_arch35.h
csrc/attention/kv_quant_sparse_flash_attention/op_kernel/arch35/kv_quant_sparse_flash_attention_kernel_mla.h
csrc/attention/kv_quant_sparse_flash_attention/op_kernel/arch35/kv_quant_sparse_flash_attention_kvcache.h
csrc/attention/kv_quant_sparse_flash_attention/op_kernel/arch35/kv_quant_sparse_flash_attention_service_cube_mla.h
csrc/attention/kv_quant_sparse_flash_attention/op_kernel/arch35/kv_quant_sparse_flash_attention_service_vector_mla.h
csrc/attention/lightning_indexer/CMakeLists.txt
csrc/attention/lightning_indexer/README.md
csrc/attention/lightning_indexer/lightning_indexer_torch_adpt.h
csrc/attention/lightning_indexer/docs/aclnnLightningIndexer.md
csrc/attention/lightning_indexer/op_host/CMakeLists.txt
csrc/attention/lightning_indexer/op_host/lightning_indexer_def.cpp
csrc/attention/lightning_indexer/op_host/lightning_indexer_infershape.cpp
csrc/attention/lightning_indexer/op_host/lightning_indexer_tiling.cpp
csrc/attention/lightning_indexer/op_host/lightning_indexer_tiling.h
csrc/attention/lightning_indexer/op_host/op_api/aclnn_lightning_indexer.cpp
csrc/attention/lightning_indexer/op_host/op_api/aclnn_lightning_indexer.h
csrc/attention/lightning_indexer/op_kernel/lightning_indexer.cpp
csrc/attention/lightning_indexer/op_kernel/lightning_indexer_common.h
csrc/attention/lightning_indexer/op_kernel/lightning_indexer_template_tiling_key.h
csrc/attention/lightning_indexer/op_kernel/arch22/lightning_indexer_kernel.h
csrc/attention/lightning_indexer/op_kernel/arch22/lightning_indexer_service_cube.h
csrc/attention/lightning_indexer/op_kernel/arch22/lightning_indexer_service_vector.h
csrc/attention/lightning_indexer/op_kernel/arch22/lightning_indexer_vector.h
csrc/attention/lightning_indexer/op_kernel/arch35/lightning_indexer_kernel.h
csrc/attention/lightning_indexer/op_kernel/arch35/lightning_indexer_service_cube.h
csrc/attention/lightning_indexer/op_kernel/arch35/lightning_indexer_service_vector.h
csrc/attention/lightning_indexer/op_kernel/arch35/vf/lightning_indexer_topk.h
csrc/attention/lightning_indexer/op_kernel/arch35/vf/lightning_indexer_vector1.h
csrc/attention/lightning_indexer/op_kernel/arch35/vf/vf_topk.h
csrc/attention/lightning_indexer/op_kernel/arch35/vf/vf_topk_16_gather.h
csrc/attention/lightning_indexer_quant/CMakeLists.txt
csrc/attention/lightning_indexer_quant/lightning_indexer_quant_torch_adpt.h
csrc/attention/lightning_indexer_quant/op_host/CMakeLists.txt
csrc/attention/lightning_indexer_quant/op_host/lightning_indexer_quant_def.cpp
csrc/attention/lightning_indexer_quant/op_host/lightning_indexer_quant_proto.cpp
csrc/attention/lightning_indexer_quant/op_host/lightning_indexer_quant_tiling.cpp
csrc/attention/lightning_indexer_quant/op_host/lightning_indexer_quant_tiling.h
csrc/attention/lightning_indexer_quant/op_kernel/lightning_indexer_quant.cpp
csrc/attention/lightning_indexer_quant/op_kernel/lightning_indexer_quant_common.h
csrc/attention/lightning_indexer_quant/op_kernel/lightning_indexer_quant_kernel.h
csrc/attention/lightning_indexer_quant/op_kernel/lightning_indexer_quant_service_cube.h
csrc/attention/lightning_indexer_quant/op_kernel/lightning_indexer_quant_service_vector.h
csrc/attention/lightning_indexer_quant/op_kernel/lightning_indexer_quant_template_tiling_key.h
csrc/attention/lightning_indexer_quant/op_kernel/lightning_indexer_quant_vector.h
csrc/attention/lightning_indexer_vllm/CMakeLists.txt
csrc/attention/lightning_indexer_vllm/lightning_indexer_vllm_torch_adpt.h
csrc/attention/lightning_indexer_vllm/op_host/CMakeLists.txt
csrc/attention/lightning_indexer_vllm/op_host/lightning_indexer_vllm_def.cpp
csrc/attention/lightning_indexer_vllm/op_host/lightning_indexer_vllm_proto.cpp
csrc/attention/lightning_indexer_vllm/op_host/lightning_indexer_vllm_tiling.cpp
csrc/attention/lightning_indexer_vllm/op_host/lightning_indexer_vllm_tiling.h
csrc/attention/lightning_indexer_vllm/op_kernel/lightning_indexer_common.h
csrc/attention/lightning_indexer_vllm/op_kernel/lightning_indexer_kernel.h
csrc/attention/lightning_indexer_vllm/op_kernel/lightning_indexer_service_cube.h
csrc/attention/lightning_indexer_vllm/op_kernel/lightning_indexer_service_vector.h
csrc/attention/lightning_indexer_vllm/op_kernel/lightning_indexer_template_tiling_key.h
csrc/attention/lightning_indexer_vllm/op_kernel/lightning_indexer_vector.h
csrc/attention/lightning_indexer_vllm/op_kernel/lightning_indexer_vllm.cpp
csrc/attention/load_index_kv_cache/CMakeLists.txt
csrc/attention/load_index_kv_cache/op_host/CMakeLists.txt
csrc/attention/load_index_kv_cache/op_host/load_index_kv_cache_def.cpp
csrc/attention/load_index_kv_cache/op_host/load_index_kv_cache_proto.cpp
csrc/attention/load_index_kv_cache/op_host/load_index_kv_cache_tiling.cpp
csrc/attention/load_index_kv_cache/op_host/load_index_kv_cache_tiling.h
csrc/attention/load_index_kv_cache/op_kernel/load_index_kv_cache.cpp
csrc/attention/load_index_kv_cache/op_kernel/load_index_kv_cache_base.h
csrc/attention/load_index_kv_cache/op_kernel/load_index_kv_cache_perf.h
csrc/attention/ngram_spec_decode/CMakeLists.txt
csrc/attention/ngram_spec_decode/ngram_spec_decode_torch_adpt.h
csrc/attention/ngram_spec_decode/op_host/CMakeLists.txt
csrc/attention/ngram_spec_decode/op_host/ngram_spec_decode_def.cpp
csrc/attention/ngram_spec_decode/op_host/ngram_spec_decode_tiling.cpp
csrc/attention/ngram_spec_decode/op_host/ngram_spec_decode_tiling.h
csrc/attention/ngram_spec_decode/op_host/op_api/aclnn_ngram_spec_decode.cpp
csrc/attention/ngram_spec_decode/op_host/op_api/aclnn_ngram_spec_decode.h
csrc/attention/ngram_spec_decode/op_kernel/ngram_spec_decode.cpp
csrc/attention/ngram_spec_decode/op_kernel/ngram_spec_decode.h
csrc/attention/recurrent_gated_delta_rule/CMakeLists.txt
csrc/attention/recurrent_gated_delta_rule/recurrent_gated_delta_rule_torch_adpt.h
csrc/attention/recurrent_gated_delta_rule/op_host/CMakeLists.txt
csrc/attention/recurrent_gated_delta_rule/op_host/math_util.h
csrc/attention/recurrent_gated_delta_rule/op_host/recurrent_gated_delta_rule.h
csrc/attention/recurrent_gated_delta_rule/op_host/recurrent_gated_delta_rule_def.cpp
csrc/attention/recurrent_gated_delta_rule/op_host/recurrent_gated_delta_rule_infershape.cpp
csrc/attention/recurrent_gated_delta_rule/op_host/recurrent_gated_delta_rule_tiling.cpp
csrc/attention/recurrent_gated_delta_rule/op_host/recurrent_gated_delta_rule_tiling.h
csrc/attention/recurrent_gated_delta_rule/op_host/arch35/recurrent_gated_delta_rule_tiling_arch35.cpp
csrc/attention/recurrent_gated_delta_rule/op_host/op_api/aclnn_recurrent_gated_delta_rule.cpp
csrc/attention/recurrent_gated_delta_rule/op_host/op_api/aclnn_recurrent_gated_delta_rule.h
csrc/attention/recurrent_gated_delta_rule/op_host/op_api/recurrent_gated_delta_rule.cpp
csrc/attention/recurrent_gated_delta_rule/op_kernel/recurrent_gated_delta_rule.cpp
csrc/attention/recurrent_gated_delta_rule/op_kernel/recurrent_gated_delta_rule.h
csrc/attention/recurrent_gated_delta_rule/op_kernel/recurrent_gated_delta_rule_tiling_data.h
csrc/attention/recurrent_gated_delta_rule/op_kernel/arch35/recurrent_gated_delta_rule.h
csrc/attention/recurrent_gated_delta_rule_v310/CMakeLists.txt
csrc/attention/recurrent_gated_delta_rule_v310/recurrent_gated_delta_rule_310_torch_adpt.h
csrc/attention/recurrent_gated_delta_rule_v310/op_host/CMakeLists.txt
csrc/attention/recurrent_gated_delta_rule_v310/op_host/math_util.h
csrc/attention/recurrent_gated_delta_rule_v310/op_host/recurrent_gated_delta_rule_v310.h
csrc/attention/recurrent_gated_delta_rule_v310/op_host/recurrent_gated_delta_rule_v310_def.cpp
csrc/attention/recurrent_gated_delta_rule_v310/op_host/recurrent_gated_delta_rule_v310_infershape.cpp
csrc/attention/recurrent_gated_delta_rule_v310/op_host/recurrent_gated_delta_rule_v310_tiling.cpp
csrc/attention/recurrent_gated_delta_rule_v310/op_host/recurrent_gated_delta_rule_v310_tiling.h
csrc/attention/recurrent_gated_delta_rule_v310/op_host/op_api/aclnn_recurrent_gated_delta_rule_v310.cpp
csrc/attention/recurrent_gated_delta_rule_v310/op_host/op_api/aclnn_recurrent_gated_delta_rule_v310.h
csrc/attention/recurrent_gated_delta_rule_v310/op_host/op_api/recurrent_gated_delta_rule_v310.cpp
csrc/attention/recurrent_gated_delta_rule_v310/op_kernel/recurrent_gated_delta_rule_v310.cpp
csrc/attention/recurrent_gated_delta_rule_v310/op_kernel/recurrent_gated_delta_rule_v310.h
csrc/attention/recurrent_gated_delta_rule_v310/op_kernel/recurrent_gated_delta_rule_v310_tiling_data.h
csrc/attention/reshape_and_cache_bnsd/CMakeLists.txt
csrc/attention/reshape_and_cache_bnsd/op_host/CMakeLists.txt
csrc/attention/reshape_and_cache_bnsd/op_host/reshape_and_cache_bnsd.cpp
csrc/attention/reshape_and_cache_bnsd/op_host/reshape_and_cache_bnsd_proto.cpp
csrc/attention/reshape_and_cache_bnsd/op_host/reshape_and_cache_bnsd_tiling.cpp
csrc/attention/reshape_and_cache_bnsd/op_host/reshape_and_cache_bnsd_tiling.h
csrc/attention/reshape_and_cache_bnsd/op_kernel/kernel_utils.h
csrc/attention/reshape_and_cache_bnsd/op_kernel/reshape_and_cache_bnsd.cpp
csrc/attention/rms_norm_dynamic_quant/CMakeLists.txt
csrc/attention/rms_norm_dynamic_quant/op_host/CMakeLists.txt
csrc/attention/rms_norm_dynamic_quant/op_host/rms_norm_dynamic_quant_def.cpp
csrc/attention/rms_norm_dynamic_quant/op_host/rms_norm_dynamic_quant_proto.cpp
csrc/attention/rms_norm_dynamic_quant/op_host/rms_norm_dynamic_quant_tiling.cpp
csrc/attention/rms_norm_dynamic_quant/op_host/rms_norm_dynamic_quant_tiling.h
csrc/attention/rms_norm_dynamic_quant/op_kernel/reduce_common.h
csrc/attention/rms_norm_dynamic_quant/op_kernel/rms_norm_dynamic_quant.cpp
csrc/attention/rms_norm_dynamic_quant/op_kernel/rms_norm_dynamic_quant_base.h
csrc/attention/rms_norm_dynamic_quant/op_kernel/rms_norm_dynamic_quant_cut_d_kernel.h
csrc/attention/rms_norm_dynamic_quant/op_kernel/rms_norm_dynamic_quant_helper.h
csrc/attention/rms_norm_dynamic_quant/op_kernel/rms_norm_dynamic_quant_normal_kernel.h
csrc/attention/rms_norm_dynamic_quant/op_kernel/rms_norm_dynamic_quant_single_row_kernel.h
csrc/attention/sparse_attn_sharedkv/CMakeLists.txt
csrc/attention/sparse_attn_sharedkv/README.md
csrc/attention/sparse_attn_sharedkv/op_host/CMakeLists.txt
csrc/attention/sparse_attn_sharedkv/op_host/sparse_attn_sharedkv_def.cpp
csrc/attention/sparse_attn_sharedkv/op_host/sparse_attn_sharedkv_proto.cpp
csrc/attention/sparse_attn_sharedkv/op_host/sparse_attn_sharedkv_tiling.cpp
csrc/attention/sparse_attn_sharedkv/op_host/sparse_attn_sharedkv_tiling.h
csrc/attention/sparse_attn_sharedkv/op_kernel/sparse_attn_sharedkv.cpp
csrc/attention/sparse_attn_sharedkv/op_kernel/sparse_attn_sharedkv_common.h
csrc/attention/sparse_attn_sharedkv/op_kernel/sparse_attn_sharedkv_metadata.h
csrc/attention/sparse_attn_sharedkv/op_kernel/sparse_attn_sharedkv_template_tiling_key.h
csrc/attention/sparse_attn_sharedkv/op_kernel/arch32/sparse_attn_sharedkv_scfa_block_cube.h
csrc/attention/sparse_attn_sharedkv/op_kernel/arch32/sparse_attn_sharedkv_scfa_block_vector.h
csrc/attention/sparse_attn_sharedkv/op_kernel/arch32/sparse_attn_sharedkv_scfa_kernel.h
csrc/attention/sparse_attn_sharedkv/op_kernel/arch32/sparse_attn_sharedkv_swa_block_cube.h
csrc/attention/sparse_attn_sharedkv/op_kernel/arch32/sparse_attn_sharedkv_swa_block_vector.h
csrc/attention/sparse_attn_sharedkv/op_kernel/arch32/sparse_attn_sharedkv_swa_kernel.h
csrc/attention/sparse_attn_sharedkv_metadata/CMakeLists.txt
csrc/attention/sparse_attn_sharedkv_metadata/README.md
csrc/attention/sparse_attn_sharedkv_metadata/op_api/aclnn_sparse_attn_sharedkv_metadata.cpp
csrc/attention/sparse_attn_sharedkv_metadata/op_api/aclnn_sparse_attn_sharedkv_metadata.h
csrc/attention/sparse_attn_sharedkv_metadata/op_api/l0_sparse_attn_sharedkv_metadata.cpp
csrc/attention/sparse_attn_sharedkv_metadata/op_api/l0_sparse_attn_sharedkv_metadata.h
csrc/attention/sparse_attn_sharedkv_metadata/op_graph/sparse_attn_sharedkv_metadata_proto.h
csrc/attention/sparse_attn_sharedkv_metadata/op_host/sparse_attn_sharedkv_metadata_infershape.cpp
csrc/attention/sparse_attn_sharedkv_metadata/op_kernel_aicpu/sparse_attn_sharedkv_metadata_aicpu.cpp
csrc/attention/sparse_attn_sharedkv_metadata/op_kernel_aicpu/sparse_attn_sharedkv_metadata_aicpu.h
csrc/attention/sparse_attn_sharedkv_metadata/op_kernel_aicpu/sparse_attn_sharedkv_metadata_aicpu.json
csrc/attention/sparse_flash_attention/CMakeLists.txt
csrc/attention/sparse_flash_attention/README.md
csrc/attention/sparse_flash_attention/sparse_flash_attention_torch_adpt.h
csrc/attention/sparse_flash_attention/docs/aclnnSparseFlashAttention.md
csrc/attention/sparse_flash_attention/examples/test_aclnn_sparse_flash_attention.cpp
csrc/attention/sparse_flash_attention/op_host/CMakeLists.txt
csrc/attention/sparse_flash_attention/op_host/sparse_flash_attention_def.cpp
csrc/attention/sparse_flash_attention/op_host/sparse_flash_attention_infershape.cpp
csrc/attention/sparse_flash_attention/op_host/sparse_flash_attention_tiling.cpp
csrc/attention/sparse_flash_attention/op_host/sparse_flash_attention_tiling.h
csrc/attention/sparse_flash_attention/op_host/op_api/aclnn_sparse_flash_attention.cpp
csrc/attention/sparse_flash_attention/op_host/op_api/aclnn_sparse_flash_attention.h
csrc/attention/sparse_flash_attention/op_kernel/sparse_flash_attention.cpp
csrc/attention/sparse_flash_attention/op_kernel/sparse_flash_attention_common.h
csrc/attention/sparse_flash_attention/op_kernel/sparse_flash_attention_template_tiling_key.h
csrc/attention/sparse_flash_attention/op_kernel/arch22/sparse_flash_attention_kernel_mla.h
csrc/attention/sparse_flash_attention/op_kernel/arch22/sparse_flash_attention_service_cube_mla.h
csrc/attention/sparse_flash_attention/op_kernel/arch22/sparse_flash_attention_service_vector_mla.h
csrc/attention/sparse_flash_attention/op_kernel/arch35/sparse_flash_attention_common_arch35.h
csrc/attention/sparse_flash_attention/op_kernel/arch35/sparse_flash_attention_kernel_mla.h
csrc/attention/sparse_flash_attention/op_kernel/arch35/sparse_flash_attention_kvcache.h
csrc/attention/sparse_flash_attention/op_kernel/arch35/sparse_flash_attention_service_cube_mla.h
csrc/attention/sparse_flash_attention/op_kernel/arch35/sparse_flash_attention_service_vector_mla.h
csrc/attention/sparse_flash_attention/op_kernel/arch35/util_regbase.h
csrc/attention/store_kv_block/CMakeLists.txt
csrc/attention/store_kv_block/store_kv_block_torch_adpt.h
csrc/attention/store_kv_block/op_host/CMakeLists.txt
csrc/attention/store_kv_block/op_host/store_kv_block_def.cpp
csrc/attention/store_kv_block/op_host/store_kv_block_infershape.cpp
csrc/attention/store_kv_block/op_host/store_kv_block_tiling.cpp
csrc/attention/store_kv_block/op_host/store_kv_block_tiling.h
csrc/attention/store_kv_block/op_kernel/store_kv_block.cpp
csrc/attention/store_kv_block/op_kernel/store_kv_block.h
csrc/attention/store_kv_block_metadata/CMakeLists.txt
csrc/attention/store_kv_block_metadata/store_kv_block_metadata_torch_adpt.cpp
csrc/attention/store_kv_block_metadata/op_api/aclnn_store_kv_block_metadata.cpp
csrc/attention/store_kv_block_metadata/op_api/aclnn_store_kv_block_metadata.h
csrc/attention/store_kv_block_metadata/op_api/l0_store_kv_block_metadata.cpp
csrc/attention/store_kv_block_metadata/op_api/l0_store_kv_block_metadata.h
csrc/attention/store_kv_block_metadata/op_graph/store_kv_block_metadata_proto.h
csrc/attention/store_kv_block_metadata/op_host/store_kv_block_metadata_infershape.cpp
csrc/attention/store_kv_block_metadata/op_kernel_aicpu/store_kv_block_metadata_aicpu.cpp
csrc/attention/store_kv_block_metadata/op_kernel_aicpu/store_kv_block_metadata_aicpu.h
csrc/attention/store_kv_block_metadata/op_kernel_aicpu/store_kv_block_metadata_aicpu.json
csrc/attention/vllm_quant_lightning_indexer/CMakeLists.txt
csrc/attention/vllm_quant_lightning_indexer/README.md
csrc/attention/vllm_quant_lightning_indexer/op_host/CMakeLists.txt
csrc/attention/vllm_quant_lightning_indexer/op_host/vllm_quant_lightning_indexer_def.cpp
csrc/attention/vllm_quant_lightning_indexer/op_host/vllm_quant_lightning_indexer_infershape.cpp
csrc/attention/vllm_quant_lightning_indexer/op_host/vllm_quant_lightning_indexer_tiling.cpp
csrc/attention/vllm_quant_lightning_indexer/op_host/vllm_quant_lightning_indexer_tiling.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/vllm_quant_lightning_indexer.cpp
csrc/attention/vllm_quant_lightning_indexer/op_kernel/vllm_quant_lightning_indexer_metadata.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/vllm_quant_lightning_indexer_template_tiling_key.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch32/quant_lightning_indexer_common.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch32/quant_lightning_indexer_kernel.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch32/quant_lightning_indexer_service_cube.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch32/quant_lightning_indexer_service_vector.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch32/quant_lightning_indexer_vector.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch35/quant_lightning_indexer_common.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch35/quant_lightning_indexer_kernel.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch35/quant_lightning_indexer_service_cube.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch35/quant_lightning_indexer_service_vector.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch35/vf/quant_lightning_indexer_topk.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch35/vf/quant_lightning_indexer_vector1.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch35/vf/vf_topk.h
csrc/attention/vllm_quant_lightning_indexer/op_kernel/arch35/vf/vf_topk_16_gather.h
csrc/attention/vllm_quant_lightning_indexer_metadata/CMakeLists.txt
csrc/attention/vllm_quant_lightning_indexer_metadata/README.md
csrc/attention/vllm_quant_lightning_indexer_metadata/op_api/aclnn_vllm_quant_lightning_indexer_metadata.cpp
csrc/attention/vllm_quant_lightning_indexer_metadata/op_api/aclnn_vllm_quant_lightning_indexer_metadata.h
csrc/attention/vllm_quant_lightning_indexer_metadata/op_api/l0_vllm_quant_lightning_indexer_metadata.cpp
csrc/attention/vllm_quant_lightning_indexer_metadata/op_api/l0_vllm_quant_lightning_indexer_metadata.h
csrc/attention/vllm_quant_lightning_indexer_metadata/op_graph/vllm_quant_lightning_indexer_metadata_proto.h
csrc/attention/vllm_quant_lightning_indexer_metadata/op_host/vllm_quant_lightning_indexer_metadata_infershape.cpp
csrc/attention/vllm_quant_lightning_indexer_metadata/op_kernel_aicpu/vllm_quant_lightning_indexer_metadata_aicpu.cpp
csrc/attention/vllm_quant_lightning_indexer_metadata/op_kernel_aicpu/vllm_quant_lightning_indexer_metadata_aicpu.h
csrc/attention/vllm_quant_lightning_indexer_metadata/op_kernel_aicpu/vllm_quant_lightning_indexer_metadata_aicpu.json
csrc/batch_matmul_transpose/batch_matmul_transpose_torch_adpt.h
csrc/batch_matmul_transpose/op_host/batch_matmul_transpose.h
csrc/batch_matmul_transpose/op_host/common.h
csrc/batch_matmul_transpose/op_host/common_tiling.h
csrc/batch_matmul_transpose/op_host/tiling/tiling_data.cpp
csrc/batch_matmul_transpose/op_host/tiling/tiling_data.h
csrc/batch_matmul_transpose/op_kernel/batch_matmul_transpose_kernel.cpp
csrc/cmake/Third_Party_Open_Source_Software_List.yaml
csrc/cmake/aclnn_ops_transformer.h.in
csrc/cmake/build_empty_package.cmake
csrc/cmake/config.cmake
csrc/cmake/config_utest.cmake
csrc/cmake/custom_build.cmake
csrc/cmake/dependencies.cmake
csrc/cmake/func.cmake
csrc/cmake/func_examples.cmake
csrc/cmake/func_utest.cmake
csrc/cmake/gen_ops_info.cmake
csrc/cmake/intf.cmake
csrc/cmake/intf_pub.cmake
csrc/cmake/intf_pub_examples.cmake
csrc/cmake/intf_pub_linux.cmake
csrc/cmake/intf_pub_llt_gccnative.cmake
csrc/cmake/intf_pub_utest.cmake
csrc/cmake/makeself_built_in.cmake
csrc/cmake/makeself_custom.cmake
csrc/cmake/obj_func.cmake
csrc/cmake/opbuild.cmake
csrc/cmake/package.cmake
csrc/cmake/rty_obj_func.cmake
csrc/cmake/runtimeKB.cmake
csrc/cmake/static.cmake
csrc/cmake/symbol.cmake
csrc/cmake/ut.cmake
csrc/cmake/variables.cmake
csrc/cmake/modules/FindOPBASE.cmake
csrc/cmake/modules/FindPython.cmake
csrc/cmake/modules/Findaicpu.cmake
csrc/cmake/modules/Findalog.cmake
csrc/cmake/modules/Finddlog.cmake
csrc/cmake/modules/Findjson.cmake
csrc/cmake/modules/Findmetadef.cmake
csrc/cmake/modules/Findnnopbase.cmake
csrc/cmake/modules/Findoptiling.cmake
csrc/cmake/modules/Findplatform.cmake
csrc/cmake/modules/Findruntime.cmake
csrc/cmake/modules/Findsecurec.cmake
csrc/cmake/modules/Findtilingapi.cmake
csrc/cmake/modules/Findunified_dlog.cmake
csrc/cmake/scripts/check_version_compatible.py
csrc/cmake/scripts/convert_yaml.py
csrc/cmake/scripts/fix_format.sh
csrc/cmake/scripts/parse_changed_files.py
csrc/cmake/scripts/prepare.sh
csrc/cmake/scripts/custom/help.info
csrc/cmake/scripts/custom/install.sh
csrc/cmake/scripts/custom/upgrade.sh
csrc/cmake/scripts/examples/get_opapi_abs_path.py
csrc/cmake/scripts/examples/get_soc_info.py
csrc/cmake/scripts/utest/gen_coverage.py
csrc/cmake/scripts/utest/gen_tiling_data_stub.py
csrc/cmake/scripts/util/ascendc_bin_param_build.py
csrc/cmake/scripts/util/ascendc_gen_options.py
csrc/cmake/scripts/util/ascendc_impl_build.py
csrc/cmake/scripts/util/ascendc_ops_config.py
csrc/cmake/scripts/util/const_var.py
csrc/cmake/scripts/util/gen_version_info.sh
csrc/cmake/scripts/util/opdesc_parser.py
csrc/cmake/scripts/util/parse_ini_to_json.py
csrc/cmake/third_party/.gitkeep
csrc/cmake/third_party/abseil-cpp.cmake
csrc/cmake/third_party/ascend_protobuf.cmake
csrc/cmake/third_party/gtest.cmake
csrc/cmake/third_party/json.cmake
csrc/cmake/third_party/makeself-fetch.cmake
csrc/cmake/third_party/protobuf.cmake
csrc/cmake/third_party/secure_c.cmake
csrc/cmake/third_party/build/modules/patch/protobuf-hide_absl_symbols.patch
csrc/cmake/third_party/build/modules/patch/protobuf_25.1_change_version.patch
csrc/common/CMakeLists.txt
csrc/common/aicpu/cpu_context_util.h
csrc/common/include/cann_compat.h
csrc/common/include/common/op_api_def.h
csrc/common/include/common/tensor_util.cpp
csrc/common/include/common/tensor_util.h
csrc/common/include/err/ops_err.h
csrc/common/include/external/aclnn_util.h
csrc/common/include/external/aclnn_kernels/cast.h
csrc/common/include/external/aclnn_kernels/contiguous.h
csrc/common/include/external/aclnn_kernels/pad.h
csrc/common/include/external/aclnn_kernels/reshape.h
csrc/common/include/external/aclnn_kernels/slice.h
csrc/common/include/external/aclnn_kernels/transdata.h
csrc/common/include/external/aclnn_kernels/transpose.h
csrc/common/include/external/aclnn_kernels/common/op_error_check.h
csrc/common/include/fallback/fallback.h
csrc/common/include/fallback/fallback_2stages.h
csrc/common/include/fallback/fallback_comm.h
csrc/common/include/fallback/fallback_comm_2stages.h
csrc/common/include/framework/onnx_common.h
csrc/common/include/kernel/common.h
csrc/common/include/kernel/common_func.h
csrc/common/include/kernel/dropmask.h
csrc/common/include/kernel/gm_to_l1_iterator.h
csrc/common/include/kernel/gm_to_ub_iterator.h
csrc/common/include/kernel/hardware.h
csrc/common/include/kernel/iterator.h
csrc/common/include/kernel/l0c_to_gm_iterator.h
csrc/common/include/kernel/l0c_to_l1_iterator.h
csrc/common/include/kernel/l0c_to_ub_iterator.h
csrc/common/include/kernel/l1_to_bt_iterator.h
csrc/common/include/kernel/l1_to_fb_iterator.h
csrc/common/include/kernel/l1_to_l0_iterator.h
csrc/common/include/kernel/l1_to_ub_iterator.h
csrc/common/include/kernel/layout.h
csrc/common/include/kernel/mem.h
csrc/common/include/kernel/mma.h
csrc/common/include/kernel/pse.h
csrc/common/include/kernel/simd.h
csrc/common/include/kernel/util.h
csrc/common/include/op_graph/op_transformer_proto_extend.h
csrc/common/include/static/op_resource.h
csrc/common/include/static/static_space.h
csrc/common/include/tiling_base/data_copy_transpose_tiling.h
csrc/common/include/tiling_base/data_copy_transpose_tiling_def.h
csrc/common/include/tiling_base/error_log.h
csrc/common/include/tiling_base/tiling_base.h
csrc/common/include/tiling_base/tiling_key.h
csrc/common/include/tiling_base/tiling_templates_registry.h
csrc/common/include/tiling_base/tiling_type.h
csrc/common/include/tiling_base/tiling_util.h
csrc/common/include/tiling_sink/device_op_impl_registry_impl.h
csrc/common/include/tiling_sink/tiling_aicpu_task.h
csrc/common/src/fallback_comm.cpp
csrc/common/src/fallback_comm_2stages.cpp
csrc/common/src/framework/CMakeLists.txt
csrc/common/src/framework/embedding_bag_onnx_plugin.cpp
csrc/common/src/framework/fillwindowcache_onnx_plugin.cpp
csrc/common/src/framework/multi_head_attention_onnx_plugin.cpp
csrc/common/src/framework/npu_fused_attention_score_fwd_onnx_plugin.cpp
csrc/common/src/framework/npu_fused_attention_score_onnx_plugin.cpp
csrc/common/src/framework/npu_masked_softmax_with_relposbias_onnx_plugin.cpp
csrc/common/src/framework/npu_scaled_masked_softmax_onnx_plugin.cpp
csrc/common/src/framework/tfidf_vectorizer_onnx_plugin.cpp
csrc/common/src/tiling_base/tiling_util.cpp
csrc/common/src/tiling_sink/CMakeLists.txt
csrc/common/src/tiling_sink/tiling_sink_registry.cpp
csrc/common/stub/CMakeLists.txt
csrc/common/stub/inc/framework/stub_ops.h
csrc/common/stub/op_api/CMakeLists.txt
csrc/common/stub/op_api/opapi_stub.cpp
csrc/common/stub/op_api/aclnn_kernels/cast.h
csrc/common/stub/op_api/aclnn_kernels/contiguous.h
csrc/common/stub/op_api/aclnn_kernels/pad.h
csrc/common/stub/op_api/aclnn_kernels/reshape.h
csrc/common/stub/op_api/aclnn_kernels/slice.h
csrc/common/stub/op_api/aclnn_kernels/transdata.h
csrc/common/stub/op_api/aclnn_kernels/transpose.h
csrc/common/stub/op_api/aclnn_kernels/common/op_error_check.h
csrc/common/stub/op_api/level0/add.h
csrc/common/stub/op_api/level0/arange.h
csrc/common/stub/op_api/level0/axpy.h
csrc/common/stub/op_api/level0/batch_norm_backward.h
csrc/common/stub/op_api/level0/broadcast_to.h
csrc/common/stub/op_api/level0/dilation.h
csrc/common/stub/op_api/level0/div.h
csrc/common/stub/op_api/level0/dot.h
csrc/common/stub/op_api/level0/expand.h
csrc/common/stub/op_api/level0/fault_injection.h
csrc/common/stub/op_api/level0/fill.h
csrc/common/stub/op_api/level0/gather_elements.h
csrc/common/stub/op_api/level0/gather_v2.h
csrc/common/stub/op_api/level0/gather_v3.h
csrc/common/stub/op_api/level0/inplace_index_add.h
csrc/common/stub/op_api/level0/masked_scatter.h
csrc/common/stub/op_api/level0/matmul_v2tov3.h
csrc/common/stub/op_api/level0/maximum.h
csrc/common/stub/op_api/level0/minimum.h
csrc/common/stub/op_api/level0/mul.h
csrc/common/stub/op_api/level0/muls.h
csrc/common/stub/op_api/level0/ones_like.h
csrc/common/stub/op_api/level0/padv3.h
csrc/common/stub/op_api/level0/reduce_mean.h
csrc/common/stub/op_api/level0/reduce_sum_op.h
csrc/common/stub/op_api/level0/shape_op.h
csrc/common/stub/op_api/level0/sort.h
csrc/common/stub/op_api/level0/squeeze.h
csrc/common/stub/op_api/level0/sub.h
csrc/common/stub/op_api/level0/tensor_move.h
csrc/common/stub/op_api/level0/unsqueeze.h
csrc/common/stub/op_api/level0/zero_op.h
csrc/common/stub/op_tiling/CMakeLists.txt
csrc/common/stub/op_tiling/op_cache_def_tiling.h
csrc/common/stub/op_tiling/op_cache_tiling.cpp
csrc/common/stub/op_tiling/op_cache_tiling.h
csrc/common/stub/op_tiling/runtime_kb_api.cpp
csrc/common/stub/op_tiling/runtime_kb_api.h
csrc/common/stub/op_tiling/tbe_tiling_api.cpp
csrc/common/stub/op_tiling/tbe_tiling_api.h
csrc/common/stub/op_tiling/register/tuning_bank_key_registry.h
csrc/common/stub/op_tiling/register/tuning_tiling_reflection_utils.h
csrc/common/stub/op_tiling/register/tuning_tiling_registry.h
csrc/gmm/CMakeLists.txt
csrc/gmm/grouped_matmul_swiglu_quant/CMakeLists.txt
csrc/gmm/grouped_matmul_swiglu_quant/README.md
csrc/gmm/grouped_matmul_swiglu_quant/op_host/CMakeLists.txt
csrc/gmm/grouped_matmul_swiglu_quant/op_host/grouped_matmul_swiglu_quant_def.cpp
csrc/gmm/grouped_matmul_swiglu_quant/op_host/grouped_matmul_swiglu_quant_infershape.cpp
csrc/gmm/grouped_matmul_swiglu_quant/op_host/grouped_matmul_swiglu_quant_tiling.cpp
csrc/gmm/grouped_matmul_swiglu_quant/op_host/grouped_matmul_swiglu_quant_tiling.h
csrc/gmm/grouped_matmul_swiglu_quant/op_host/op_api/aclnn_grouped_matmul_swiglu_quant.cpp
csrc/gmm/grouped_matmul_swiglu_quant/op_host/op_api/aclnn_grouped_matmul_swiglu_quant.h
csrc/gmm/grouped_matmul_swiglu_quant/op_host/op_api/aclnn_grouped_matmul_swiglu_quant_weight_nz.h
csrc/gmm/grouped_matmul_swiglu_quant/op_host/op_api/grouped_matmul_swiglu_quant.cpp
csrc/gmm/grouped_matmul_swiglu_quant/op_host/op_api/grouped_matmul_swiglu_quant.h
csrc/gmm/grouped_matmul_swiglu_quant/op_kernel/grouped_matmul_swiglu_pipeline.h
csrc/gmm/grouped_matmul_swiglu_quant/op_kernel/grouped_matmul_swiglu_quant.cpp
csrc/gmm/grouped_matmul_swiglu_quant/op_kernel/grouped_matmul_swiglu_quant.h
csrc/gmm/grouped_matmul_swiglu_quant/op_kernel/grouped_matmul_swiglu_quant_a8w4_msd_mid.h
csrc/gmm/grouped_matmul_swiglu_quant/op_kernel/grouped_matmul_swiglu_quant_a8w4_msd_post.h
csrc/gmm/grouped_matmul_swiglu_quant/op_kernel/grouped_matmul_swiglu_quant_a8w4_msd_pre.h
csrc/gmm/grouped_matmul_swiglu_quant/op_kernel/grouped_matmul_swiglu_quant_split_ws.h
csrc/gmm/grouped_matmul_swiglu_quant/op_kernel/grouped_matmul_swiglu_quant_utils.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/CMakeLists.txt
csrc/gmm/grouped_matmul_swiglu_quant_v2/grouped_matmul_swiglu_quant_v2_torch_adpt.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/CMakeLists.txt
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/grouped_matmul_swiglu_quant_v2_base_tiling.cpp
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/grouped_matmul_swiglu_quant_v2_base_tiling.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/grouped_matmul_swiglu_quant_v2_def.cpp
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/grouped_matmul_swiglu_quant_v2_fusion_tiling.cpp
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/grouped_matmul_swiglu_quant_v2_fusion_tiling.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/grouped_matmul_swiglu_quant_v2_host_utils.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/grouped_matmul_swiglu_quant_v2_infershape.cpp
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/grouped_matmul_swiglu_quant_v2_tiling.cpp
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/grouped_matmul_swiglu_quant_v2_tiling.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/op_api/aclnn_grouped_matmul_swiglu_quant_v2.cpp
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/op_api/aclnn_grouped_matmul_swiglu_quant_v2.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/op_api/aclnn_grouped_matmul_swiglu_quant_weight_nz_v2.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/op_api/gmm_dsq_base.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/op_api/grouped_matmul_swiglu_quant_utils.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/op_api/grouped_matmul_swiglu_quant_v2.cpp
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/op_api/grouped_matmul_swiglu_quant_v2.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_host/op_api/grouped_matmul_swiglu_quant_v2_utils.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/grouped_matmul_swiglu_quant_spilit_fusion.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/grouped_matmul_swiglu_quant_v2.cpp
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/grouped_matmul_swiglu_quant_v2_a4w4_mid.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/grouped_matmul_swiglu_quant_v2_a4w4_pipeline.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/grouped_matmul_swiglu_quant_v2_a4w4_post.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/grouped_matmul_swiglu_quant_v2_a8w4_msd_mid.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/grouped_matmul_swiglu_quant_v2_a8w4_msd_pipeline.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/grouped_matmul_swiglu_quant_v2_a8w4_msd_post.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/grouped_matmul_swiglu_quant_v2_a8w4_msd_pre.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/grouped_matmul_swiglu_quant_v2_apt.cpp
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/grouped_matmul_swiglu_quant_v2_utils.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/arch35/grouped_matmul_swiglu_quant_v2_mxquant.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/arch35/grouped_matmul_swiglu_quant_v2_pertoken_quant.h
csrc/gmm/grouped_matmul_swiglu_quant_v2/op_kernel/arch35/grouped_matmul_swiglu_quant_v2_tiling_key.h
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/CMakeLists.txt
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/grouped_matmul_swiglu_quant_torch_adpt.h
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_host/CMakeLists.txt
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_host/grouped_matmul_swiglu_quant_weight_nz_tensor_list.h
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_host/grouped_matmul_swiglu_quant_weight_nz_tensor_list_def.cpp
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_host/grouped_matmul_swiglu_quant_weight_nz_tensor_list_infershape.cpp
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_host/grouped_matmul_swiglu_quant_weight_nz_tensor_list_proto.cpp
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_host/grouped_matmul_swiglu_quant_weight_nz_tensor_list_tiling.cpp
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_host/grouped_matmul_swiglu_quant_weight_nz_tensor_list_tiling.h
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_host/op_api/aclnn_grouped_matmul_swiglu_quant_weight_nz_tensor_list.cpp
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_host/op_api/aclnn_grouped_matmul_swiglu_quant_weight_nz_tensor_list.h
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_host/op_api/grouped_matmul_swiglu_quant_weight_nz_tensor_list.cpp
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_kernel/grouped_matmul_swiglu_quant_weight_nz_tensor_list.cpp
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_kernel/grouped_matmul_swiglu_quant_weight_nz_tensor_list.h
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_kernel/grouped_matmul_swiglu_quant_weight_nz_tensor_list_split_ws.h
csrc/gmm/grouped_matmul_swiglu_quant_weight_nz_tensor_list/op_kernel/grouped_matmul_swiglu_quant_weight_nz_tensor_list_utils.h
csrc/kernels/bgmv_expand.cpp
csrc/kernels/bgmv_shrink.cpp
csrc/kernels/get_masked_input_and_mask_kernel.cpp
csrc/kernels/math_utils.h
csrc/kernels/sgmv_expand.cpp
csrc/kernels/sgmv_shrink.cpp
csrc/kernels/types.h
csrc/kernels/utils.h
csrc/mc2/CMakeLists.txt
csrc/mc2/dispatch_ffn_combine/CMakeLists.txt
csrc/mc2/dispatch_ffn_combine/dispatch_ffn_combine_torch_adpt.h
csrc/mc2/dispatch_ffn_combine/op_host/CMakeLists.txt
csrc/mc2/dispatch_ffn_combine/op_host/dispatch_ffn_combine_def.cpp
csrc/mc2/dispatch_ffn_combine/op_host/dispatch_ffn_combine_proto.cpp
csrc/mc2/dispatch_ffn_combine/op_host/dispatch_ffn_combine_tiling.cpp
csrc/mc2/dispatch_ffn_combine/op_host/hcom_topo_info.h
csrc/mc2/dispatch_ffn_combine/op_host/tiling_args.h
csrc/mc2/dispatch_ffn_combine/op_host/op_api/aclnn_dispatch_ffn_combine.cpp
csrc/mc2/dispatch_ffn_combine/op_host/op_api/aclnn_dispatch_ffn_combine.h
csrc/mc2/dispatch_ffn_combine/op_kernel/dispatch_ffn_combine.cpp
csrc/mc2/dispatch_ffn_combine/op_kernel/dispatch_ffn_combine.h
csrc/mc2/dispatch_ffn_combine/op_kernel/dispatch_ffn_combine_kernel.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/dispatch_ffn_combine_tiling.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_init_routing_quant_v2.cpp
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_init_routing_quant_v2_tiling.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_init_routing_v2_tiling.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_common.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_expert_token_out.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_fullload_dynamic_quant.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_fullload_quant.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_fullload_quant_base.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_gather_dynamic_quant.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_gather_out.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_gather_quant.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_init_routing_fullload.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_mrgsort.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_mrgsort_out.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_sort_base.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_sort_multi_core.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_sort_one_core.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_src_to_dst_and_gather.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_src_to_dst_op.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/moe_v2_src_to_dst_with_capacity.h
csrc/mc2/dispatch_ffn_combine/op_kernel/moe_init_routing_quant_v2/tiling_base.h
csrc/mc2/dispatch_ffn_combine/op_kernel/unpermute/moe_token_unpermute.h
csrc/mc2/dispatch_ffn_combine/op_kernel/unpermute/moe_token_unpermute_tiling.h
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/block_epilogue_pertoken_row.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/block_epilogue_pertoken_swiglu.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/block_epilogue_pertoken_v2.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/block_mmad_preload_async_fixpipe_quant.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/const_args.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/copy_gm_to_l1_custom.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/copy_l0c_to_gm_custom.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/dispatch_policy_custom.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/get_tensor_addr.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/hccl_shmem.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/layout3d.hpp
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/moe_distribute_base.h
csrc/mc2/dispatch_ffn_combine/op_kernel/utils/select_helper.hpp
csrc/mc2/dispatch_ffn_combine_bf16/CMakeLists.txt
csrc/mc2/dispatch_ffn_combine_bf16/op_host/CMakeLists.txt
csrc/mc2/dispatch_ffn_combine_bf16/op_host/dispatch_ffn_combine_bf16_def.cpp
csrc/mc2/dispatch_ffn_combine_bf16/op_host/dispatch_ffn_combine_bf16_proto.cpp
csrc/mc2/dispatch_ffn_combine_bf16/op_host/dispatch_ffn_combine_bf16_tiling.cpp
csrc/mc2/dispatch_ffn_combine_bf16/op_host/hcom_topo_info.h
csrc/mc2/dispatch_ffn_combine_bf16/op_host/tiling_args.h
csrc/mc2/dispatch_ffn_combine_bf16/op_host/op_api/aclnn_dispatch_ffn_combine_bf16.cpp
csrc/mc2/dispatch_ffn_combine_bf16/op_host/op_api/aclnn_dispatch_ffn_combine_bf16.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/dispatch_ffn_combine_bf16.cpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/dispatch_ffn_combine_bf16.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/dispatch_ffn_combine_bf16_kernel.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/dispatch_ffn_combine_bf16_tiling.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_init_routing_v2.cpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_init_routing_v2_tiling.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_common.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_expert_token_out.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_gather_out.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_init_routing_fullload.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_mrgsort.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_mrgsort_out.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_sort_base.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_sort_multi_core.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_sort_one_core.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_src_to_dst_op.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_src_to_dst_op_simt.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/moe_v2_src_to_dst_with_capacity.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/moe_init_routing_v2/tiling_base.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/unpermute/moe_token_unpermute.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/unpermute/moe_token_unpermute_tiling.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/block_epilogue_pertoken_row.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/block_epilogue_pertoken_swiglu.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/block_epilogue_pertoken_v2.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/block_mmad_preload_async_fixpipe_quant.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/const_args.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/copy_gm_to_l1_custom.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/copy_l0c_to_gm_custom.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/dispatch_policy_custom.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/get_tensor_addr.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/hccl_shmem.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/layout3d.hpp
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/moe_distribute_base.h
csrc/mc2/dispatch_ffn_combine_bf16/op_kernel/utils/select_helper.hpp
csrc/mc2/dispatch_ffn_combine_w4_a8/CMakeLists.txt
csrc/mc2/dispatch_ffn_combine_w4_a8/op_host/CMakeLists.txt
csrc/mc2/dispatch_ffn_combine_w4_a8/op_host/dispatch_ffn_combine_w4_a8_def.cpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_host/dispatch_ffn_combine_w4_a8_proto.cpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_host/dispatch_ffn_combine_w4_a8_tiling.cpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_host/hcom_topo_info.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_host/tiling_args.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_host/op_api/aclnn_dispatch_ffn_combine_w4_a8.cpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_host/op_api/aclnn_dispatch_ffn_combine_w4_a8.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/dispatch_ffn_combine_w4_a8.cpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/dispatch_ffn_combine_w4_a8.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/dispatch_ffn_combine_w4_a8_kernel.hpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/dispatch_ffn_combine_w4_a8_tiling.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_init_routing_quant_v2.cpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_init_routing_quant_v2_tiling.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_init_routing_v2_tiling.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_common.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_expert_token_out.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_fullload_dynamic_quant.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_fullload_quant.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_fullload_quant_base.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_gather_dynamic_quant.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_gather_out.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_gather_quant.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_init_routing_fullload.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_mrgsort.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_mrgsort_out.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_sort_base.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_sort_multi_core.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_sort_one_core.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_src_to_dst_and_gather.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_src_to_dst_op.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/moe_v2_src_to_dst_with_capacity.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/moe_init_routing_quant_v2/tiling_base.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/unpermute/moe_token_unpermute.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/unpermute/moe_token_unpermute_tiling.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/utils/block_epilogue_w4a8post_pertoken_swiglu.hpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/utils/block_epilogue_w4a8post_pertoken_v2.hpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/utils/block_mmad_w4a4.hpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/utils/const_args.hpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/utils/copy_gm_to_l1_custom.hpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/utils/dispatch_policy_custom.hpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/utils/get_tensor_addr.hpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/utils/hccl_shmem.hpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/utils/layout3d.hpp
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/utils/moe_distribute_base.h
csrc/mc2/dispatch_ffn_combine_w4_a8/op_kernel/utils/select_helper.hpp
csrc/mc2/dispatch_gmm_combine_decode/CMakeLists.txt
csrc/mc2/dispatch_gmm_combine_decode/dispatch_gmm_combine_decode_torch_adpt.h
csrc/mc2/dispatch_gmm_combine_decode/op_host/CMakeLists.txt
csrc/mc2/dispatch_gmm_combine_decode/op_host/dispatch_gmm_combine_decode_def.cpp
csrc/mc2/dispatch_gmm_combine_decode/op_host/dispatch_gmm_combine_decode_proto.cpp
csrc/mc2/dispatch_gmm_combine_decode/op_host/dispatch_gmm_combine_decode_tiling.cpp
csrc/mc2/dispatch_gmm_combine_decode/op_host/op_api/aclnn_dispatch_gmm_combine_decode.cpp
csrc/mc2/dispatch_gmm_combine_decode/op_host/op_api/aclnn_dispatch_gmm_combine_decode.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode.cpp
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode_base.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode_bf16_fp16.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode_tiling.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/moe_distribute_base.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/epilogue/dispatch_policy.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/epilogue/block/block_epilogue.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/epilogue/block/block_epilogue_bf16_fp16.hpp
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/epilogue/block/block_epilogue_per_token_dequant.hpp
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/epilogue/block/block_epilogue_per_token_dequant_swiglu.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/epilogue/block/block_epilogue_swiglu_bf16_fp16.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/epilogue/tile/tile_stride_binary.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/epilogue/tile/tile_stride_muls.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/gemm/dispatch_policy.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/gemm/block/block_mmad.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/gemm/block/block_mmad_preload_async_with_callback_resident_a.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/gemm/kernel/grouped_matmul_slice_m_multistage_workspace_bf16_fp16.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/gemm/kernel/grouped_matmul_slice_m_per_token_dequant_multistage_workspace.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/gemm/kernel/grouped_matmul_slice_m_per_token_dequant_swiglu_quant_multistage_workspace.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/gemm/kernel/grouped_matmul_slice_m_swiglu_multistage_workspace_bf16_fp16.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/raw_distributed/cam_moe_distribute_combine.h
csrc/mc2/dispatch_gmm_combine_decode/op_kernel/dispatch_gmm_combine_decode/raw_distributed/cam_moe_distribute_dispatch.h
csrc/mc2/matmul_allreduce_add_rmsnorm/CMakeLists.txt
csrc/mc2/matmul_allreduce_add_rmsnorm/matmul_allreduce_add_rmsnorm_torch_adpt.h
csrc/mc2/matmul_allreduce_add_rmsnorm/op_host/CMakeLists.txt
csrc/mc2/matmul_allreduce_add_rmsnorm/op_host/matmul_allreduce_add_rmsnorm_def.cpp
csrc/mc2/matmul_allreduce_add_rmsnorm/op_host/matmul_allreduce_add_rmsnorm_proto.cpp
csrc/mc2/matmul_allreduce_add_rmsnorm/op_host/matmul_allreduce_add_rmsnorm_tiling.cpp
csrc/mc2/matmul_allreduce_add_rmsnorm/op_host/matmul_allreduce_add_rmsnorm_workspace.h
csrc/mc2/matmul_allreduce_add_rmsnorm/op_host/op_api/aclnn_matmul_allreduce_add_rmsnorm.cpp
csrc/mc2/matmul_allreduce_add_rmsnorm/op_host/op_api/aclnn_matmul_allreduce_add_rmsnorm.h
csrc/mc2/matmul_allreduce_add_rmsnorm/op_kernel/matmul_allreduce_add_rmsnorm.cpp
csrc/mc2/matmul_allreduce_add_rmsnorm/op_kernel/matmul_allreduce_add_rmsnorm_aic_kernel.h
csrc/mc2/matmul_allreduce_add_rmsnorm/op_kernel/matmul_allreduce_add_rmsnorm_aiv_kernel.h
csrc/mc2/matmul_allreduce_add_rmsnorm/op_kernel/matmul_allreduce_add_rmsnorm_tiling.h
csrc/mc2/matmul_allreduce_add_rmsnorm/op_kernel/matmul_allreduce_add_rmsnorm_utils.h
csrc/mla_preprocess/mla_preprocess_torch_adpt.h
csrc/mla_preprocess/op_host/mla_preprocess.h
csrc/mla_preprocess/op_host/tiling/mla_preprocess_tiling.h
csrc/mla_preprocess/op_kernel/mla_preprocess.h
csrc/mla_preprocess/op_kernel/mla_preprocess_kernel.cpp
csrc/mla_preprocess/op_kernel/mla_preprocess_mix_bf16.hpp
csrc/mla_preprocess/op_kernel/mla_preprocess_mix_bf16_nq.hpp
csrc/mla_preprocess/op_kernel/mla_preprocess_mix_bf16_qdown.hpp
csrc/mla_preprocess/op_kernel/mla_preprocess_mix_fp16.hpp
csrc/mla_preprocess/op_kernel/kernel/common.h
csrc/mla_preprocess/op_kernel/kernel/common_func.h
csrc/mla_preprocess/op_kernel/kernel/hardware.h
csrc/mla_preprocess/op_kernel/kernel/iterator.h
csrc/mla_preprocess/op_kernel/kernel/kernel_utils.h
csrc/mla_preprocess/op_kernel/kernel/layout.h
csrc/mla_preprocess/op_kernel/kernel/mem.h
csrc/mla_preprocess/op_kernel/kernel/mma.h
csrc/mla_preprocess/op_kernel/kernel/set_fpc.h
csrc/mla_preprocess/op_kernel/kernel/simd.h
csrc/mla_preprocess/op_kernel/kernel/utils.h
csrc/mla_preprocess/op_kernel/kernel/iterators/gm_to_l1_iterator.inc
csrc/mla_preprocess/op_kernel/kernel/iterators/gm_to_ub_iterator.inc
csrc/mla_preprocess/op_kernel/kernel/iterators/l0c_to_gm_iterator.inc
csrc/mla_preprocess/op_kernel/kernel/iterators/l0c_to_l1_iterator.inc
csrc/mla_preprocess/op_kernel/kernel/iterators/l0c_to_ub_iterator.inc
csrc/mla_preprocess/op_kernel/kernel/iterators/l1_to_bt_iterator.inc
csrc/mla_preprocess/op_kernel/kernel/iterators/l1_to_fb_iterator.inc
csrc/mla_preprocess/op_kernel/kernel/iterators/l1_to_l0_iterator.inc
csrc/mla_preprocess/op_kernel/kernel/iterators/l1_to_ub_iterator.inc
csrc/moe/CMakeLists.txt
csrc/moe/add_rms_norm_bias/CMakeLists.txt
csrc/moe/add_rms_norm_bias/add_rms_norm_bias_torch_adpt.h
csrc/moe/add_rms_norm_bias/op_host/CMakeLists.txt
csrc/moe/add_rms_norm_bias/op_host/add_rms_norm_bias_def.cpp
csrc/moe/add_rms_norm_bias/op_host/add_rms_norm_bias_infershape.cpp
csrc/moe/add_rms_norm_bias/op_host/add_rms_norm_bias_tiling.cpp
csrc/moe/add_rms_norm_bias/op_host/add_rms_norm_bias_tiling.h
csrc/moe/add_rms_norm_bias/op_kernel/add_rms_norm_bias.cpp
csrc/moe/add_rms_norm_bias/op_kernel/add_rms_norm_bias.h
csrc/moe/add_rms_norm_bias/op_kernel/add_rms_norm_bias_merge_n.h
csrc/moe/add_rms_norm_bias/op_kernel/add_rms_norm_bias_multi_n.h
csrc/moe/add_rms_norm_bias/op_kernel/add_rms_norm_bias_single_n.h
csrc/moe/add_rms_norm_bias/op_kernel/add_rms_norm_bias_split_d.h
csrc/moe/add_rms_norm_bias/op_kernel/reduce_common.h
csrc/moe/add_rms_norm_bias/op_kernel/rms_norm_base.h
csrc/moe/causal_conv1d/CMakeLists.txt
csrc/moe/causal_conv1d/op_host/CMakeLists.txt
csrc/moe/causal_conv1d/op_host/causal_conv1d_def.cpp
csrc/moe/causal_conv1d/op_host/causal_conv1d_infershape.cpp
csrc/moe/causal_conv1d/op_host/causal_conv1d_tiling.cpp
csrc/moe/causal_conv1d/op_host/causal_conv1d_tiling_planner.h
csrc/moe/causal_conv1d/op_host/causal_conv1d_tiling_utils.h
csrc/moe/causal_conv1d/op_host/causal_conv1d_tiling_validation.h
csrc/moe/causal_conv1d/op_host/math_util.h
csrc/moe/causal_conv1d/op_kernel/causal_conv1d.cpp
csrc/moe/causal_conv1d/op_kernel/causal_conv1d.h
csrc/moe/causal_conv1d/op_kernel/causal_conv1d_common.h
csrc/moe/causal_conv1d/op_kernel/causal_conv1d_fn.h
csrc/moe/causal_conv1d/op_kernel/causal_conv1d_fn_tasks.h
csrc/moe/causal_conv1d/op_kernel/causal_conv1d_tiling_data.h
csrc/moe/causal_conv1d/op_kernel/causal_conv1d_tiling_key.h
csrc/moe/causal_conv1d/op_kernel/causal_conv1d_update.h
csrc/moe/causal_conv1d/op_kernel/arch35/causal_conv1d_regbase.h
csrc/moe/causal_conv1d_v310/CMakeLists.txt
csrc/moe/causal_conv1d_v310/causal_conv1d_310_torch_adpt.h
csrc/moe/causal_conv1d_v310/op_host/CMakeLists.txt
csrc/moe/causal_conv1d_v310/op_host/causal_conv1d_v310_def.cpp
csrc/moe/causal_conv1d_v310/op_host/causal_conv1d_v310_infershape.cpp
csrc/moe/causal_conv1d_v310/op_host/causal_conv1d_v310_tiling.cpp
csrc/moe/causal_conv1d_v310/op_host/causal_conv1d_v310_tiling.h
csrc/moe/causal_conv1d_v310/op_host/math_util.h
csrc/moe/causal_conv1d_v310/op_kernel/causal_conv1d_v310.cpp
csrc/moe/causal_conv1d_v310/op_kernel/causal_conv1d_v310.h
csrc/moe/causal_conv1d_v310/op_kernel/causal_conv1d_v310_common.h
csrc/moe/causal_conv1d_v310/op_kernel/causal_conv1d_v310_tiling_data.h
csrc/moe/causal_conv1d_v310/op_kernel/causal_conv1d_v310_tiling_key.h
csrc/moe/chunk_fwd_o/CMakeLists.txt
csrc/moe/chunk_fwd_o/op_host/CMakeLists.txt
csrc/moe/chunk_fwd_o/op_host/chunk_fwd_o_def.cpp
csrc/moe/chunk_fwd_o/op_host/chunk_fwd_o_tiling.cpp
csrc/moe/chunk_fwd_o/op_host/chunk_fwd_o_tiling.h
csrc/moe/chunk_fwd_o/op_host/op_api/aclnn_chunk_fwd_o.cpp
csrc/moe/chunk_fwd_o/op_host/op_api/aclnn_chunk_fwd_o.h
csrc/moe/chunk_fwd_o/op_host/op_api/chunk_fwd_o.cpp
csrc/moe/chunk_fwd_o/op_host/op_api/chunk_fwd_o.h
csrc/moe/chunk_fwd_o/op_kernel/chunk_fwd_o.cpp
csrc/moe/chunk_fwd_o/op_kernel/arch20/compat_310p.h
csrc/moe/chunk_fwd_o/op_kernel/arch20/epilogue/gdn_fwd_o_epilogue_policies.hpp
csrc/moe/chunk_fwd_o/op_kernel/arch20/epilogue/block/block_epilogue_gdn_fwdo_output.hpp
csrc/moe/chunk_fwd_o/op_kernel/arch20/epilogue/block/block_epilogue_gdn_fwdo_qkmask.hpp
csrc/moe/chunk_fwd_o/op_kernel/arch20/gemm/block/block_scheduler_gdn_fwd_o.hpp
csrc/moe/chunk_fwd_o/op_kernel/arch20/gemm/kernel/gdn_fwd_o_kernel.hpp
csrc/moe/chunk_fwd_o/op_kernel/arch22/epilogue/gdn_fwd_o_epilogue_policies.hpp
csrc/moe/chunk_fwd_o/op_kernel/arch22/epilogue/block/block_epilogue_gdn_fwdo_output.hpp
csrc/moe/chunk_fwd_o/op_kernel/arch22/epilogue/block/block_epilogue_gdn_fwdo_qkmask.hpp
csrc/moe/chunk_fwd_o/op_kernel/arch22/gemm/block/block_scheduler_gdn_fwd_o.hpp
csrc/moe/chunk_fwd_o/op_kernel/arch22/gemm/kernel/gdn_fwd_o_kernel.hpp
csrc/moe/chunk_fwd_o/tiling_base/data_copy_transpose_tiling.h
csrc/moe/chunk_fwd_o/tiling_base/data_copy_transpose_tiling_def.h
csrc/moe/chunk_fwd_o/tiling_base/error_log.h
csrc/moe/chunk_fwd_o/tiling_base/tiling_base.h
csrc/moe/chunk_fwd_o/tiling_base/tiling_key.h
csrc/moe/chunk_fwd_o/tiling_base/tiling_templates_registry.h
csrc/moe/chunk_fwd_o/tiling_base/tiling_type.h
csrc/moe/chunk_fwd_o/tiling_base/tiling_util.h
csrc/moe/chunk_gated_delta_rule_fwd_h/CMakeLists.txt
csrc/moe/chunk_gated_delta_rule_fwd_h/op_host/CMakeLists.txt
csrc/moe/chunk_gated_delta_rule_fwd_h/op_host/chunk_gated_delta_rule_fwd_h_def.cpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_host/chunk_gated_delta_rule_fwd_h_tiling.cpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_host/chunk_gated_delta_rule_fwd_h_tiling.h
csrc/moe/chunk_gated_delta_rule_fwd_h/op_host/op_api/aclnn_chunk_gated_delta_rule_fwd_h.cpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_host/op_api/aclnn_chunk_gated_delta_rule_fwd_h.h
csrc/moe/chunk_gated_delta_rule_fwd_h/op_host/op_api/chunk_gated_delta_rule_fwd_h.cpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_host/op_api/chunk_gated_delta_rule_fwd_h.h
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/chunk_gated_delta_rule_fwd_h.cpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/arch20/compat_310p.h
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/arch20/epilogue/gdn_fwd_h_epilogue_policies.hpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/arch20/epilogue/block/block_epilogue_gdn_fwdh_update.hpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/arch20/epilogue/block/block_epilogue_gdn_fwdh_vnew.hpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/arch20/gemm/block/block_scheduler_gdn_fwd_h.hpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/arch20/gemm/kernel/gdn_fwd_h_kernel.hpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/arch22/epilogue/gdn_fwd_h_epilogue_policies.hpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/arch22/epilogue/block/block_epilogue_gdn_fwdh_update.hpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/arch22/epilogue/block/block_epilogue_gdn_fwdh_vnew.hpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/arch22/gemm/block/block_scheduler_gdn_fwd_h.hpp
csrc/moe/chunk_gated_delta_rule_fwd_h/op_kernel/arch22/gemm/kernel/gdn_fwd_h_kernel.hpp
csrc/moe/chunk_gated_delta_rule_fwd_h/tiling_base/data_copy_transpose_tiling.h
csrc/moe/chunk_gated_delta_rule_fwd_h/tiling_base/data_copy_transpose_tiling_def.h
csrc/moe/chunk_gated_delta_rule_fwd_h/tiling_base/error_log.h
csrc/moe/chunk_gated_delta_rule_fwd_h/tiling_base/tiling_base.h
csrc/moe/chunk_gated_delta_rule_fwd_h/tiling_base/tiling_key.h
csrc/moe/chunk_gated_delta_rule_fwd_h/tiling_base/tiling_templates_registry.h
csrc/moe/chunk_gated_delta_rule_fwd_h/tiling_base/tiling_type.h
csrc/moe/chunk_gated_delta_rule_fwd_h/tiling_base/tiling_util.h
csrc/moe/common/kernel_utils/block/block_mmad_pingpong_tla_multi.hpp
csrc/moe/copy_and_expand_eagle_inputs/CMakeLists.txt
csrc/moe/copy_and_expand_eagle_inputs/op_host/CMakeLists.txt
csrc/moe/copy_and_expand_eagle_inputs/op_host/copy_and_expand_eagle_inputs_def.cpp
csrc/moe/copy_and_expand_eagle_inputs/op_host/copy_and_expand_eagle_inputs_infershape.cpp
csrc/moe/copy_and_expand_eagle_inputs/op_host/copy_and_expand_eagle_inputs_tiling.cpp
csrc/moe/copy_and_expand_eagle_inputs/op_host/copy_and_expand_eagle_inputs_tiling.h
csrc/moe/copy_and_expand_eagle_inputs/op_kernel/copy_and_expand_eagle_inputs.cpp
csrc/moe/dequant_swiglu_quant/CMakeLists.txt
csrc/moe/dequant_swiglu_quant/op_host/CMakeLists.txt
csrc/moe/dequant_swiglu_quant/op_host/dequant_swiglu_quant_def.cpp
csrc/moe/dequant_swiglu_quant/op_host/dequant_swiglu_quant_infershape.cpp
csrc/moe/dequant_swiglu_quant/op_host/dequant_swiglu_quant_proto.h
csrc/moe/dequant_swiglu_quant/op_host/dequant_swiglu_quant_tiling.cpp
csrc/moe/dequant_swiglu_quant/op_host/dequant_swiglu_quant_tiling.h
csrc/moe/dequant_swiglu_quant/op_host/dequant_swiglu_quant_tiling_arch35.cpp
csrc/moe/dequant_swiglu_quant/op_host/dequant_swiglu_quant_tiling_base.cpp
csrc/moe/dequant_swiglu_quant/op_host/swi_glu_grad_regbase_tiling.h
csrc/moe/dequant_swiglu_quant/op_host/swi_glu_grad_tiling_regbase.h
csrc/moe/dequant_swiglu_quant/op_host/swi_glu_tiling.h
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant.cpp
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant.h
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant_apt.cpp
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant_cut_group.h
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant_dynamic_base.hpp
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant_dynamic_bf16.hpp
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant_dynamic_bias_float.hpp
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant_dynamic_bias_int32.hpp
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant_dynamic_performance.hpp
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant_static_base.hpp
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant_static_bf16.hpp
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant_static_bias_float.hpp
csrc/moe/dequant_swiglu_quant/op_kernel/dequant_swiglu_quant_static_bias_int32.hpp
csrc/moe/dequant_swiglu_quant/tiling_base/error_log.h
csrc/moe/dequant_swiglu_quant/tiling_base/static_register_symbol.h
csrc/moe/dequant_swiglu_quant/tiling_base/tiling_base.h
csrc/moe/dequant_swiglu_quant/tiling_base/tiling_key.h
csrc/moe/dequant_swiglu_quant/tiling_base/tiling_templates_registry.h
csrc/moe/dequant_swiglu_quant/tiling_base/tiling_util.h
csrc/moe/hamming_dist_top_k/CMakeLists.txt
csrc/moe/hamming_dist_top_k/op_host/CMakeLists.txt
csrc/moe/hamming_dist_top_k/op_host/hamming_dist_top_k.cpp
csrc/moe/hamming_dist_top_k/op_host/hamming_dist_top_k.h
csrc/moe/hamming_dist_top_k/op_host/hamming_dist_top_k_def.cpp
csrc/moe/hamming_dist_top_k/op_host/hamming_dist_top_k_proto.cpp
csrc/moe/hamming_dist_top_k/op_host/hamming_dist_top_k_split.cpp
csrc/moe/hamming_dist_top_k/op_host/hamming_dist_top_k_split.h
csrc/moe/hamming_dist_top_k/op_host/hamming_dist_top_k_tiling.cpp
csrc/moe/hamming_dist_top_k/op_host/hamming_dist_top_k_tiling.h
csrc/moe/hamming_dist_top_k/op_host/op_host_util.h
csrc/moe/hamming_dist_top_k/op_kernel/hamming_dist_top_k.cpp
csrc/moe/hamming_dist_top_k/op_kernel/hamming_dist_top_k_base.h
csrc/moe/hamming_dist_top_k/op_kernel/hamming_dist_top_k_parallel.h
csrc/moe/hamming_dist_top_k/op_kernel/hamming_dist_top_k_split_s.h
csrc/moe/hc_post/CMakeLists.txt
csrc/moe/hc_post/op_host/CMakeLists.txt
csrc/moe/hc_post/op_host/hc_post_def.cpp
csrc/moe/hc_post/op_host/hc_post_proto.cpp
csrc/moe/hc_post/op_host/hc_post_tiling.cpp
csrc/moe/hc_post/op_host/hc_post_tiling.h
csrc/moe/hc_post/op_host/hc_post_tiling_arch35.h
csrc/moe/hc_post/op_kernel/hc_post.cpp
csrc/moe/hc_post/op_kernel/hc_post_bfloat16.h
csrc/moe/hc_post/op_kernel/hc_post_d_split.h
csrc/moe/hc_post/op_kernel/hc_post_float32.h
csrc/moe/hc_pre/CMakeLists.txt
csrc/moe/hc_pre/op_host/CMakeLists.txt
csrc/moe/hc_pre/op_host/hc_pre_def.cpp
csrc/moe/hc_pre/op_host/hc_pre_proto.cpp
csrc/moe/hc_pre/op_host/hc_pre_tiling.cpp
csrc/moe/hc_pre/op_host/hc_pre_tiling.h
csrc/moe/hc_pre/op_host/hc_pre_tiling_arch35.h
csrc/moe/hc_pre/op_kernel/hc_pre.cpp
csrc/moe/hc_pre/op_kernel/hc_pre_base.h
csrc/moe/hc_pre/op_kernel/hc_pre_base_arch35.h
csrc/moe/hc_pre/op_kernel/hc_pre_cube_compute.h
csrc/moe/hc_pre/op_kernel/hc_pre_cube_compute_arch35.h
csrc/moe/hc_pre/op_kernel/hc_pre_m_k_split_core.h
csrc/moe/hc_pre/op_kernel/hc_pre_m_k_split_core_arch35.h
csrc/moe/hc_pre/op_kernel/hc_pre_m_split_core_arch35.h
csrc/moe/hc_pre_inv_rms/CMakeLists.txt
csrc/moe/hc_pre_inv_rms/op_host/CMakeLists.txt
csrc/moe/hc_pre_inv_rms/op_host/hc_pre_inv_rms_def.cpp
csrc/moe/hc_pre_inv_rms/op_host/hc_pre_inv_rms_proto.cpp
csrc/moe/hc_pre_inv_rms/op_host/hc_pre_inv_rms_tiling.cpp
csrc/moe/hc_pre_inv_rms/op_host/hc_pre_inv_rms_tiling.h
csrc/moe/hc_pre_inv_rms/op_host/hc_pre_inv_rms_tiling_arch35.h
csrc/moe/hc_pre_inv_rms/op_host/hc_pre_inv_rms_tiling_large_d.h
csrc/moe/hc_pre_inv_rms/op_kernel/hc_pre_inv_rms.cpp
csrc/moe/hc_pre_inv_rms/op_kernel/hc_pre_inv_rms_full_load.h
csrc/moe/hc_pre_inv_rms/op_kernel/hc_pre_inv_rms_full_load_large_d.h
csrc/moe/hc_pre_inv_rms/op_kernel/hc_pre_inv_rms_full_load_regbase.h
csrc/moe/hc_pre_sinkhorn/CMakeLists.txt
csrc/moe/hc_pre_sinkhorn/op_host/CMakeLists.txt
csrc/moe/hc_pre_sinkhorn/op_host/hc_pre_sinkhorn_def.cpp
csrc/moe/hc_pre_sinkhorn/op_host/hc_pre_sinkhorn_proto.cpp
csrc/moe/hc_pre_sinkhorn/op_host/hc_pre_sinkhorn_tiling.cpp
csrc/moe/hc_pre_sinkhorn/op_host/hc_pre_sinkhorn_tiling.h
csrc/moe/hc_pre_sinkhorn/op_kernel/hc_pre_sinkhorn.cpp
csrc/moe/hc_pre_sinkhorn/op_kernel/hc_pre_sinkhorn_base.h
csrc/moe/hc_pre_sinkhorn/op_kernel/hc_pre_sinkhorn_perf.h
csrc/moe/hc_pre_sinkhorn/op_kernel/hc_pre_sinkhorn_regbase_base.h
csrc/moe/hc_pre_sinkhorn/op_kernel/hc_pre_sinkhorn_regbase_perf.h
csrc/moe/moe_gating_top_k/CMakeLists.txt
csrc/moe/moe_gating_top_k/moe_gating_top_k_torch_adpt.h
csrc/moe/moe_gating_top_k/op_host/CMakeLists.txt
csrc/moe/moe_gating_top_k/op_host/math_util.h
csrc/moe/moe_gating_top_k/op_host/moe_gating_top_k_def.cpp
csrc/moe/moe_gating_top_k/op_host/moe_gating_top_k_infershape.cpp
csrc/moe/moe_gating_top_k/op_host/moe_gating_top_k_proto.cpp
csrc/moe/moe_gating_top_k/op_host/moe_gating_top_k_proto.h
csrc/moe/moe_gating_top_k/op_host/moe_gating_top_k_tiling.cpp
csrc/moe/moe_gating_top_k/op_host/moe_gating_top_k_tiling.h
csrc/moe/moe_gating_top_k/op_host/moe_gating_top_k_tiling_arch35.cpp
csrc/moe/moe_gating_top_k/op_host/moe_gating_top_k_tiling_base.cpp
csrc/moe/moe_gating_top_k/op_kernel/common.h
csrc/moe/moe_gating_top_k/op_kernel/error_log.h
csrc/moe/moe_gating_top_k/op_kernel/moe_gating_top_k.cpp
csrc/moe/moe_gating_top_k/op_kernel/moe_gating_top_k_apt.cpp
csrc/moe/moe_gating_top_k/op_kernel/moe_gating_top_k_e_k_fullload.h
csrc/moe/moe_gating_top_k/op_kernel/moe_gating_top_k_generalized.h
csrc/moe/moe_gating_top_k/op_kernel/moe_gating_top_k_without_group.h
csrc/moe/moe_gating_top_k_hash/CMakeLists.txt
csrc/moe/moe_gating_top_k_hash/op_host/CMakeLists.txt
csrc/moe/moe_gating_top_k_hash/op_host/moe_gating_top_k_hash_def.cpp
csrc/moe/moe_gating_top_k_hash/op_host/moe_gating_top_k_hash_proto.cpp
csrc/moe/moe_gating_top_k_hash/op_host/moe_gating_top_k_hash_tiling.cpp
csrc/moe/moe_gating_top_k_hash/op_host/moe_gating_top_k_hash_tiling.h
csrc/moe/moe_gating_top_k_hash/op_host/moe_gating_top_k_hash_tiling_arch35.h
csrc/moe/moe_gating_top_k_hash/op_kernel/common.h
csrc/moe/moe_gating_top_k_hash/op_kernel/common_regbase.h
csrc/moe/moe_gating_top_k_hash/op_kernel/moe_gating_top_k_hash.cpp
csrc/moe/moe_gating_top_k_hash/op_kernel/moe_gating_top_k_hash_e_k_fullload.h
csrc/moe/moe_gating_top_k_hash/op_kernel/moe_gating_top_k_hash_generalized.h
csrc/moe/moe_gating_top_k_hash/op_kernel/moe_gating_top_k_hash_regbase.h
csrc/moe/moe_gating_top_k_hash/op_kernel/moe_gating_top_k_hash_without_group.h
csrc/moe/moe_gating_top_k_hash/op_kernel/arch35/common.h
csrc/moe/moe_gating_top_k_hash/op_kernel/arch35/moe_gating_top_k_hash_regbase.h
csrc/moe/moe_grouped_matmul/CMakeLists.txt
csrc/moe/moe_grouped_matmul/op_host/CMakeLists.txt
csrc/moe/moe_grouped_matmul/op_host/moe_grouped_matmul_cpu.cpp
csrc/moe/moe_grouped_matmul/op_host/moe_grouped_matmul_def.cpp
csrc/moe/moe_grouped_matmul/op_host/moe_grouped_matmul_infershape.cpp
csrc/moe/moe_grouped_matmul/op_host/moe_grouped_matmul_tiling.h
csrc/moe/moe_grouped_matmul/op_host/op_api/aclnn_moe_grouped_matmul.cpp
csrc/moe/moe_grouped_matmul/op_host/op_api/aclnn_moe_grouped_matmul.h
csrc/moe/moe_grouped_matmul/op_host/op_api/aclnn_moe_grouped_matmul_weight_nz.h
csrc/moe/moe_grouped_matmul/op_host/op_api/moe_grouped_matmul_l0.cpp
csrc/moe/moe_grouped_matmul/op_host/op_api/moe_grouped_matmul_l0.h
csrc/moe/moe_grouped_matmul/op_kernel/moe_grouped_matmul.cpp
csrc/moe/moe_grouped_matmul/op_kernel/moe_grouped_matmul.h
csrc/moe/moe_grouped_matmul/op_kernel/moe_grouped_matmul_tiling_data.h
csrc/moe/moe_init_routing_custom/CMakeLists.txt
csrc/moe/moe_init_routing_custom/moe_init_routing_custom_torch_adpt.h
csrc/moe/moe_init_routing_custom/op_host/CMakeLists.txt
csrc/moe/moe_init_routing_custom/op_host/aclnn_moe_init_routing_custom.cpp
csrc/moe/moe_init_routing_custom/op_host/aclnn_moe_init_routing_custom.h
csrc/moe/moe_init_routing_custom/op_host/moe_init_routing_custom.cpp
csrc/moe/moe_init_routing_custom/op_host/moe_init_routing_custom.h
csrc/moe/moe_init_routing_custom/op_host/moe_init_routing_custom_def.cpp
csrc/moe/moe_init_routing_custom/op_host/moe_init_routing_custom_infershape.cpp
csrc/moe/moe_init_routing_custom/op_host/moe_init_routing_custom_tiling.cpp
csrc/moe/moe_init_routing_custom/op_host/moe_init_routing_custom_tiling.h
csrc/moe/moe_init_routing_custom/op_host/moe_init_routing_custom_tiling_base.cpp
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_common.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_expert_tokens_count.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_full_load.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_full_load_base.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_full_load_dynamic_quant.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_full_load_static_quant.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_full_load_unquantized.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_gather_droppad_static_quant.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_gather_dynamic_quant.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_gather_out.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_gather_out_droppad.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_gather_sort_multi_core.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_gather_static_quant.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_mrgsort.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_mrgsort_out.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_mrgsort_out_performance.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_mrgsort_performance.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_row_idx_gather.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_row_idx_gather_droppad.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_row_idx_gather_droppad_dynamic.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_sort_actual_expert.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_sort_base.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_sort_multi_core.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_sort_multi_core_performance.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_custom_sort_one_core.h
csrc/moe/moe_init_routing_custom/op_kernel/moe_init_routing_custom.cpp
csrc/moe/scatter_nd_update_v2/CMakeLists.txt
csrc/moe/scatter_nd_update_v2/op_host/CMakeLists.txt
csrc/moe/scatter_nd_update_v2/op_host/scatter_nd_update_infershape.cpp
csrc/moe/scatter_nd_update_v2/op_host/scatter_nd_update_v2_def.cpp
csrc/moe/scatter_nd_update_v2/op_host/scatter_nd_update_v2_tiling.cpp
csrc/moe/scatter_nd_update_v2/op_host/scatter_nd_update_v2_tiling.h
csrc/moe/scatter_nd_update_v2/op_host/config/ascend910_93/scatter_nd_update_v2_binary.json
csrc/moe/scatter_nd_update_v2/op_host/config/ascend910_93/scatter_nd_update_v2_simplified_key.ini
csrc/moe/scatter_nd_update_v2/op_host/config/ascend910b/scatter_nd_update_v2_binary.json
csrc/moe/scatter_nd_update_v2/op_host/config/ascend910b/scatter_nd_update_v2_simplified_key.ini
csrc/moe/scatter_nd_update_v2/op_host/op_api/aclnn_scatter_nd_update_v2.cpp
csrc/moe/scatter_nd_update_v2/op_host/op_api/aclnn_scatter_nd_update_v2.h
csrc/moe/scatter_nd_update_v2/op_host/op_api/scatter_nd_update_v2.cpp
csrc/moe/scatter_nd_update_v2/op_host/op_api/scatter_nd_update_v2.h
csrc/moe/scatter_nd_update_v2/op_kernel/scatter_nd_update_common.h
csrc/moe/scatter_nd_update_v2/op_kernel/scatter_nd_update_large_index.h
csrc/moe/scatter_nd_update_v2/op_kernel/scatter_nd_update_linear_index.h
csrc/moe/scatter_nd_update_v2/op_kernel/scatter_nd_update_no_sort.h
csrc/moe/scatter_nd_update_v2/op_kernel/scatter_nd_update_v2.cpp
csrc/moe/scatter_nd_update_v2/op_kernel/scatter_nd_update_v2.h
csrc/moe/swiglu_group_quant/CMakeLists.txt
csrc/moe/swiglu_group_quant/op_host/CMakeLists.txt
csrc/moe/swiglu_group_quant/op_host/swiglu_group_quant_def.cpp
csrc/moe/swiglu_group_quant/op_host/swiglu_group_quant_proto.cpp
csrc/moe/swiglu_group_quant/op_host/swiglu_group_quant_tiling.cpp
csrc/moe/swiglu_group_quant/op_host/swiglu_group_quant_tiling.h
csrc/moe/swiglu_group_quant/op_kernel/swiglu_fp8_quant_per_token.h
csrc/moe/swiglu_group_quant/op_kernel/swiglu_group_quant.cpp
csrc/moe/swiglu_group_quant/op_kernel/swiglu_group_quant_base.h
csrc/moe/swiglu_group_quant/op_kernel/swiglu_group_quant_perf.h
csrc/moe/swiglu_group_quant/op_kernel/swiglu_mx_quant_perf.h
csrc/moe/transpose_kv_cache_by_block/CMakeLists.txt
csrc/moe/transpose_kv_cache_by_block/op_host/CMakeLists.txt
csrc/moe/transpose_kv_cache_by_block/op_host/transpose_kv_cache_by_block_def.cpp
csrc/moe/transpose_kv_cache_by_block/op_host/transpose_kv_cache_by_block_proto.cpp
csrc/moe/transpose_kv_cache_by_block/op_host/transpose_kv_cache_by_block_tiling.cpp
csrc/moe/transpose_kv_cache_by_block/op_host/transpose_kv_cache_by_block_tiling.h
csrc/moe/transpose_kv_cache_by_block/op_kernel/common.h
csrc/moe/transpose_kv_cache_by_block/op_kernel/full_load.h
csrc/moe/transpose_kv_cache_by_block/op_kernel/general.h
csrc/moe/transpose_kv_cache_by_block/op_kernel/transpose_kv_cache_by_block.cpp
csrc/scripts/opgen/opgen_standalone.py
csrc/scripts/opgen/template/CMakeLists.txt
csrc/scripts/opgen/template/add/CMakeLists.txt
csrc/scripts/opgen/template/add/examples/test_aclnn_add_example.cpp
csrc/scripts/opgen/template/add/op_host/CMakeLists.txt
csrc/scripts/opgen/template/add/op_host/add_example_def.cpp
csrc/scripts/opgen/template/add/op_host/add_example_infershape.cpp
csrc/scripts/opgen/template/add/op_host/add_example_tiling.cpp
csrc/scripts/opgen/template/add/op_kernel/add_example.cpp
csrc/scripts/opgen/template/add/op_kernel/add_example.h
csrc/scripts/opgen/template/add/op_kernel/add_example_tiling_data.h
csrc/scripts/opgen/template/add/op_kernel/add_example_tiling_key.h
csrc/scripts/opgen/template/add/tests/ut/.gitkeep
csrc/scripts/package/package.py
csrc/scripts/package/common/__init__.py
csrc/scripts/package/common/cfg/path.cfg
csrc/scripts/package/common/py/__init__.py
csrc/scripts/package/common/py/filelist.py
csrc/scripts/package/common/py/merge_binary_info_config.py
csrc/scripts/package/common/py/packer.py
csrc/scripts/package/common/py/pkg_parser.py
csrc/scripts/package/common/py/version_info.py
csrc/scripts/package/common/py/utils/comm_log.py
csrc/scripts/package/common/py/utils/funcbase.py
csrc/scripts/package/common/py/utils/pkg_utils.py
csrc/scripts/package/common/sh/check_version_required.awk
csrc/scripts/package/common/sh/cleanup.sh
csrc/scripts/package/common/sh/common_func.inc
csrc/scripts/package/common/sh/common_func_v2.inc
csrc/scripts/package/common/sh/common_installer.inc
csrc/scripts/package/common/sh/common_interface.csh
csrc/scripts/package/common/sh/common_interface.fish
csrc/scripts/package/common/sh/common_interface.sh
csrc/scripts/package/common/sh/install_common_parser.sh
csrc/scripts/package/common/sh/multi_version.inc
csrc/scripts/package/common/sh/script_operator.inc
csrc/scripts/package/common/sh/version_cfg.inc
csrc/scripts/package/common/sh/version_compatiable.inc
csrc/scripts/package/latest_manager/scripts/filelist.csv
csrc/scripts/package/latest_manager/scripts/install.sh
csrc/scripts/package/latest_manager/scripts/manager.sh
csrc/scripts/package/latest_manager/scripts/manager_func.sh
csrc/scripts/package/latest_manager/scripts/uninstall.sh
csrc/scripts/package/latest_manager/scripts/version.info
csrc/scripts/package/module/ascend/EngineeringCommon.xml
csrc/scripts/package/module/ascend/EngineeringFiles.xml
csrc/scripts/package/module/ascend/OpsTransformer.xml
csrc/scripts/package/module/ascend/OpsTransformerInc.xml
csrc/scripts/package/ops_transformer/ops_transformer.xml
csrc/scripts/package/ops_transformer/scripts/cleanup.sh
csrc/scripts/package/ops_transformer/scripts/help.info
csrc/scripts/package/ops_transformer/scripts/install.sh
csrc/scripts/package/ops_transformer/scripts/opp_common.sh
csrc/scripts/package/ops_transformer/scripts/opp_custom_install.sh
csrc/scripts/package/ops_transformer/scripts/opp_custom_uninstall.sh
csrc/scripts/package/ops_transformer/scripts/opp_install.sh
csrc/scripts/package/ops_transformer/scripts/opp_uninstall.sh
csrc/scripts/package/ops_transformer/scripts/uninstall.sh
csrc/scripts/package/ops_transformer/scripts/ver_check.sh
csrc/scripts/package/ops_transformer/scripts/empty_package_scripts/cleanup.sh
csrc/scripts/package/ops_transformer/scripts/empty_package_scripts/install.sh
csrc/scripts/util/__init__.py
csrc/scripts/util/build_opp_kernel_static.py
csrc/scripts/util/const_var.py
csrc/scripts/util/insert_op_info.py
csrc/scripts/util/merge_aicpu_info_json.sh
csrc/scripts/util/merge_proto.py
csrc/scripts/util/modify_gen_aclnn.py
csrc/third_party/catlass/.clang-format
csrc/third_party/catlass/.gitignore
csrc/third_party/catlass/.gitmodules
csrc/third_party/catlass/CHANGELOG.md
csrc/third_party/catlass/CMakeLists.txt
csrc/third_party/catlass/CONTRIBUTING.md
csrc/third_party/catlass/LICENSE
csrc/third_party/catlass/OAT.xml
csrc/third_party/catlass/OWNERS
csrc/third_party/catlass/README.md
csrc/third_party/catlass/SECURITYNOTE.md
csrc/third_party/catlass/Third_Party_Open_Source_Software_List.yaml
csrc/third_party/catlass/Third_Party_Open_Source_Software_Notice
csrc/third_party/catlass/.gitcode/PULL_REQUEST_TEMPLATE.zh-CN.md
csrc/third_party/catlass/.gitcode/ISSUE_TEMPLATE/bug-report.yml
csrc/third_party/catlass/.gitcode/ISSUE_TEMPLATE/documentation.yml
csrc/third_party/catlass/.gitcode/ISSUE_TEMPLATE/feature-request.yml
csrc/third_party/catlass/.gitcode/ISSUE_TEMPLATE/question.yml
csrc/third_party/catlass/3rdparty/CMakeLists.txt
csrc/third_party/catlass/3rdparty/googletest/.clang-format
csrc/third_party/catlass/3rdparty/googletest/.gitignore
csrc/third_party/catlass/3rdparty/googletest/BUILD.bazel
csrc/third_party/catlass/3rdparty/googletest/CMakeLists.txt
csrc/third_party/catlass/3rdparty/googletest/CONTRIBUTING.md
csrc/third_party/catlass/3rdparty/googletest/CONTRIBUTORS
csrc/third_party/catlass/3rdparty/googletest/LICENSE
csrc/third_party/catlass/3rdparty/googletest/README.md
csrc/third_party/catlass/3rdparty/googletest/WORKSPACE
csrc/third_party/catlass/3rdparty/googletest/googletest_deps.bzl
csrc/third_party/catlass/3rdparty/googletest/.github/ISSUE_TEMPLATE/00-bug_report.yml
csrc/third_party/catlass/3rdparty/googletest/.github/ISSUE_TEMPLATE/10-feature_request.yml
csrc/third_party/catlass/3rdparty/googletest/.github/ISSUE_TEMPLATE/config.yml
csrc/third_party/catlass/3rdparty/googletest/.github/workflows/gtest-ci.yml
csrc/third_party/catlass/3rdparty/googletest/ci/linux-presubmit.sh
csrc/third_party/catlass/3rdparty/googletest/ci/macos-presubmit.sh
csrc/third_party/catlass/3rdparty/googletest/ci/windows-presubmit.bat
csrc/third_party/catlass/3rdparty/googletest/docs/_config.yml
csrc/third_party/catlass/3rdparty/googletest/docs/advanced.md
csrc/third_party/catlass/3rdparty/googletest/docs/community_created_documentation.md
csrc/third_party/catlass/3rdparty/googletest/docs/faq.md
csrc/third_party/catlass/3rdparty/googletest/docs/gmock_cheat_sheet.md
csrc/third_party/catlass/3rdparty/googletest/docs/gmock_cook_book.md
csrc/third_party/catlass/3rdparty/googletest/docs/gmock_faq.md
csrc/third_party/catlass/3rdparty/googletest/docs/gmock_for_dummies.md
csrc/third_party/catlass/3rdparty/googletest/docs/index.md
csrc/third_party/catlass/3rdparty/googletest/docs/pkgconfig.md
csrc/third_party/catlass/3rdparty/googletest/docs/platforms.md
csrc/third_party/catlass/3rdparty/googletest/docs/primer.md
csrc/third_party/catlass/3rdparty/googletest/docs/quickstart-bazel.md
csrc/third_party/catlass/3rdparty/googletest/docs/quickstart-cmake.md
csrc/third_party/catlass/3rdparty/googletest/docs/samples.md
csrc/third_party/catlass/3rdparty/googletest/docs/_data/navigation.yml
csrc/third_party/catlass/3rdparty/googletest/docs/_layouts/default.html
csrc/third_party/catlass/3rdparty/googletest/docs/_sass/main.scss
csrc/third_party/catlass/3rdparty/googletest/docs/assets/css/style.scss
csrc/third_party/catlass/3rdparty/googletest/docs/reference/actions.md
csrc/third_party/catlass/3rdparty/googletest/docs/reference/assertions.md
csrc/third_party/catlass/3rdparty/googletest/docs/reference/matchers.md
csrc/third_party/catlass/3rdparty/googletest/docs/reference/mocking.md
csrc/third_party/catlass/3rdparty/googletest/docs/reference/testing.md
csrc/third_party/catlass/3rdparty/googletest/googlemock/CMakeLists.txt
csrc/third_party/catlass/3rdparty/googletest/googlemock/README.md
csrc/third_party/catlass/3rdparty/googletest/googlemock/cmake/gmock.pc.in
csrc/third_party/catlass/3rdparty/googletest/googlemock/cmake/gmock_main.pc.in
csrc/third_party/catlass/3rdparty/googletest/googlemock/docs/README.md
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/gmock-actions.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/gmock-cardinalities.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/gmock-function-mocker.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/gmock-matchers.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/gmock-more-actions.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/gmock-more-matchers.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/gmock-nice-strict.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/gmock-spec-builders.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/gmock.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/internal/gmock-internal-utils.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/internal/gmock-port.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/internal/gmock-pp.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/internal/custom/README.md
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/internal/custom/gmock-generated-actions.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/internal/custom/gmock-matchers.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/include/gmock/internal/custom/gmock-port.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/src/gmock-all.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/src/gmock-cardinalities.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/src/gmock-internal-utils.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/src/gmock-matchers.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/src/gmock-spec-builders.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/src/gmock.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/src/gmock_main.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/BUILD.bazel
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-actions_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-cardinalities_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-function-mocker_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-internal-utils_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-matchers-arithmetic_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-matchers-comparisons_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-matchers-containers_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-matchers-misc_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-matchers_test.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-more-actions_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-nice-strict_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-port_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-pp-string_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-pp_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock-spec-builders_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_all_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_ex_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_leak_test.py
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_leak_test_.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_link2_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_link_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_link_test.h
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_output_test.py
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_output_test_.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_output_test_golden.txt
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_stress_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_test.cc
csrc/third_party/catlass/3rdparty/googletest/googlemock/test/gmock_test_utils.py
csrc/third_party/catlass/3rdparty/googletest/googletest/CMakeLists.txt
csrc/third_party/catlass/3rdparty/googletest/googletest/README.md
csrc/third_party/catlass/3rdparty/googletest/googletest/cmake/Config.cmake.in
csrc/third_party/catlass/3rdparty/googletest/googletest/cmake/gtest.pc.in
csrc/third_party/catlass/3rdparty/googletest/googletest/cmake/gtest_main.pc.in
csrc/third_party/catlass/3rdparty/googletest/googletest/cmake/internal_utils.cmake
csrc/third_party/catlass/3rdparty/googletest/googletest/cmake/libgtest.la.in
csrc/third_party/catlass/3rdparty/googletest/googletest/docs/README.md
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest-assertion-result.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest-death-test.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest-matchers.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest-message.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest-param-test.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest-printers.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest-spi.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest-test-part.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest-typed-test.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest_pred_impl.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/gtest_prod.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/gtest-death-test-internal.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/gtest-filepath.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/gtest-internal.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/gtest-param-util.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/gtest-port-arch.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/gtest-port.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/gtest-string.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/gtest-type-util.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/custom/README.md
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/custom/gtest-port.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/custom/gtest-printers.h
csrc/third_party/catlass/3rdparty/googletest/googletest/include/gtest/internal/custom/gtest.h
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/prime_tables.h
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample1.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample1.h
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample10_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample1_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample2.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample2.h
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample2_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample3-inl.h
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample3_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample4.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample4.h
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample4_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample5_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample6_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample7_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample8_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/samples/sample9_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest-all.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest-assertion-result.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest-death-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest-filepath.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest-internal-inl.h
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest-matchers.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest-port.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest-printers.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest-test-part.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest-typed-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/src/gtest_main.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/BUILD.bazel
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-break-on-failure-unittest.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-break-on-failure-unittest_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-catch-exceptions-test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-catch-exceptions-test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-color-test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-color-test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-death-test-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-death-test_ex_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-env-var-test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-env-var-test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-failfast-unittest.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-failfast-unittest_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-filepath-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-filter-unittest.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-filter-unittest_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-global-environment-unittest.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-global-environment-unittest_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-json-outfiles-test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-json-output-unittest.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-list-tests-unittest.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-list-tests-unittest_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-listener-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-message-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-options-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-output-test-golden-lin.txt
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-output-test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-output-test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-param-test-invalid-name1-test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-param-test-invalid-name1-test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-param-test-invalid-name2-test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-param-test-invalid-name2-test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-param-test-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-param-test-test.h
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-param-test2-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-port-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-printers-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-setuptestsuite-test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-setuptestsuite-test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-shuffle-test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-shuffle-test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-test-part-test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-throw-on-failure-test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-throw-on-failure-test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-uninitialized-test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/googletest-uninitialized-test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest-typed-test2_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest-typed-test_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest-typed-test_test.h
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest-unittest-api_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_all_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_assert_by_exception_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_dirs_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_environment_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_help_test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_help_test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_json_test_utils.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_list_output_unittest.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_list_output_unittest_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_main_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_no_test_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_pred_impl_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_premature_exit_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_prod_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_repeat_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_skip_check_output_test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_skip_environment_check_output_test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_skip_in_environment_setup_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_skip_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_sole_header_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_stress_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_test_macro_stack_footprint_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_test_utils.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_testbridge_test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_testbridge_test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_throw_on_failure_ex_test.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_unittest.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_xml_outfile1_test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_xml_outfile2_test_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_xml_outfiles_test.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_xml_output_unittest.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_xml_output_unittest_.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/gtest_xml_test_utils.py
csrc/third_party/catlass/3rdparty/googletest/googletest/test/production.cc
csrc/third_party/catlass/3rdparty/googletest/googletest/test/production.h
csrc/third_party/catlass/docs/Q&A.md
csrc/third_party/catlass/docs/README.md
csrc/third_party/catlass/docs/1_Practice/01_quick_start.md
csrc/third_party/catlass/docs/1_Practice/02_host_example_assembly.md
csrc/third_party/catlass/docs/1_Practice/08_evaluation.md
csrc/third_party/catlass/docs/1_Practice/10_matmul_optimization.md
csrc/third_party/catlass/docs/1_Practice/evaluation_tools/ascendc_dump.md
csrc/third_party/catlass/docs/1_Practice/evaluation_tools/msdebug.md
csrc/third_party/catlass/docs/1_Practice/evaluation_tools/performance_tools.md
csrc/third_party/catlass/docs/1_Practice/evaluation_tools/print.md
csrc/third_party/catlass/docs/2_Design/00_project_overview.md
csrc/third_party/catlass/docs/2_Design/01_kernel_design/01_example_design.md
csrc/third_party/catlass/docs/2_Design/01_kernel_design/02_swizzle.md
csrc/third_party/catlass/docs/2_Design/01_kernel_design/03_dispatch_policies.md
csrc/third_party/catlass/docs/2_Design/01_kernel_design/04_matmul_summary.md
csrc/third_party/catlass/docs/2_Design/01_kernel_design/05_aswt.md
csrc/third_party/catlass/docs/2_Design/02_tla/01_layout.md
csrc/third_party/catlass/docs/2_Design/02_tla/02_layout_tag.md
csrc/third_party/catlass/docs/2_Design/02_tla/03_tensor.md
csrc/third_party/catlass/docs/3_API/README.md
csrc/third_party/catlass/docs/3_API/gemm_api.md
csrc/third_party/catlass/docs/3_API/include/catlass/epilogue/block/README.md
csrc/third_party/catlass/docs/3_API/include/catlass/epilogue/block/block_epilogue.md
csrc/third_party/catlass/docs/3_API/include/catlass/epilogue/block/block_epilogue_per_token_dequant.md
csrc/third_party/catlass/docs/3_API/include/catlass/epilogue/tile/README.md
csrc/third_party/catlass/docs/3_API/include/catlass/gemm/block/README.md
csrc/third_party/catlass/docs/3_API/include/catlass/gemm/block/block_mmad.md
csrc/third_party/catlass/docs/3_API/include/catlass/gemm/block/block_mmad_pingpong.md
csrc/third_party/catlass/docs/3_API/include/catlass/gemm/block/block_swizzle/GemmIdentityBlockSwizzle.md
csrc/third_party/catlass/docs/3_API/include/catlass/gemm/block/block_swizzle/block_swizzle.md
csrc/third_party/catlass/docs/3_API/include/catlass/gemm/kernel/README.md
csrc/third_party/catlass/docs/3_API/include/catlass/gemm/kernel/basic_matmul.md
csrc/third_party/catlass/docs/3_API/include/catlass/gemm/tile/README.md
csrc/third_party/catlass/docs/3_API/include/catlass/gemm/tile/copy_gm_to_l1.md
csrc/third_party/catlass/docs/3_API/include/catlass/gemm/tile/tile_copy.md
csrc/third_party/catlass/docs/3_API/include/catlass/gemm/tile/tile_mmad.md
csrc/third_party/catlass/docs/3_API/include/tla/README.md
csrc/third_party/catlass/docs/figures/api_custom.png
csrc/third_party/catlass/docs/figures/api_level.png
csrc/third_party/catlass/docs/figures/aswt.png
csrc/third_party/catlass/docs/figures/fixpipe-opti.png
csrc/third_party/catlass/docs/figures/fixpipe_dequant.png
csrc/third_party/catlass/docs/figures/fixpipe_quant.png
csrc/third_party/catlass/docs/figures/flash_attention_infer_cv_pipeline.png
csrc/third_party/catlass/docs/figures/flash_attention_infer_operator.png
csrc/third_party/catlass/docs/figures/homepage_perf_gmm.png
csrc/third_party/catlass/docs/figures/homepage_perf_mm.png
csrc/third_party/catlass/docs/figures/split_k_matmul.png
csrc/third_party/catlass/docs/figures/swizzle10.png
csrc/third_party/catlass/docs/figures/swizzle30.png
csrc/third_party/catlass/docs/figures/swizzle31.png
csrc/third_party/catlass/docs/figures/catlass_optimize_guidance/swizzle_case.png
csrc/third_party/catlass/examples/CMakeLists.txt
csrc/third_party/catlass/examples/00_basic_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/00_basic_matmul/README.md
csrc/third_party/catlass/examples/00_basic_matmul/basic_matmul.cpp
csrc/third_party/catlass/examples/01_batched_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/01_batched_matmul/README.md
csrc/third_party/catlass/examples/01_batched_matmul/batched_matmul.cpp
csrc/third_party/catlass/examples/02_grouped_matmul_slice_m/CMakeLists.txt
csrc/third_party/catlass/examples/02_grouped_matmul_slice_m/README.md
csrc/third_party/catlass/examples/02_grouped_matmul_slice_m/grouped_matmul_slice_m.cpp
csrc/third_party/catlass/examples/03_matmul_add/CMakeLists.txt
csrc/third_party/catlass/examples/03_matmul_add/README.md
csrc/third_party/catlass/examples/03_matmul_add/matmul_add.cpp
csrc/third_party/catlass/examples/04_padding_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/04_padding_matmul/README.md
csrc/third_party/catlass/examples/04_padding_matmul/padding_matmul.cpp
csrc/third_party/catlass/examples/05_grouped_matmul_slice_k/CMakeLists.txt
csrc/third_party/catlass/examples/05_grouped_matmul_slice_k/README.md
csrc/third_party/catlass/examples/05_grouped_matmul_slice_k/grouped_matmul_slice_k.cpp
csrc/third_party/catlass/examples/06_optimized_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/06_optimized_matmul/README.md
csrc/third_party/catlass/examples/06_optimized_matmul/optimized_matmul.cpp
csrc/third_party/catlass/examples/07_grouped_matmul_slice_m_per_token_dequant_moe/CMakeLists.txt
csrc/third_party/catlass/examples/07_grouped_matmul_slice_m_per_token_dequant_moe/README.md
csrc/third_party/catlass/examples/07_grouped_matmul_slice_m_per_token_dequant_moe/grouped_matmul_slice_m_per_token_dequant_moe.cpp
csrc/third_party/catlass/examples/08_grouped_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/08_grouped_matmul/README.md
csrc/third_party/catlass/examples/08_grouped_matmul/grouped_matmul.cpp
csrc/third_party/catlass/examples/09_splitk_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/09_splitk_matmul/README.md
csrc/third_party/catlass/examples/09_splitk_matmul/splitk_matmul.cpp
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/.gitignore
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/README.md
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/dynamic_optimized_matmul.cpp
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/doc/CommonMatmul.md
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/doc/MultiCoreSplitkMatmul.md
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/doc/SingleCoreSplitkMatmul.md
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/doc/StreamkMatmul.md
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/doc/工程结构介绍.md
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/aiv_matmul_kernel.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/common_matmul_kernel.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/kernel_utils.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/local_padding_c_padding_common_matmul_kernel.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/padding_common_matmul_kernel.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/padding_multi_core_splitk_matmul_kernel.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/padding_single_core_splitk_for_small_k_matmul_kernel.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/padding_single_core_splitk_k_loop_middle_matmul_kernel.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/padding_single_core_splitk_k_loop_outer_matmul_kernel.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/padding_streamk_matmul_kernel.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/single_core_splitk_for_small_k_matmul_kernel.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/kernel/small_matmul_kernel.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/wrapper_code_gen.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/aiv_matmul_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/common_matmul_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/launch_map_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/local_padding_c_padding_common_matmul_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/padding_common_matmul_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/padding_multi_core_splitk_matmul_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/padding_single_core_splitk_for_small_k_matmul_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/padding_single_core_splitk_k_loop_middle_matmul_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/padding_single_core_splitk_k_loop_outer_matmul_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/padding_streamk_matmul_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/single_core_splitk_for_small_k_matmul_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/templates/small_matmul_template.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/impl/scripts/utils/config.py
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/include/do_tiling_b16.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/include/dynamic_optimized_matmul.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/include/platform_info.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/include/select_kernel_b16.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/include/tiling_params.h
csrc/third_party/catlass/examples/102_dynamic_optimized_matmul/include/utils.h
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/CMakeLists.txt
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/README.md
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/dynamic_optimized_quant_matmul_per_token_basic.cpp
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/impl/kernel/kernel_utils.h
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/impl/kernel/per_token_matmul_kernel.h
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/impl/scripts/wrapper_code_gen.py
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/impl/scripts/templates/launch_map_template.py
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/impl/scripts/templates/per_token_matmul_template.py
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/impl/scripts/utils/config.py
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/include/do_tiling_b8.h
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/include/dynamic_optimized_matmul_w8a8.h
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/include/platform_info.h
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/include/select_kernel_b8.h
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/include/tiling_params.h
csrc/third_party/catlass/examples/103_dynamic_optimized_quant_matmul_per_token_basic/include/utils.h
csrc/third_party/catlass/examples/10_grouped_matmul_slice_m_per_token_dequant/10_grouped_matmul_slice_m_per_token_dequant.md
csrc/third_party/catlass/examples/10_grouped_matmul_slice_m_per_token_dequant/CMakeLists.txt
csrc/third_party/catlass/examples/10_grouped_matmul_slice_m_per_token_dequant/README.md
csrc/third_party/catlass/examples/10_grouped_matmul_slice_m_per_token_dequant/grouped_matmul_slice_m_per_token_dequant.cpp
csrc/third_party/catlass/examples/11_grouped_matmul_slice_k_per_token_dequant/CMakeLists.txt
csrc/third_party/catlass/examples/11_grouped_matmul_slice_k_per_token_dequant/README.md
csrc/third_party/catlass/examples/11_grouped_matmul_slice_k_per_token_dequant/grouped_matmul_slice_k_per_token_dequant.cpp
csrc/third_party/catlass/examples/12_quant_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/12_quant_matmul/README.md
csrc/third_party/catlass/examples/12_quant_matmul/quant_matmul.cpp
csrc/third_party/catlass/examples/13_basic_matmul_tla/CMakeLists.txt
csrc/third_party/catlass/examples/13_basic_matmul_tla/README.md
csrc/third_party/catlass/examples/13_basic_matmul_tla/basic_matmul_tla.cpp
csrc/third_party/catlass/examples/14_optimized_matmul_tla/CMakeLists.txt
csrc/third_party/catlass/examples/14_optimized_matmul_tla/README.md
csrc/third_party/catlass/examples/14_optimized_matmul_tla/optimized_matmul_tla.cpp
csrc/third_party/catlass/examples/15_gemm/CMakeLists.txt
csrc/third_party/catlass/examples/15_gemm/README.md
csrc/third_party/catlass/examples/15_gemm/gemm.cpp
csrc/third_party/catlass/examples/16_group_gemm/CMakeLists.txt
csrc/third_party/catlass/examples/16_group_gemm/README.md
csrc/third_party/catlass/examples/16_group_gemm/group_gemm.cpp
csrc/third_party/catlass/examples/17_gemv_aiv/CMakeLists.txt
csrc/third_party/catlass/examples/17_gemv_aiv/README.md
csrc/third_party/catlass/examples/17_gemv_aiv/gemv_aiv.cpp
csrc/third_party/catlass/examples/18_gemv_aic/CMakeLists.txt
csrc/third_party/catlass/examples/18_gemv_aic/README.md
csrc/third_party/catlass/examples/18_gemv_aic/gemv_aic.cpp
csrc/third_party/catlass/examples/19_mla/CMakeLists.txt
csrc/third_party/catlass/examples/19_mla/README.md
csrc/third_party/catlass/examples/19_mla/gen_data.py
csrc/third_party/catlass/examples/19_mla/kernel_common.hpp
csrc/third_party/catlass/examples/19_mla/mla.cpp
csrc/third_party/catlass/examples/19_mla/mla.md
csrc/third_party/catlass/examples/19_mla/mla_kernel.cpp
csrc/third_party/catlass/examples/19_mla/mla_kernel_tp1_spec.cpp
csrc/third_party/catlass/examples/19_mla/mla_tiling.cpp
csrc/third_party/catlass/examples/19_mla/mla_tiling.h
csrc/third_party/catlass/examples/20_matmul_bias/CMakeLists.txt
csrc/third_party/catlass/examples/20_matmul_bias/README.md
csrc/third_party/catlass/examples/20_matmul_bias/matmul_bias.cpp
csrc/third_party/catlass/examples/21_basic_matmul_preload_zN/CMakeLists.txt
csrc/third_party/catlass/examples/21_basic_matmul_preload_zN/README.md
csrc/third_party/catlass/examples/21_basic_matmul_preload_zN/basic_matmul_preload_zN.cpp
csrc/third_party/catlass/examples/22_padding_splitk_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/22_padding_splitk_matmul/README.md
csrc/third_party/catlass/examples/22_padding_splitk_matmul/padding_splitk_matmul.cpp
csrc/third_party/catlass/examples/23_flash_attention_infer/CMakeLists.txt
csrc/third_party/catlass/examples/23_flash_attention_infer/README.md
csrc/third_party/catlass/examples/23_flash_attention_infer/fai.cpp
csrc/third_party/catlass/examples/23_flash_attention_infer/fai_kernel.cpp
csrc/third_party/catlass/examples/23_flash_attention_infer/fai_tiling.cpp
csrc/third_party/catlass/examples/23_flash_attention_infer/gen_data.py
csrc/third_party/catlass/examples/23_flash_attention_infer/kernel_common.hpp
csrc/third_party/catlass/examples/24_conv_bias/CMakeLists.txt
csrc/third_party/catlass/examples/24_conv_bias/README.md
csrc/third_party/catlass/examples/24_conv_bias/conv_bias.cpp
csrc/third_party/catlass/examples/24_conv_bias/gen_data.py
csrc/third_party/catlass/examples/25_matmul_full_loadA/CMakeLists.txt
csrc/third_party/catlass/examples/25_matmul_full_loadA/README.md
csrc/third_party/catlass/examples/25_matmul_full_loadA/matmul_full_loadA.cpp
csrc/third_party/catlass/examples/26_matmul_relu/CMakeLists.txt
csrc/third_party/catlass/examples/26_matmul_relu/README.md
csrc/third_party/catlass/examples/26_matmul_relu/matmul_relu.cpp
csrc/third_party/catlass/examples/27_matmul_gelu/CMakeLists.txt
csrc/third_party/catlass/examples/27_matmul_gelu/README.md
csrc/third_party/catlass/examples/27_matmul_gelu/matmul_gelu.cpp
csrc/third_party/catlass/examples/28_matmul_silu/CMakeLists.txt
csrc/third_party/catlass/examples/28_matmul_silu/README.md
csrc/third_party/catlass/examples/28_matmul_silu/matmul_silu.cpp
csrc/third_party/catlass/examples/29_a2_fp8_e4m3_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/29_a2_fp8_e4m3_matmul/README.md
csrc/third_party/catlass/examples/29_a2_fp8_e4m3_matmul/fp8_matmul.cpp
csrc/third_party/catlass/examples/29_a2_fp8_e4m3_matmul/gen_data.py
csrc/third_party/catlass/examples/30_w8a16_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/30_w8a16_matmul/README.md
csrc/third_party/catlass/examples/30_w8a16_matmul/w8a16_matmul.cpp
csrc/third_party/catlass/examples/31_small_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/31_small_matmul/README.md
csrc/third_party/catlass/examples/31_small_matmul/small_matmul.cpp
csrc/third_party/catlass/examples/32_w4a8_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/32_w4a8_matmul/README.md
csrc/third_party/catlass/examples/32_w4a8_matmul/gen_data.py
csrc/third_party/catlass/examples/32_w4a8_matmul/w4a8.cpp
csrc/third_party/catlass/examples/33_basic_conv2d/CMakeLists.txt
csrc/third_party/catlass/examples/33_basic_conv2d/README.md
csrc/third_party/catlass/examples/33_basic_conv2d/basic_conv2d.cpp
csrc/third_party/catlass/examples/34_single_core_splitk_matmul/34_single_splitk_matmul.md
csrc/third_party/catlass/examples/34_single_core_splitk_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/34_single_core_splitk_matmul/README.md
csrc/third_party/catlass/examples/34_single_core_splitk_matmul/single_core_splitk.cpp
csrc/third_party/catlass/examples/35_w4a8_grouped_matmul_msd/gen_data.py
csrc/third_party/catlass/examples/36_w4a8_matmul_msd/gen_data.py
csrc/third_party/catlass/examples/37_streamk_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/37_streamk_matmul/README.md
csrc/third_party/catlass/examples/37_streamk_matmul/streamk_matmul.cpp
csrc/third_party/catlass/examples/38_w4a4_matmul_per_token_per_channel_dequant/CMakeLists.txt
csrc/third_party/catlass/examples/38_w4a4_matmul_per_token_per_channel_dequant/README.md
csrc/third_party/catlass/examples/38_w4a4_matmul_per_token_per_channel_dequant/gen_data.py
csrc/third_party/catlass/examples/38_w4a4_matmul_per_token_per_channel_dequant/w4a4_matmul_per_token_per_channel_dequant.cpp
csrc/third_party/catlass/examples/39_big_matmul_tla/CMakeLists.txt
csrc/third_party/catlass/examples/39_big_matmul_tla/README.md
csrc/third_party/catlass/examples/39_big_matmul_tla/big_matmul_tla.cpp
csrc/third_party/catlass/examples/40_flash_attention_infer_tla/CMakeLists.txt
csrc/third_party/catlass/examples/40_flash_attention_infer_tla/README.md
csrc/third_party/catlass/examples/40_flash_attention_infer_tla/fai.cpp
csrc/third_party/catlass/examples/40_flash_attention_infer_tla/fai_kernel.cpp
csrc/third_party/catlass/examples/40_flash_attention_infer_tla/fai_tiling.cpp
csrc/third_party/catlass/examples/40_flash_attention_infer_tla/gen_data.py
csrc/third_party/catlass/examples/40_flash_attention_infer_tla/kernel_common.hpp
csrc/third_party/catlass/examples/41_sparse_matmul_tla/CMakeLists.txt
csrc/third_party/catlass/examples/41_sparse_matmul_tla/README.md
csrc/third_party/catlass/examples/41_sparse_matmul_tla/sparse_gen_data.py
csrc/third_party/catlass/examples/41_sparse_matmul_tla/sparse_matmul_tla.cpp
csrc/third_party/catlass/examples/42_quant_optimized_matmul_tla/CMakeLists.txt
csrc/third_party/catlass/examples/42_quant_optimized_matmul_tla/README.md
csrc/third_party/catlass/examples/42_quant_optimized_matmul_tla/quant_optimized_matmul_tla.cpp
csrc/third_party/catlass/examples/43_ascend950_basic_matmul/CMakeLists.txt
csrc/third_party/catlass/examples/43_ascend950_basic_matmul/README.md
csrc/third_party/catlass/examples/43_ascend950_basic_matmul/basic_matmul_tla.cpp
csrc/third_party/catlass/examples/44_quant_matmul_full_loadA_tla/44_quant_matmul_full_loadA_tla.md
csrc/third_party/catlass/examples/44_quant_matmul_full_loadA_tla/CMakeLists.txt
csrc/third_party/catlass/examples/44_quant_matmul_full_loadA_tla/README.md
csrc/third_party/catlass/examples/44_quant_matmul_full_loadA_tla/quant_matmul_full_loadA_tla.cpp
csrc/third_party/catlass/examples/45_strided_batched_matmul_tla/CMakeLists.txt
csrc/third_party/catlass/examples/45_strided_batched_matmul_tla/README.md
csrc/third_party/catlass/examples/45_strided_batched_matmul_tla/strided_batched_matmul_tla.cpp
csrc/third_party/catlass/examples/46_ascend950_matmul_fixpipe_opti/46_ascend950_matmul_fixpipe_opti.md
csrc/third_party/catlass/examples/46_ascend950_matmul_fixpipe_opti/CMakeLists.txt
csrc/third_party/catlass/examples/46_ascend950_matmul_fixpipe_opti/README.md
csrc/third_party/catlass/examples/46_ascend950_matmul_fixpipe_opti/matmul_fixpipe_opti.cpp
csrc/third_party/catlass/examples/47_ascend950_grouped_matmul_slice_m_per_token_dequant/CMakeLists.txt
csrc/third_party/catlass/examples/47_ascend950_grouped_matmul_slice_m_per_token_dequant/README.md
csrc/third_party/catlass/examples/47_ascend950_grouped_matmul_slice_m_per_token_dequant/grouped_matmul_slice_m_per_token_dequant_tla.cpp
csrc/third_party/catlass/examples/48_ascend950_grouped_matmul_slice_m_per_tensor_per_channel_dequant/CMakeLists.txt
csrc/third_party/catlass/examples/48_ascend950_grouped_matmul_slice_m_per_tensor_per_channel_dequant/README.md
csrc/third_party/catlass/examples/48_ascend950_grouped_matmul_slice_m_per_tensor_per_channel_dequant/grouped_matmul_slice_m_per_tensor_per_channel_dequant.cpp
csrc/third_party/catlass/examples/49_ascend950_flash_attention_infer/CMakeLists.txt
csrc/third_party/catlass/examples/49_ascend950_flash_attention_infer/README.md
csrc/third_party/catlass/examples/49_ascend950_flash_attention_infer/fai.cpp
csrc/third_party/catlass/examples/49_ascend950_flash_attention_infer/fai_kernel.h
csrc/third_party/catlass/examples/49_ascend950_flash_attention_infer/fai_kernel_utils.h
csrc/third_party/catlass/examples/49_ascend950_flash_attention_infer/fai_tiling.h
csrc/third_party/catlass/examples/49_ascend950_flash_attention_infer/flash_attention_infer.md
csrc/third_party/catlass/examples/49_ascend950_flash_attention_infer/gen_data.py
csrc/third_party/catlass/examples/49_ascend950_flash_attention_infer/tiling_data_def.h
csrc/third_party/catlass/examples/50_ascend950_basic_matmul_gemv/CMakeLists.txt
csrc/third_party/catlass/examples/50_ascend950_basic_matmul_gemv/README.md
csrc/third_party/catlass/examples/50_ascend950_basic_matmul_gemv/basic_matmul_tla.cpp
csrc/third_party/catlass/examples/51_ascend950_quant_matmul_per_group_per_block_tla/CMakeLists.txt
csrc/third_party/catlass/examples/51_ascend950_quant_matmul_per_group_per_block_tla/README.md
csrc/third_party/catlass/examples/51_ascend950_quant_matmul_per_group_per_block_tla/quant_matmul_per_group_per_block.cpp
csrc/third_party/catlass/examples/52_quant_multi_core_splitk_matmul_tla/52_quant_multi_core_splitk_matmul_tla.md
csrc/third_party/catlass/examples/52_quant_multi_core_splitk_matmul_tla/CMakeLists.txt
csrc/third_party/catlass/examples/52_quant_multi_core_splitk_matmul_tla/README.md
csrc/third_party/catlass/examples/52_quant_multi_core_splitk_matmul_tla/quant_multi_core_splitk_matmul_tla.cpp
csrc/third_party/catlass/examples/advanced/basic_matmul_aclnn/CMakeLists.txt
csrc/third_party/catlass/examples/advanced/basic_matmul_aclnn/README.md
csrc/third_party/catlass/examples/advanced/basic_matmul_aclnn/basic_matmul_aclnn.cpp
csrc/third_party/catlass/examples/advanced/basic_matmul_aclnn/catlass_basic_matmul.json
csrc/third_party/catlass/examples/advanced/basic_matmul_aclnn/op_host/catlass_basic_matmul.cpp
csrc/third_party/catlass/examples/advanced/basic_matmul_aclnn/op_host/catlass_basic_matmul_tiling.h
csrc/third_party/catlass/examples/advanced/basic_matmul_aclnn/op_kernel/catlass_basic_matmul.cpp
csrc/third_party/catlass/examples/common/golden.hpp
csrc/third_party/catlass/examples/common/helper.hpp
csrc/third_party/catlass/examples/common/options.hpp
csrc/third_party/catlass/examples/common/golden/compare_data.hpp
csrc/third_party/catlass/examples/common/golden/conv2d.hpp
csrc/third_party/catlass/examples/common/golden/fill_data.hpp
csrc/third_party/catlass/examples/common/golden/matmul.hpp
csrc/third_party/catlass/examples/python_extension/CMakeLists.txt
csrc/third_party/catlass/examples/python_extension/README.md
csrc/third_party/catlass/examples/python_extension/pyproject.toml
csrc/third_party/catlass/examples/python_extension/setup.py
csrc/third_party/catlass/examples/python_extension/src/bindings/pybind_bindings.cpp
csrc/third_party/catlass/examples/python_extension/src/bindings/torch_bindings.cpp
csrc/third_party/catlass/examples/python_extension/src/include/wrapper/catlass_kernel_wrapper.h
csrc/third_party/catlass/examples/python_extension/src/include/wrapper/common.h
csrc/third_party/catlass/examples/python_extension/src/include/wrapper/conv.h
csrc/third_party/catlass/examples/python_extension/src/include/wrapper/grouped_matmul.h
csrc/third_party/catlass/examples/python_extension/src/include/wrapper/matmul.h
csrc/third_party/catlass/examples/python_extension/src/include/wrapper/run_npu_func.h
csrc/third_party/catlass/examples/python_extension/src/wrapper/catlass_kernel_wrapper.cpp
csrc/third_party/catlass/examples/python_extension/src/wrapper/common.cpp
csrc/third_party/catlass/examples/python_extension/src/wrapper/conv.cpp
csrc/third_party/catlass/examples/python_extension/src/wrapper/grouped_matmul.cpp
csrc/third_party/catlass/examples/python_extension/src/wrapper/matmul.cpp
csrc/third_party/catlass/examples/python_extension/torch_catlass/__init__.py
csrc/third_party/catlass/examples/shared_lib/CMakeLists.txt
csrc/third_party/catlass/examples/shared_lib/README.md
csrc/third_party/catlass/examples/shared_lib/basic_matmul_shared_lib.cpp
csrc/third_party/catlass/examples/shared_lib/include/catlass_kernel.h
csrc/third_party/catlass/examples/shared_lib/src/common/common.hpp
csrc/third_party/catlass/examples/shared_lib/src/kernels/basic_matmul.cpp
csrc/third_party/catlass/examples/shared_lib/src/kernels/conv_bias.cpp
csrc/third_party/catlass/examples/shared_lib/src/kernels/grouped_matmul.cpp
csrc/third_party/catlass/examples/shared_lib/src/kernels/optimized_matmul.cpp
csrc/third_party/catlass/include/catlass/catlass.hpp
csrc/third_party/catlass/include/catlass/conv_coord.hpp
csrc/third_party/catlass/include/catlass/coord.hpp
csrc/third_party/catlass/include/catlass/debug.hpp
csrc/third_party/catlass/include/catlass/gemm_coord.hpp
csrc/third_party/catlass/include/catlass/gemv_coord.hpp
csrc/third_party/catlass/include/catlass/matrix_coord.hpp
csrc/third_party/catlass/include/catlass/numeric_size.hpp
csrc/third_party/catlass/include/catlass/status.hpp
csrc/third_party/catlass/include/catlass/arch/arch.hpp
csrc/third_party/catlass/include/catlass/arch/cross_core_sync.hpp
csrc/third_party/catlass/include/catlass/arch/local_tensor_buffer.hpp
csrc/third_party/catlass/include/catlass/arch/resource.hpp
csrc/third_party/catlass/include/catlass/conv/dispatch_policy.hpp
csrc/third_party/catlass/include/catlass/conv/block/block_conv.hpp
csrc/third_party/catlass/include/catlass/conv/block/block_conv2d_pingpong.hpp
csrc/third_party/catlass/include/catlass/conv/block/block_conv3d_pingpong_bias.hpp
csrc/third_party/catlass/include/catlass/conv/block/block_swizzle.hpp
csrc/third_party/catlass/include/catlass/conv/device/device_conv.hpp
csrc/third_party/catlass/include/catlass/conv/kernel/basic_conv2d.hpp
csrc/third_party/catlass/include/catlass/conv/kernel/conv3d_bias.hpp
csrc/third_party/catlass/include/catlass/conv/tile/copy_gm_to_l1.hpp
csrc/third_party/catlass/include/catlass/conv/tile/copy_l0c_to_gm.hpp
csrc/third_party/catlass/include/catlass/conv/tile/copy_l1_to_l0a.hpp
csrc/third_party/catlass/include/catlass/conv/tile/copy_l1_to_l0b.hpp
csrc/third_party/catlass/include/catlass/conv/tile/tile_copy.hpp
csrc/third_party/catlass/include/catlass/detail/alignment.hpp
csrc/third_party/catlass/include/catlass/detail/callback.hpp
csrc/third_party/catlass/include/catlass/detail/dependent_false.hpp
csrc/third_party/catlass/include/catlass/detail/kernel_adapter.hpp
csrc/third_party/catlass/include/catlass/detail/macros.hpp
csrc/third_party/catlass/include/catlass/detail/tag_to_layout.hpp
csrc/third_party/catlass/include/catlass/epilogue/dispatch_policy.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_elemwise_no_source.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_elemwise_one_source.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_fa_rescale_o.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_fa_rescale_o_ascend950.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_fa_softmax.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_fa_softmax_ascend950.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_fixpipe.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_gemm.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_gemv.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_mla_fd_rescale_o.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_mla_rescale_o.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_mla_softmax.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_mla_tp1_rescale_o.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_mla_tp1_softmax.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_online_softmax_no_mask.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_per_group_per_block.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_per_token_dequant.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_per_token_dequant_tla.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_rescale_o_no_split_row.hpp
csrc/third_party/catlass/include/catlass/epilogue/block/block_epilogue_w4a4_per_token_per_channel_dequant.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/copy_gm_to_ub.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/copy_gm_to_ub_tla.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/copy_ub_to_gm.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/copy_ub_to_gm_tla.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/copy_ub_to_l1_tla.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_broadcast_add.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_broadcast_inplace_by_column.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_broadcast_inplace_by_row.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_broadcast_mul.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_broadcast_one_blk.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_cast.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_copy.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_elemwise_add.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_elemwise_gelu.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_elemwise_mul.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_elemwise_muls.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_elemwise_silu.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_pertoken_dequant.hpp
csrc/third_party/catlass/include/catlass/epilogue/tile/tile_swizzle.hpp
csrc/third_party/catlass/include/catlass/gemm/dispatch_policy.hpp
csrc/third_party/catlass/include/catlass/gemm/gemm_type.hpp
csrc/third_party/catlass/include/catlass/gemm/helper.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_dynamic_aiv.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_dynamic_common.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_dynamic_preload_async_with_callback.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_dynamic_single_core_splitk.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_dynamic_small.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_dynamic_streamk.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fa_pv.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fa_qk.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fai_pv_head_tail.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fai_pv_head_tail_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fai_pv_normal.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fai_pv_normal_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fai_pv_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fai_qk_head_tail.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fai_qk_head_tail_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fai_qk_normal.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fai_qk_normal_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_fai_qk_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_gemm.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_mla_pv.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_mla_pv_tp1_spec.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_mla_qk.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_mla_qk_tp1_spec.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_pingpong.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_pingpong_bias.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_pingpong_dequant_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_pingpong_full_loadA.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_pingpong_full_loadA_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_pingpong_per_group_per_block_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_pingpong_slice_k_with_prologue.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_pingpong_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_pingpong_tla_v2.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_pingpong_with_prologue.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_preload.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_preload_async.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_preload_async_with_callback.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_preload_async_with_callback_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_preload_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_single_core_splitk.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_small.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_sparse_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_streamk.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_mmad_w4a4_per_token_per_channel_dequant.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_scheduler_aswt.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_scheduler_iterateK.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_scheduler_l2_misplace_core.hpp
csrc/third_party/catlass/include/catlass/gemm/block/block_swizzle.hpp
csrc/third_party/catlass/include/catlass/gemm/device/device_gemm.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/basic_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/basic_matmul_preload.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/basic_matmul_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/batched_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/dynamic_aiv_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/dynamic_common_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/dynamic_local_padding_c_padding_common_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/dynamic_padding_common_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/dynamic_padding_multi_core_splitk_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/dynamic_padding_streamk_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/dynamic_single_core_splitk_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/dynamic_small_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/dynamic_w8a8_matmul_per_token_per_channel_dequant.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/fp8_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/gemm.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/group_gemm.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/grouped_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/grouped_matmul_slice_k.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/grouped_matmul_slice_k_per_token_dequant.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/grouped_matmul_slice_m.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/grouped_matmul_slice_m_per_tensor_per_channel_dequant_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/grouped_matmul_slice_m_per_token_dequant.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/grouped_matmul_slice_m_per_token_dequant_multistage_workspace.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/grouped_matmul_slice_m_per_token_dequant_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/matmul_activation.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/matmul_bias.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/matmul_epilogue.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/matmul_full_loadA.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/matmul_mix_fixpipe_opti.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/optimized_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/optimized_matmul_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/padding_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/padding_splitk_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/quant_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/quant_matmul_full_loadA_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/quant_matmul_multistage_workspace.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/quant_matmul_per_group_per_block_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/quant_multi_core_splitk_matmul_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/quant_optimized_matmul_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/single_core_slicek_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/small_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/sparse_matmul_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/splitk_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/streamk_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/strided_batched_matmul_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/w4a4_matmul_per_token_per_channel_dequant.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/w4a8_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/kernel/w8a16_matmul.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/cast_fp8_to_fp16.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/cast_int4_to_int8.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/cast_int8_to_fp16.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/copy_gm_to_l1.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/copy_gm_to_ub.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/copy_l0c_to_gm.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/copy_l0c_to_ub.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/copy_l1_to_bt.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/copy_l1_to_fp.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/copy_l1_to_l0a.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/copy_l1_to_l0b.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/copy_ub_to_gm.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/tile_copy.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/tile_copy_tla.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/tile_mmad.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/tile_muls.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/tile_traits.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/ascend950/copy_gm_to_l1.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/ascend950/copy_l0c_to_dst.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/ascend950/copy_l0c_to_gm.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/ascend950/copy_l0c_to_ub.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/ascend950/copy_l1_to_bt.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/ascend950/copy_l1_to_l0a.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/ascend950/copy_l1_to_l0b.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/atlasa2/cast_fp8_to_fp16.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/atlasa2/cast_int4_to_int8.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/atlasa2/cast_int8_to_fp16.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/atlasa2/copy_gm_to_l1.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/atlasa2/copy_gm_to_ub.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/atlasa2/copy_l0c_to_gm.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/atlasa2/copy_l1_to_bt.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/atlasa2/copy_l1_to_fp.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/atlasa2/copy_l1_to_l0a.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/atlasa2/copy_l1_to_l0b.hpp
csrc/third_party/catlass/include/catlass/gemm/tile/atlasa2/copy_ub_to_gm.hpp
csrc/third_party/catlass/include/catlass/gemv/helper.hpp
csrc/third_party/catlass/include/catlass/gemv/block/block_gemv.hpp
csrc/third_party/catlass/include/catlass/gemv/block/block_gemv_aic.hpp
csrc/third_party/catlass/include/catlass/gemv/block/block_gemv_aiv.hpp
csrc/third_party/catlass/include/catlass/gemv/device/device_gemv.hpp
csrc/third_party/catlass/include/catlass/gemv/kernel/kernel_gemv_aic.hpp
csrc/third_party/catlass/include/catlass/gemv/kernel/kernel_gemv_aiv.hpp
csrc/third_party/catlass/include/catlass/gemv/tile/matrix_copy_gm_to_ub.hpp
csrc/third_party/catlass/include/catlass/gemv/tile/tile_copy.hpp
csrc/third_party/catlass/include/catlass/gemv/tile/tile_vmad.hpp
csrc/third_party/catlass/include/catlass/gemv/tile/tile_vmuls.hpp
csrc/third_party/catlass/include/catlass/gemv/tile/vec_copy_gm_to_ub.hpp
csrc/third_party/catlass/include/catlass/gemv/tile/vec_copy_ub_to_gm.hpp
csrc/third_party/catlass/include/catlass/layout/layout.hpp
csrc/third_party/catlass/include/catlass/layout/matrix.hpp
csrc/third_party/catlass/include/catlass/layout/tensor.hpp
csrc/third_party/catlass/include/catlass/layout/vector.hpp
csrc/third_party/catlass/include/tla/int_tuple.hpp
csrc/third_party/catlass/include/tla/layout.hpp
csrc/third_party/catlass/include/tla/tensor.hpp
csrc/third_party/catlass/include/tla/tuple.hpp
csrc/third_party/catlass/include/tla/type_traits.hpp
csrc/third_party/catlass/include/tla/numeric/integer_sequence.hpp
csrc/third_party/catlass/include/tla/numeric/integral_constant.hpp
csrc/third_party/catlass/include/tla/numeric/math.hpp
csrc/third_party/catlass/scripts/build.sh
csrc/third_party/catlass/tests/CMakeLists.txt
csrc/third_party/catlass/tests/run_all_test.sh
csrc/third_party/catlass/tests/test_compile.sh
csrc/third_party/catlass/tests/test_example.py
csrc/third_party/catlass/tests/test_mstuner.py
csrc/third_party/catlass/tests/test_python_extension.py
csrc/third_party/catlass/tests/test_torch_lib.py
csrc/third_party/catlass/tests/self_contained_includes/CMakeLists.txt
csrc/third_party/catlass/tests/self_contained_includes/test_self_contained_includes.cpp
csrc/third_party/catlass/tests/unittest/CMakeLists.txt
csrc/third_party/catlass/tests/unittest/catlass_unittest.cpp
csrc/third_party/catlass/tests/unittest/catlass/test_gemm_coord.cpp
csrc/third_party/catlass/tools/CMakeLists.txt
csrc/third_party/catlass/tools/library/CMakeLists.txt
csrc/third_party/catlass/tools/library/include/catlass/library/manifest.h
csrc/third_party/catlass/tools/library/include/catlass/library/operation.h
csrc/third_party/catlass/tools/library/scripts/code_generator.py
csrc/third_party/catlass/tools/library/scripts/gemm_operation.py
csrc/third_party/catlass/tools/library/scripts/library.py
csrc/third_party/catlass/tools/library/scripts/manifest.py
csrc/third_party/catlass/tools/library/scripts/search_space.py
csrc/third_party/catlass/tools/library/scripts/search_space_config.py
csrc/third_party/catlass/tools/library/scripts/utils.py
csrc/third_party/catlass/tools/library/src/gemm_operation.h
csrc/third_party/catlass/tools/library/src/library_utils.h
csrc/third_party/catlass/tools/library/src/manifest.cpp
csrc/third_party/catlass/tools/tuner/CMakeLists.txt
csrc/third_party/catlass/tools/tuner/README.md
csrc/third_party/catlass/tools/tuner/dfx_kernel/CMakeLists.txt
csrc/third_party/catlass/tools/tuner/dfx_kernel/clear_l2_cache.cpp
csrc/third_party/catlass/tools/tuner/include/catlass_tuner.h
csrc/third_party/catlass/tools/tuner/include/command_line_parser.h
csrc/third_party/catlass/tools/tuner/include/device_memory_manager.h
csrc/third_party/catlass/tools/tuner/include/gemm_op_config.h
csrc/third_party/catlass/tools/tuner/include/library_helper.h
csrc/third_party/catlass/tools/tuner/include/log.h
csrc/third_party/catlass/tools/tuner/include/m_t_var.h
csrc/third_party/catlass/tools/tuner/include/metric.h
csrc/third_party/catlass/tools/tuner/include/metrics.h
csrc/third_party/catlass/tools/tuner/include/op_config.h
csrc/third_party/catlass/tools/tuner/include/op_launcher.h
csrc/third_party/catlass/tools/tuner/include/profiler.h
csrc/third_party/catlass/tools/tuner/src/catlass_tuner.cpp
csrc/third_party/catlass/tools/tuner/src/command_line_parser.cpp
csrc/third_party/catlass/tools/tuner/src/device_memory_manager.cpp
csrc/third_party/catlass/tools/tuner/src/gemm_op_config.cpp
csrc/third_party/catlass/tools/tuner/src/library_helper.cpp
csrc/third_party/catlass/tools/tuner/src/main.cpp
csrc/third_party/catlass/tools/tuner/src/metric.cpp
csrc/third_party/catlass/tools/tuner/src/metrics.cpp
csrc/third_party/catlass/tools/tuner/src/op_config.cpp
csrc/third_party/catlass/tools/tuner/src/op_launcher.cpp
csrc/third_party/catlass/tools/tuner/src/profiler.cpp
csrc/utils/CMakeLists.txt
csrc/utils/inc/aclnn_util.h
csrc/utils/inc/fallback.h
csrc/utils/inc/fallback_comm.h
csrc/utils/inc/error/ops_error.h
csrc/utils/inc/kernel/comm_args.h
csrc/utils/inc/kernel/data_copy.h
csrc/utils/inc/kernel/dropmask.h
csrc/utils/inc/kernel/moe_distribute_base.h
csrc/utils/inc/kernel/pse.h
csrc/utils/inc/kernel/sync_collectives.h
csrc/utils/inc/kernel/util.h
csrc/utils/inc/log/ops_log.h
csrc/utils/inc/log/inner/dfx_base.h
csrc/utils/inc/tiling/data_copy_transpose_tiling.h
csrc/utils/inc/tiling/data_copy_transpose_tiling_def.h
csrc/utils/inc/tiling/tiling_base.h
csrc/utils/inc/tiling/tiling_templates_registry.h
csrc/utils/inc/tiling/tiling_type.h
csrc/utils/src/fallback_comm.cpp
docs/Makefile
docs/README.md
docs/requirements-docs.txt
docs/source/conf.py
docs/source/faqs.md
docs/source/index.md
docs/source/installation.md
docs/source/llms.txt
docs/source/quick_start.md
docs/source/_templates/Model-Deployment-Tutorial-Template.md
docs/source/_templates/Model-Deployment-Tutorial-Template.zh.md
docs/source/_templates/sections/header.html
docs/source/assets/ci_log_summary.png
docs/source/assets/deployment.png
docs/source/assets/disaggregated_prefill_pull.png
docs/source/assets/disaggregated_prefill_push.png
docs/source/assets/eplb.png
docs/source/assets/multi_node_dp_deepseek.png
docs/source/assets/multi_node_dp_kimi.png
docs/source/assets/sp_moe.png
docs/source/assets/workflow.png
docs/source/assets/cp/blocktable.png
docs/source/assets/cp/chunkedprefill.png
docs/source/assets/cp/dcp-decode.png
docs/source/assets/cp/dcp-prefill.png
docs/source/assets/cp/device_world.png
docs/source/assets/cp/head-tail-style.png
docs/source/assets/cp/overview.png
docs/source/assets/cp/pcp-decode.png
docs/source/assets/cp/pcp-prefill.png
docs/source/assets/quantization/get_quant_method.png
docs/source/assets/quantization/quant_algorithm_overview.png
docs/source/assets/quantization/quant_method_base_class.png
docs/source/assets/quantization/quant_method_call_flow.png
docs/source/assets/quantization/quant_methods_overview.png
docs/source/community/contributors.md
docs/source/community/governance.md
docs/source/community/issue-workflow-guidelines.md
docs/source/community/slash-commands.md
docs/source/community/versioning_policy.md
docs/source/community/images/ascend_assistant.png
docs/source/community/images/issue_label_workflow.png
docs/source/community/user_stories/index.md
docs/source/community/user_stories/llamafactory.md
docs/source/developer_guide/Design_Documents/ACL_Graph.md
docs/source/developer_guide/Design_Documents/KV_Cache_Pool_Guide.md
docs/source/developer_guide/Design_Documents/ModelRunner_prepare_inputs.md
docs/source/developer_guide/Design_Documents/add_custom_aclnn_op.md
docs/source/developer_guide/Design_Documents/context_parallel.md
docs/source/developer_guide/Design_Documents/cpu_binding.md
docs/source/developer_guide/Design_Documents/disaggregated_prefill.md
docs/source/developer_guide/Design_Documents/dynamic_chunked_pipeline_parallel.md
docs/source/developer_guide/Design_Documents/eplb_swift_balancer.md
docs/source/developer_guide/Design_Documents/index.md
docs/source/developer_guide/Design_Documents/npugraph_ex.md
docs/source/developer_guide/Design_Documents/patch.md
docs/source/developer_guide/Design_Documents/quantization.md
docs/source/developer_guide/contribution/doc_writing.md
docs/source/developer_guide/contribution/e2e_ci_test.md
docs/source/developer_guide/contribution/index.md
docs/source/developer_guide/contribution/multi_node_test.md
docs/source/developer_guide/contribution/nightly_ci_test.md
docs/source/developer_guide/contribution/testing.md
docs/source/developer_guide/evaluation/index.md
docs/source/developer_guide/evaluation/using_ais_bench.md
docs/source/developer_guide/evaluation/using_evalscope.md
docs/source/developer_guide/evaluation/using_lm_eval.md
docs/source/developer_guide/evaluation/using_opencompass.md
docs/source/developer_guide/performance_and_debug/index.md
docs/source/developer_guide/performance_and_debug/msprobe_guide.md
docs/source/developer_guide/performance_and_debug/optimization_and_tuning.md
docs/source/developer_guide/performance_and_debug/performance_benchmark.md
docs/source/developer_guide/performance_and_debug/service_profiling_guide.md
docs/source/locale/zh_CN/LC_MESSAGES/faqs.po
docs/source/locale/zh_CN/LC_MESSAGES/index.po
docs/source/locale/zh_CN/LC_MESSAGES/installation.po
docs/source/locale/zh_CN/LC_MESSAGES/quick_start.po
docs/source/locale/zh_CN/LC_MESSAGES/community/contributors.po
docs/source/locale/zh_CN/LC_MESSAGES/community/governance.po
docs/source/locale/zh_CN/LC_MESSAGES/community/issue-workflow-guidelines.po
docs/source/locale/zh_CN/LC_MESSAGES/community/slash-commands.po
docs/source/locale/zh_CN/LC_MESSAGES/community/versioning_policy.po
docs/source/locale/zh_CN/LC_MESSAGES/community/user_stories/index.po
docs/source/locale/zh_CN/LC_MESSAGES/community/user_stories/llamafactory.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/ACL_Graph.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/KV_Cache_Pool_Guide.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/ModelRunner_prepare_inputs.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/add_custom_aclnn_op.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/context_parallel.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/cpu_binding.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/disaggregated_prefill.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/dynamic_chunked_pipeline_parallel.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/eplb_swift_balancer.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/index.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/npugraph_ex.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/patch.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/quantization.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/doc_writing.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/e2e_ci_test.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/index.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/multi_node_test.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/nightly_ci_test.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/contribution/testing.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/index.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_ais_bench.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_evalscope.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_lm_eval.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/evaluation/using_opencompass.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance_and_debug/index.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance_and_debug/msprobe_guide.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance_and_debug/optimization_and_tuning.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance_and_debug/performance_benchmark.po
docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/performance_and_debug/service_profiling_guide.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/dynamic_chunked_pipeline_parallel.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/index.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/long_sequence_context_parallel_multi_node.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/long_sequence_context_parallel_single_node.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/pd_colocated_mooncake_multi_instance.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/pd_disaggregation_mooncake_multi_node.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/pd_disaggregation_mooncake_single_node.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/ray.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/features/suffix_speculative_decoding.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeek-R1.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeek-V3.1.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeek-V3.2.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeek-V4-Flash.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeek-V4-Pro.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/DeepSeekOCR2.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/GLM4.x.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/GLM5.2.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/GLM5.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Hunyuan-A13B-Instruct.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Hy3-preview.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/InternVL3.5.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Kimi-K2-Thinking.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Kimi-K2.5.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Kimi-K2.6.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Kimi-K3.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/LLaVA-OneVision-Qwen2-0.5B-OV.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/MiniMax-M2.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Minitron-8B-Base.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Mixtral-8x7B-Instruct-v0.1.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/PaddleOCR-VL.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen-VL-Dense.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen2.5-Math-RM-72B.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-235B-A22B.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-30B-A3B.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-ASR-1.7B.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-Coder-30B-A3B.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-Dense.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-Embedding.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-Next.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-Omni-30B-A3B-Thinking.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-Reranker.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-VL-235B-A22B-Instruct.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-VL-30B-A3B-Instruct.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-VL-Embedding.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3-VL-Reranker.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3.5-27B-Qwen3.6-27B.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3.5-397B-A17B.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3.5-Dense.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/Qwen3.6-35B-A3B.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/gpt-oss-120b.po
docs/source/locale/zh_CN/LC_MESSAGES/tutorials/models/index.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/release_notes.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/additional_config.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/env_vars.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/configuration/index.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/deployment_guide/index.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/deployment_guide/using_mindie_motor.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/deployment_guide/using_volcano_kthena.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/Ai_QoS_introduction_en.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/Fine_grained_TP.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/batch_invariance.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/context_parallel.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/cpu_binding.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/dynamic_batch.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/dynamic_chunk_pipeline_parallel.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/epd_disaggregation.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/expert_parallelism_load_balancer.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/external_dp.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/flash_attention.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/graph_mode.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/index.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/kv_cache_cpu_offload.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/kv_pool.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/large_scale_ep.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/layer_sharding.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/layerwise_kv_pool.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/lmcache_ascend_deployment.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/lora.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/netloader.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/quantization.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/recompute_cpu_offload.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/rfork.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/sequence_parallelism.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/sleep_mode.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/speculative_decoding.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/structured_output.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/ucm_deployment.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/feature_guide/weight_prefetch.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/feature_matrix.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/index.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/supported_features.po
docs/source/locale/zh_CN/LC_MESSAGES/user_guide/support_matrix/supported_models.po
docs/source/logos/vllm-ascend-logo-text-dark.png
docs/source/logos/vllm-ascend-logo-text-light.png
docs/source/tutorials/features/dynamic_chunked_pipeline_parallel.md
docs/source/tutorials/features/index.md
docs/source/tutorials/features/long_sequence_context_parallel_multi_node.md
docs/source/tutorials/features/long_sequence_context_parallel_single_node.md
docs/source/tutorials/features/pd_colocated_mooncake_multi_instance.md
docs/source/tutorials/features/pd_disaggregation_mooncake_multi_node.md
docs/source/tutorials/features/pd_disaggregation_mooncake_single_node.md
docs/source/tutorials/features/ray.md
docs/source/tutorials/features/suffix_speculative_decoding.md
docs/source/tutorials/models/DeepSeek-R1.md
docs/source/tutorials/models/DeepSeek-V3.1.md
docs/source/tutorials/models/DeepSeek-V3.2.md
docs/source/tutorials/models/DeepSeek-V4-Flash.md
docs/source/tutorials/models/DeepSeek-V4-Pro.md
docs/source/tutorials/models/DeepSeekOCR2.md
docs/source/tutorials/models/GLM4.x.md
docs/source/tutorials/models/GLM5.2.md
docs/source/tutorials/models/GLM5.md
docs/source/tutorials/models/Hunyuan-A13B-Instruct.md
docs/source/tutorials/models/Hy3-preview.md
docs/source/tutorials/models/InternVL3.5.md
docs/source/tutorials/models/Kimi-K2-Thinking.md
docs/source/tutorials/models/Kimi-K2.5.md
docs/source/tutorials/models/Kimi-K2.6.md
docs/source/tutorials/models/Kimi-K3.md
docs/source/tutorials/models/LLaVA-OneVision-Qwen2-0.5B-OV.md
docs/source/tutorials/models/MiniMax-M2.md
docs/source/tutorials/models/Minitron-8B-Base.md
docs/source/tutorials/models/Mixtral-8x7B-Instruct-v0.1.md
docs/source/tutorials/models/PaddleOCR-VL.md
docs/source/tutorials/models/Qwen-VL-Dense.md
docs/source/tutorials/models/Qwen2.5-Math-RM-72B.md
docs/source/tutorials/models/Qwen3-235B-A22B.md
docs/source/tutorials/models/Qwen3-30B-A3B.md
docs/source/tutorials/models/Qwen3-ASR-1.7B.md
docs/source/tutorials/models/Qwen3-Coder-30B-A3B.md
docs/source/tutorials/models/Qwen3-Dense.md
docs/source/tutorials/models/Qwen3-Embedding.md
docs/source/tutorials/models/Qwen3-Next.md
docs/source/tutorials/models/Qwen3-Omni-30B-A3B-Thinking.md
docs/source/tutorials/models/Qwen3-Reranker.md
docs/source/tutorials/models/Qwen3-VL-235B-A22B-Instruct.md
docs/source/tutorials/models/Qwen3-VL-30B-A3B-Instruct.md
docs/source/tutorials/models/Qwen3-VL-Embedding.md
docs/source/tutorials/models/Qwen3-VL-Reranker.md
docs/source/tutorials/models/Qwen3.5-27B-Qwen3.6-27B.md
docs/source/tutorials/models/Qwen3.5-397B-A17B.md
docs/source/tutorials/models/Qwen3.5-Dense.md
docs/source/tutorials/models/Qwen3.6-35B-A3B.md
docs/source/tutorials/models/gpt-oss-120b.md
docs/source/tutorials/models/index.md
docs/source/user_guide/image-1.png
docs/source/user_guide/image.png
docs/source/user_guide/release_notes.md
docs/source/user_guide/configuration/additional_config.md
docs/source/user_guide/configuration/env_vars.md
docs/source/user_guide/configuration/index.md
docs/source/user_guide/deployment_guide/index.md
docs/source/user_guide/deployment_guide/using_mindie_motor.md
docs/source/user_guide/deployment_guide/using_volcano_kthena.md
docs/source/user_guide/feature_guide/Ai_QoS_introduction_en.md
docs/source/user_guide/feature_guide/Fine_grained_TP.md
docs/source/user_guide/feature_guide/batch_invariance.md
docs/source/user_guide/feature_guide/context_parallel.md
docs/source/user_guide/feature_guide/cpu_binding.md
docs/source/user_guide/feature_guide/dynamic_batch.md
docs/source/user_guide/feature_guide/dynamic_chunk_pipeline_parallel.md
docs/source/user_guide/feature_guide/epd_disaggregation.md
docs/source/user_guide/feature_guide/expert_parallelism_load_balancer.md
docs/source/user_guide/feature_guide/external_dp.md
docs/source/user_guide/feature_guide/flash_attention.md
docs/source/user_guide/feature_guide/graph_mode.md
docs/source/user_guide/feature_guide/index.md
docs/source/user_guide/feature_guide/kv_cache_cpu_offload.md
docs/source/user_guide/feature_guide/kv_pool.md
docs/source/user_guide/feature_guide/large_scale_ep.md
docs/source/user_guide/feature_guide/layer_sharding.md
docs/source/user_guide/feature_guide/layerwise_kv_pool.md
docs/source/user_guide/feature_guide/lmcache_ascend_deployment.md
docs/source/user_guide/feature_guide/lora.md
docs/source/user_guide/feature_guide/netloader.md
docs/source/user_guide/feature_guide/quantization.md
docs/source/user_guide/feature_guide/recompute_cpu_offload.md
docs/source/user_guide/feature_guide/rfork.md
docs/source/user_guide/feature_guide/sequence_parallelism.md
docs/source/user_guide/feature_guide/sleep_mode.md
docs/source/user_guide/feature_guide/speculative_decoding.md
docs/source/user_guide/feature_guide/structured_output.md
docs/source/user_guide/feature_guide/ucm_deployment.md
docs/source/user_guide/feature_guide/weight_prefetch.md
docs/source/user_guide/feature_guide/images/ai_qos1.png
docs/source/user_guide/feature_guide/images/ai_qos2.png
docs/source/user_guide/feature_guide/images/epd_disaggregation.jpg
docs/source/user_guide/feature_guide/images/eplb_img.png
docs/source/user_guide/feature_guide/images/layer_sharding.png
docs/source/user_guide/feature_guide/images/netloader_flowchart.png
docs/source/user_guide/feature_guide/images/netloader_timing_diagram.png
docs/source/user_guide/feature_guide/images/rfork_flowchart.jpg
docs/source/user_guide/feature_guide/images/structured_output_1.png
docs/source/user_guide/support_matrix/feature_matrix.md
docs/source/user_guide/support_matrix/index.md
docs/source/user_guide/support_matrix/supported_features.md
docs/source/user_guide/support_matrix/supported_models.md
examples/device_print_demo.py
examples/offline_data_parallel.py
examples/offline_disaggregated_prefill_npu.py
examples/offline_embed.py
examples/offline_external_launcher.py
examples/offline_inference_audio_language.py
examples/offline_inference_metrics.py
examples/offline_inference_npu.py
examples/offline_inference_npu_long_seq.py
examples/offline_inference_npu_tp2.py
examples/offline_inference_sleep_mode_npu.py
examples/offline_weight_load.py
examples/prompt_embed_inference.py
examples/prompt_embedding_inference.py
examples/run_dp_server.sh
examples/save_sharded_state_310.py
examples/chat_templates/template_qwen2_audio.jinja
examples/disaggregated_encoder/disagg_1e1pd_example.sh
examples/disaggregated_encoder/disagg_epd_proxy.py
examples/disaggregated_prefill_v1/load_balance_proxy_layerwise_server_example.py
examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py
examples/disaggregated_prefill_v1/mooncake_connector_deployment_guide.md
examples/dynamic_bucket_load_balancer/README.md
examples/dynamic_bucket_load_balancer/dynamic_bucket_load_balancer.py
examples/dynamic_bucket_load_balancer/hybrid_proxy_server.py
examples/epd_disaggregated/epd_disaggregated_guide.md
examples/epd_disaggregated/epd_load_balance_proxy_layerwise_server_example.py
examples/eplb/eplb_deepseek.py
examples/eplb/eplb_strategy.py
examples/external_online_dp/README.md
examples/external_online_dp/dp_load_balance_proxy_server.py
examples/external_online_dp/launch_online_dp.py
examples/external_online_dp/run_dp_template.sh
examples/quantization/llm-compressor/w4a8_dynamic_moe.py
examples/quantization/llm-compressor/w8a8_int8.py
examples/quantization/llm-compressor/w8a8_int8_dynamic.py
examples/quantization/llm-compressor/w8a8_int8_dynamic_moe.py
examples/rfork/rfork_planner.py
examples/rl/rlhf_http_hccl.py
examples/rl/rlhf_http_npu_ipc.py
tests/__init__.py
tests/e2e/__init__.py
tests/e2e/common.sh
tests/e2e/conftest.py
tests/e2e/coverage.md
tests/e2e/generate_coverage_md.py
tests/e2e/model_utils.py
tests/e2e/run_doctests.sh
tests/e2e/utils.py
tests/e2e/doctests/001-quickstart-test.sh
tests/e2e/doctests/002-pip-binary-installation-test.sh
tests/e2e/models/conftest.py
tests/e2e/models/report_template.md
tests/e2e/models/test_asr_eval_correctness.py
tests/e2e/models/test_lm_eval_correctness.py
tests/e2e/models/test_rm_eval_correctness.py
tests/e2e/models/configs/ERNIE-4.5-21B-A3B-PT.yaml
tests/e2e/models/configs/Hunyuan-A13B-Instruct.yaml
tests/e2e/models/configs/InternVL3_5-8B-hf.yaml
tests/e2e/models/configs/Llama-3.2-3B-Instruct.yaml
tests/e2e/models/configs/Minitron-8B-Base.yaml
tests/e2e/models/configs/Mixtral-8x7B-Instruct-v0.1.yaml
tests/e2e/models/configs/Molmo-7B-D-0924.yaml
tests/e2e/models/configs/Qwen2-Audio-7B-Instruct.yaml
tests/e2e/models/configs/Qwen2.5-Math-RM-72B.yaml
tests/e2e/models/configs/Qwen3-30B-A3B-W8A8.yaml
tests/e2e/models/configs/Qwen3-30B-A3B.yaml
tests/e2e/models/configs/Qwen3-8B-W8A8.yaml
tests/e2e/models/configs/Qwen3-8B.yaml
tests/e2e/models/configs/Qwen3-ASR-1.7B.yaml
tests/e2e/models/configs/Qwen3-Next-80B-A3B-Instruct.yaml
tests/e2e/models/configs/Qwen3-Omni-30B-A3B-Instruct.yaml
tests/e2e/models/configs/Qwen3-VL-30B-A3B-Instruct.yaml
tests/e2e/models/configs/Qwen3-VL-8B-Instruct-W8A8.yaml
tests/e2e/models/configs/Qwen3-VL-8B-Instruct.yaml
tests/e2e/models/configs/accuracy.txt
tests/e2e/models/configs/gemma-3-4b-it.yaml
tests/e2e/models/configs/internlm3-8b-instruct.yaml
tests/e2e/models/configs/llava-onevision-qwen2-0.5b-ov-hf.yaml
tests/e2e/nightly/310p/single_node/ops/singlecard_ops/test_chunk_fwd_o_310.py
tests/e2e/nightly/310p/single_node/ops/singlecard_ops/test_chunk_gated_delta_rule_fwd_h_aclnn.py
tests/e2e/nightly/310p/single_node/ops/singlecard_ops/test_recurrent_gated_delta_rule_v310.py
tests/e2e/nightly/multi_node/__init__.py
tests/e2e/nightly/multi_node/external_dp/__init__.py
tests/e2e/nightly/multi_node/external_dp/config/DeepSeek-V4-Pro-w4a8-1M-PD.yaml
tests/e2e/nightly/multi_node/external_dp/config/DeepSeek-V4-Pro-w4a8-prefix-cache-PD.yaml
tests/e2e/nightly/multi_node/external_dp/config/DeepSeek-V4-flash-w8a8-PD-prefix.yaml
tests/e2e/nightly/multi_node/external_dp/config/GLM5_1-W8A8-EP-external.yaml
tests/e2e/nightly/multi_node/external_dp/config/Kimi-K2.6-W4A8-64k-1k-TPOT50-PD.yaml
tests/e2e/nightly/multi_node/external_dp/config/Minimax_m2.7_in128k_1k_prefix90_tpot50.yaml
tests/e2e/nightly/multi_node/external_dp/config/template.md
tests/e2e/nightly/multi_node/external_dp/scripts/__init__.py
tests/e2e/nightly/multi_node/external_dp/scripts/external_dp_config.py
tests/e2e/nightly/multi_node/external_dp/scripts/runtime.py
tests/e2e/nightly/multi_node/external_dp/scripts/test_external_dp.py
tests/e2e/nightly/multi_node/external_dp/scripts/utils.py
tests/e2e/nightly/multi_node/internal_dp/config/DeepSeek-R1-W8A8-EPLB.yaml
tests/e2e/nightly/multi_node/internal_dp/config/DeepSeek-R1-W8A8-longseq.yaml
tests/e2e/nightly/multi_node/internal_dp/config/DeepSeek-V3.1-BF16.yaml
tests/e2e/nightly/multi_node/internal_dp/config/DeepSeek-V3_2-W8A8-A3-dual-nodes.yaml
tests/e2e/nightly/multi_node/internal_dp/config/DeepSeek-V3_2-W8A8-EP.yaml
tests/e2e/nightly/multi_node/internal_dp/config/GLM-5.1-W8A8C8-A3_128k_90_50.yaml
tests/e2e/nightly/multi_node/internal_dp/config/GLM5_1-W8A8-A2-dual-nodes.yaml
tests/e2e/nightly/multi_node/internal_dp/config/GLM5_1-W8A8-A3-dual-nodes.yaml
tests/e2e/nightly/multi_node/internal_dp/config/GLM5_1-W8A8-EP.yaml
tests/e2e/nightly/multi_node/internal_dp/config/GLM5_2-W8A8-A3-dual-nodes.yaml
tests/e2e/nightly/multi_node/internal_dp/config/Kimi-K2_5-W4A8-A2-dual-nodes.yaml
tests/e2e/nightly/multi_node/internal_dp/config/Qwen3-235B-A22B-A2.yaml
tests/e2e/nightly/multi_node/internal_dp/config/Qwen3-235B-A22B.yaml
tests/e2e/nightly/multi_node/internal_dp/config/Qwen3-235B-W8A8-EPLB.yaml
tests/e2e/nightly/multi_node/internal_dp/config/Qwen3-235B-W8A8-longseq.yaml
tests/e2e/nightly/multi_node/internal_dp/config/Qwen3-235B-W8A8.yaml
tests/e2e/nightly/multi_node/internal_dp/config/Qwen3-235B-disagg-pd.yaml
tests/e2e/nightly/multi_node/internal_dp/config/Qwen3-VL-235B-disagg-pd.yaml
tests/e2e/nightly/multi_node/internal_dp/scripts/__init__.py
tests/e2e/nightly/multi_node/internal_dp/scripts/multi_node_config.py
tests/e2e/nightly/multi_node/internal_dp/scripts/test_multi_node.py
tests/e2e/nightly/multi_node/internal_dp/scripts/utils.py
tests/e2e/nightly/multi_node/scripts/__init__.py
tests/e2e/nightly/multi_node/scripts/benchmark_results.py
tests/e2e/nightly/multi_node/scripts/lws.yaml.jinja2
tests/e2e/nightly/multi_node/scripts/run.sh
tests/e2e/nightly/multi_node/scripts/utils.py
tests/e2e/nightly/scripts/aop_capture.sh
tests/e2e/nightly/scripts/aop_classify.sh
tests/e2e/nightly/scripts/aop_commit_age.sh
tests/e2e/nightly/scripts/aop_process.sh
tests/e2e/nightly/scripts/aop_skip.sh
tests/e2e/nightly/scripts/rules-env.txt
tests/e2e/nightly/scripts/update_good_table.py
tests/e2e/nightly/single_node/models/configs/DeepSeek-R1-0528-W8A8.yaml
tests/e2e/nightly/single_node/models/configs/DeepSeek-V3.2-W8A8-DCP.yaml
tests/e2e/nightly/single_node/models/configs/DeepSeek-V3.2-W8A8.yaml
tests/e2e/nightly/single_node/models/configs/DeepSeek-V4-Flash-W8A8-A3.yaml
tests/e2e/nightly/single_node/models/configs/GLM-4.7.yaml
tests/e2e/nightly/single_node/models/configs/GLM-5.1-W8A8-PrefillMC2.yaml
tests/e2e/nightly/single_node/models/configs/Hy3-preview.yaml
tests/e2e/nightly/single_node/models/configs/Kimi-K2-Thinking.yaml
tests/e2e/nightly/single_node/models/configs/Kimi-K2.5.yaml
tests/e2e/nightly/single_node/models/configs/Kimi-K2.6-w4a8-A3.yaml
tests/e2e/nightly/single_node/models/configs/MTPX-DeepSeek-R1-0528-W8A8.yaml
tests/e2e/nightly/single_node/models/configs/MiniMax-M2.5-w8a8-QuaRot-A2.yaml
tests/e2e/nightly/single_node/models/configs/MiniMax-M2.5-w8a8-QuaRot-A3.yaml
tests/e2e/nightly/single_node/models/configs/Minimax_m2.7_w8a8_A3.yaml
tests/e2e/nightly/single_node/models/configs/Prefix-Cache-DeepSeek-R1-0528-W8A8.yaml
tests/e2e/nightly/single_node/models/configs/Prefix-Cache-Qwen3-32B-Int8.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3-235B-A22B-W8A8.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3-30B-A3B-W4A8-llm-compressor.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3-30B-A3B-W8A8.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3-30B-QuaRot-eagle3.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3-32B-Int8-A2.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3-32B-Int8.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3-32B-QuaRot-eagle3.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3-VL-235B-A22B-Instruct-W8A8.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3-VL-32B-Instruct-W8A8.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3.5-122B-A10B-W8A8-A3.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3.5-27B-w8a8-A2.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3.5-27B-w8a8-A3.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3.5-397B-A17B-w4a8-mtp-A2.yaml
tests/e2e/nightly/single_node/models/configs/Qwen3.5-397B-A17B-w8a8-mtp-longseq-A3.yaml
tests/e2e/nightly/single_node/models/scripts/GUIDE_AND_TEMPLATE.md
tests/e2e/nightly/single_node/models/scripts/__init__.py
tests/e2e/nightly/single_node/models/scripts/single_node_config.py
tests/e2e/nightly/single_node/models/scripts/test_single_node.py
tests/e2e/nightly/single_node/ops/__init__.py
tests/e2e/nightly/single_node/ops/conftest.py
tests/e2e/nightly/single_node/ops/multicard_ops_a2/__init__.py
tests/e2e/nightly/single_node/ops/multicard_ops_a2/test_matmul_allreduce_add_rmsnorm.py
tests/e2e/nightly/single_node/ops/multicard_ops_a3/__init__.py
tests/e2e/nightly/single_node/ops/multicard_ops_a3/test_dispatch_ffn_combine.py
tests/e2e/nightly/single_node/ops/multicard_ops_a3/test_dispatch_ffn_combine_bf16.py
tests/e2e/nightly/single_node/ops/multicard_ops_a3/test_dispatch_ffn_combine_w4a8.py
tests/e2e/nightly/single_node/ops/multicard_ops_a3/test_dispatch_gmm_combine_decode.py
tests/e2e/nightly/single_node/ops/singlecard_ops/__init__.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_add_rms_norm_bias.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_batch_matmul_transpose.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_bgmv_expand.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_bgmv_shrink.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_causal_conv1d_310.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_compressor_metadata.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_copy_and_expand_eagle_inputs.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_dequant_swiglu_quant.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_fused_gdn_gating.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_fused_moe.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_gating_top_k_softmax.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_gmm_swiglu_quant_weight_nz_tensor_list.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_grouped_matmul_swiglu_quant.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_hamming_dist_top_k.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_kv_quant_sparse_flash_attention.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_mla_preprocess.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_mla_preprocess_nq.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_mla_preprocess_qdown.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_moe_init_routing_custom.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_ngram_spec_decode.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_npu_hc_pre.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_npu_moe_gating_top_k.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_recurrent_gated_delta_rule.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_recurrent_gated_delta_rule_310.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_reshape_and_cache_bnsd.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_store_kv_block.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_transpose_kv_cache_by_block.py
tests/e2e/nightly/single_node/ops/singlecard_ops/test_vocabparallelembedding.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/__init__.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_apply_penalties_triton.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_bad_words.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_batch_memcpy.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_bincount.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_causal_conv1d.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_chunk_gated_delta_rule.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_chunk_kda_npu.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_clear_ssm_states.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_compute_slot_mapping.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_compute_token_logprobs.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_compute_topk_logprobs.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_fused_gdn_gating.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_fused_qkvzba_split_reshape_cat.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_fused_recurrent_gated_delta_rule.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_fused_recurrent_kda_npu.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_fused_sigmoid_gating_delta_rule.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_l2norm.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_lightning_attn.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_log_softmax.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_min_p.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_mrope.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_muls_add.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_penality.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_post_update.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_postprocess_mamba.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_prepare_inputs_padded.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_rejection_sample.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_rope.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_split_qkv_rmsnorm_mrope.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_split_qkv_rmsnorm_rope.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_split_qkv_tp_rmsnorm_rope.py
tests/e2e/nightly/single_node/ops/singlecard_ops/triton/test_temperature.py
tests/e2e/prompts/example.txt
tests/e2e/prompts/long_prompt.txt
tests/e2e/prompts/qwen.png
tests/e2e/pull_request/__init__.py
tests/e2e/pull_request/utils.py
tests/e2e/pull_request/utils_310p.py
tests/e2e/pull_request/four_card/__init__.py
tests/e2e/pull_request/four_card/test_data_parallel_tp2.py
tests/e2e/pull_request/four_card/test_deepseek_v3_2_w8a8_pruning.py
tests/e2e/pull_request/four_card/test_deepseek_v4.py
tests/e2e/pull_request/four_card/test_graph_mode.py
tests/e2e/pull_request/four_card/test_pipeline_parallel.py
tests/e2e/pull_request/four_card/test_profiling_chunk_performance.py
tests/e2e/pull_request/four_card/test_qwen3_5.py
tests/e2e/pull_request/four_card/test_qwen3_next.py
tests/e2e/pull_request/four_card/_310p/__init__.py
tests/e2e/pull_request/four_card/_310p/test_dense_model_310p.py
tests/e2e/pull_request/four_card/_310p/test_moe_model_310p.py
tests/e2e/pull_request/four_card/_310p/test_vl_model_310p.py
tests/e2e/pull_request/four_card/context_parallel/__init__.py
tests/e2e/pull_request/four_card/context_parallel/test_accuracy.py
tests/e2e/pull_request/four_card/context_parallel/test_prefix_caching_cp.py
tests/e2e/pull_request/four_card/spec_decode/__init__.py
tests/e2e/pull_request/four_card/spec_decode/test_mtp_qwen3_next.py
tests/e2e/pull_request/one_card/__init__.py
tests/e2e/pull_request/one_card/test_attention_fa3.py
tests/e2e/pull_request/one_card/test_batch_invariant.py
tests/e2e/pull_request/one_card/test_camem.py
tests/e2e/pull_request/one_card/test_completion_with_prompt_embeds.py
tests/e2e/pull_request/one_card/test_cpu_offloading.py
tests/e2e/pull_request/one_card/test_cpu_weight_offload.py
tests/e2e/pull_request/one_card/test_guided_decoding.py
tests/e2e/pull_request/one_card/test_minicpm.py
tests/e2e/pull_request/one_card/test_multi_instance.py
tests/e2e/pull_request/one_card/test_multistream_overlap_shared_expert.py
tests/e2e/pull_request/one_card/test_npu_ipc_weight_transfer.py
tests/e2e/pull_request/one_card/test_qwen3_0_6b.py
tests/e2e/pull_request/one_card/test_qwen3_5_0_8b.py
tests/e2e/pull_request/one_card/test_qwen3_8b_w8a8.py
tests/e2e/pull_request/one_card/test_qwen3_embedding_0_6b.py
tests/e2e/pull_request/one_card/test_sampler.py
tests/e2e/pull_request/one_card/test_simple_cpu_offload.py
tests/e2e/pull_request/one_card/test_vlm.py
tests/e2e/pull_request/one_card/test_xlite.py
tests/e2e/pull_request/one_card/_310p/__init__.py
tests/e2e/pull_request/one_card/_310p/test_classification_310p.py
tests/e2e/pull_request/one_card/_310p/test_dense_model_310p.py
tests/e2e/pull_request/one_card/_310p/test_embedding_310p.py
tests/e2e/pull_request/one_card/_310p/test_scoring_310p.py
tests/e2e/pull_request/one_card/_310p/test_spec_decode_mtp_310p.py
tests/e2e/pull_request/one_card/_310p/test_vl_model_310p.py
tests/e2e/pull_request/one_card/aclgraph/__init__.py
tests/e2e/pull_request/one_card/compile/__init__.py
tests/e2e/pull_request/one_card/compile/backend.py
tests/e2e/pull_request/one_card/compile/test_graphex_norm_quant_fusion.py
tests/e2e/pull_request/one_card/compile/test_graphex_qknorm_rope_fusion.py
tests/e2e/pull_request/one_card/compile/test_norm_quant_fusion.py
tests/e2e/pull_request/one_card/lora/__init__.py
tests/e2e/pull_request/one_card/lora/test_ilama_lora.py
tests/e2e/pull_request/one_card/lora/test_llama32_lora.py
tests/e2e/pull_request/one_card/lora/test_lora_with_spec_decode.py
tests/e2e/pull_request/one_card/lora/test_olmoe_lora.py
tests/e2e/pull_request/one_card/lora/test_qwen35_densemodel_lora.py
tests/e2e/pull_request/one_card/lora/test_qwen3_multi_loras.py
tests/e2e/pull_request/one_card/lora/test_qwen3_reranker_lora.py
tests/e2e/pull_request/one_card/model_runner_v2/__init__.py
tests/e2e/pull_request/one_card/model_runner_v2/test_basic.py
tests/e2e/pull_request/one_card/model_runner_v2/test_uva.py
tests/e2e/pull_request/one_card/pooling/__init__.py
tests/e2e/pull_request/one_card/pooling/test_classification.py
tests/e2e/pull_request/one_card/pooling/test_embedding.py
tests/e2e/pull_request/one_card/pooling/test_scoring.py
tests/e2e/pull_request/one_card/pooling/template/qwen3_reranker.jinja
tests/e2e/pull_request/one_card/spec_decode/__init__.py
tests/e2e/pull_request/one_card/spec_decode/conftest.py
tests/e2e/pull_request/one_card/spec_decode/test_dflash.py
tests/e2e/pull_request/one_card/spec_decode/test_draft_parallel.py
tests/e2e/pull_request/one_card/spec_decode/test_eagle.py
tests/e2e/pull_request/one_card/spec_decode/test_extract_hidden_states.py
tests/e2e/pull_request/one_card/spec_decode/test_mtp_eagle_correctness.py
tests/e2e/pull_request/one_card/spec_decode/test_ngram.py
tests/e2e/pull_request/one_card/spec_decode/test_ngram_npu.py
tests/e2e/pull_request/one_card/spec_decode/test_suffix.py
tests/e2e/pull_request/one_card/spec_decode/utils.py
tests/e2e/pull_request/two_card/__init__.py
tests/e2e/pull_request/two_card/test_data_parallel.py
tests/e2e/pull_request/two_card/test_deepseek_multistream_moe.py
tests/e2e/pull_request/two_card/test_disaggregated_encoder.py
tests/e2e/pull_request/two_card/test_external_launcher.py
tests/e2e/pull_request/two_card/test_flashcomm_distributed.py
tests/e2e/pull_request/two_card/test_gpt_oss_distributed.py
tests/e2e/pull_request/two_card/test_hccl_weight_transfer.py
tests/e2e/pull_request/two_card/test_moe_routing_replay.py
tests/e2e/pull_request/two_card/test_offline_weight_load.py
tests/e2e/pull_request/two_card/test_prefix_caching.py
tests/e2e/pull_request/two_card/test_qwen3_30b_a3b.py
tests/e2e/pull_request/two_card/test_qwen3_5_35b_a3b_w8a8.py
tests/e2e/pull_request/two_card/test_qwen3_6_27b_fia.py
tests/e2e/pull_request/two_card/test_qwen3_moe_eplb.py
tests/e2e/pull_request/two_card/test_qwen3_performance.py
tests/e2e/pull_request/two_card/test_qwen3_vl_30b_a3b_instruct.py
tests/e2e/pull_request/two_card/test_sequence_parallelism_moe.py
tests/e2e/pull_request/two_card/test_shared_expert_dp.py
tests/e2e/pull_request/two_card/test_sp_pass.py
tests/e2e/pull_request/two_card/aclgraph/test_aclgraph_capture_replay.py
tests/e2e/pull_request/two_card/lora/__init__.py
tests/e2e/pull_request/two_card/lora/test_ilama_lora_tp2.py
tests/e2e/pull_request/two_card/lora/test_llama32_lora_tp2.py
tests/e2e/pull_request/two_card/lora/test_qwen3moe_lora_tp.py
tests/e2e/pull_request/two_card/spec_decode/__init__.py
tests/e2e/pull_request/two_card/spec_decode/test_spec_decode.py
tests/e2e/vllm_interface/vllm_test.cfg
tests/e2e/vllm_interface/singlecard/test_sampler.py
tests/e2e/weekly/multi_node/external_dp/config/DeepSeek-V4-Pro-w4a8-PD-no-prefix.yaml
tests/e2e/weekly/multi_node/external_dp/config/DeepSeek-V4-Pro-w4a8-prefix-cache-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/DeepSeek-V4-flash-w8a8-PD-no-prefix.yaml
tests/e2e/weekly/multi_node/external_dp/config/DeepSeek_V3.1T_MTP1_128K_1K_PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/DeepSeek_V3.1T_MTP1_3_5K_1_5K_PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/DeepSeek_V3.1T_MTP1_PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/DeepSeek_V3.1T_MTP3_PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/DeepSeek_V3.1T_layerwise_PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/DeepSeek_V3.2T_MTP2_PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/DeepSeek_V3.2T_MTP3_PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/GLM-5.1-W8A8C8-128k-1k-90-50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/GLM-5.1-W8A8C8-3.5k-1.5k-0-20-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/GLM-5.1-W8A8C8-3.5k-1.5k-0-50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/GLM-5.1-W8A8C8-64k-1k-90-50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/GLM-5.2-W4A8C8-128k-1k-90-50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/GLM-5.2-W4A8C8-3.5k-1.5k-0-20-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/GLM-5.2-W4A8C8-3.5k-1.5k-0-50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/GLM-5.2-W4A8C8-64k-1k-90-50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/GLM_5_1_PD_in32k_bs16-0.yaml
tests/e2e/weekly/multi_node/external_dp/config/GLM_5_1_PD_in32k_bs20-90.yaml
tests/e2e/weekly/multi_node/external_dp/config/GLM_5_1_PD_in64k_bs16-90.yaml
tests/e2e/weekly/multi_node/external_dp/config/Kimi-K2.5-W4A8-128k-1k-TPOT50.yaml
tests/e2e/weekly/multi_node/external_dp/config/Kimi-K2.5-W4A8-16k-1k-TPOT50.yaml
tests/e2e/weekly/multi_node/external_dp/config/Kimi-K2.6-W4A8-128k-1k-TPOT50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/Kimi-K2.6-W4A8-254k-1k-TPOT20-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/Kimi-K2.6-W4A8-3.5k-1.5k-TPOT50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/Kimi-K2.7-W4A8-128k-1k-TPOT50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/Kimi-K2.7-W4A8-254k-1k-TPOT20-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/Kimi-K2.7-W4A8-3.5k-1.5k-TPOT50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/Kimi-K2.7-W4A8-64k-1k-TPOT50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/MiniMax-PD-in32k-bs4-1.yaml
tests/e2e/weekly/multi_node/external_dp/config/Minimax_m2.7_in3_5_tpot20.yaml
tests/e2e/weekly/multi_node/external_dp/config/Minimax_m2.7_in3_5_tpot50.yaml
tests/e2e/weekly/multi_node/external_dp/config/Minimax_m2.7_in64k_1k_prefix90_tpot50.yaml
tests/e2e/weekly/multi_node/external_dp/config/QWEN3_235B_PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/QWEN3_235B_PD_3_5K_1_5k.yaml
tests/e2e/weekly/multi_node/external_dp/config/Qwen-3.5-397B-A17B-W8A8-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/Qwen3.5-397B-w4a8_128k-1k-90-50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/Qwen3.5-397B-w4a8_3.5k-1.5k-0-50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/Qwen3.5-397B-w4a8_64k-1k-90-50-PD.yaml
tests/e2e/weekly/multi_node/external_dp/config/Qwen3.5-397B-w4a8_986k-function-PD.yaml
tests/e2e/weekly/multi_node/internal_dp/config/DeepSeek-V3.yaml
tests/e2e/weekly/multi_node/internal_dp/config/DeepSeek-V3_2-W8A8-EP_weekly.yaml
tests/e2e/weekly/multi_node/internal_dp/config/GLM-4.7-W8A8C8-Mooncake-Layerwise.yaml
tests/e2e/weekly/multi_node/internal_dp/config/GLM-5.1-W8A8C8-A3_198k_function.yaml
tests/e2e/weekly/multi_node/internal_dp/config/GLM-5.1-W8A8C8-A3_3.5k_1.5k_0_50.yaml
tests/e2e/weekly/multi_node/internal_dp/config/GLM-5.1-W8A8C8-A3_64k_128k_90_50.yaml
tests/e2e/weekly/multi_node/internal_dp/config/GLM-5.2-W4A8C8-A3_198k_function.yaml
tests/e2e/weekly/multi_node/internal_dp/config/GLM-5.2-W4A8C8-A3_3.5k_1.5k_0_50.yaml
tests/e2e/weekly/multi_node/internal_dp/config/GLM-5.2-W4A8C8-A3_64k_128k_90_50.yaml
tests/e2e/weekly/single_node/configs/DeepSeek-V3.2-W8A8_A3_weekly.yaml
tests/e2e/weekly/single_node/configs/Deepseek_R1_W8A8_A3.yaml
tests/e2e/weekly/single_node/configs/Deepseek_R1_W8A8_Reasoning_output_A3.yaml
tests/e2e/weekly/single_node/configs/GLM-5.yaml
tests/e2e/weekly/single_node/configs/GLM-5_1-W8A8_A3_weekly.yaml
tests/e2e/weekly/single_node/configs/Kimi-K2.6-32k-512.yaml
tests/e2e/weekly/single_node/configs/Kimi-K2.6-w4a8-A3.yaml
tests/e2e/weekly/single_node/configs/Kimi-K2.6.yaml
tests/e2e/weekly/single_node/configs/Kimi-K2.7-w4a8-A3.yaml
tests/e2e/weekly/single_node/configs/MiniMax-M2.5-W8A8-A3.yaml
tests/e2e/weekly/single_node/configs/Minimax_m2.7_w8a8_A3.yaml
tests/e2e/weekly/single_node/configs/Qwen2.5-VL-7B-Instruct-EPD.yaml
tests/e2e/weekly/single_node/configs/Qwen3-14B-w8a8sc-310p.yaml
tests/e2e/weekly/single_node/configs/Qwen3-235B-A22B-W8A8_piecewise_fullgraph_A3.yaml
tests/e2e/weekly/single_node/configs/Qwen3-32B-w8a8sc-310p.yaml
tests/e2e/weekly/single_node/configs/Qwen3-32B.yaml
tests/e2e/weekly/single_node/configs/Qwen3-8B-w8a8sc-310p.yaml
tests/e2e/weekly/single_node/configs/Qwen3.5-122B-A10B-W8A8-A2.yaml
tests/e2e/weekly/single_node/configs/Qwen3.5-122B-A10B-W8A8-A3.yaml
tests/e2e/weekly/single_node/configs/Qwen3.5-27B-w8a8-A3.yaml
tests/e2e/weekly/single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3.yaml
tests/e2e/weekly/single_node/configs/Qwen3.5-397B-A17B-W8A8-mtp-A3_weekly.yaml
tests/e2e/weekly/single_node/configs/Qwen3.5-397B-A17B-w8a8-3.5k-1.5k-0-50-single.yaml
tests/e2e/weekly/single_node/configs/Qwen3.5-397B-A17B-w8a8-64k-1k-90-50-single.yaml
tests/e2e/weekly/single_node/configs/Qwen3.6-35B-A3B-w4a8-A3.yaml
tests/e2e/weekly/single_node/configs/Qwen3.6-35B-A3B-w8a8-A3-accuracy.yaml
tests/e2e/weekly/single_node/configs/Qwen3_235b_w8a8_A5.yaml
tests/e2e/weekly/single_node/configs/Qwen3_32b_W8A8_wl_A3.yaml
tests/e2e/weekly/single_node/configs/Qwen3_32b_w8a8_ml_A3.yaml
tests/e2e/weekly/single_node/configs/Qwq_32b_A3.yaml
tests/e2e/weekly/single_node/configs/qwen_3_6_27b_w8a8_A3.yaml
tests/e2e/weekly/single_node/engine_func_test_robot/__init__.py
tests/e2e/weekly/single_node/engine_func_test_robot/conftest.py
tests/e2e/weekly/single_node/engine_func_test_robot/tests/chat_template_kwargs/__init__.py
tests/e2e/weekly/single_node/engine_func_test_robot/tests/chat_template_kwargs/test_chat_template_kwargs_abnormal.py
tests/e2e/weekly/single_node/engine_func_test_robot/tests/chat_template_kwargs/test_chat_template_kwargs_boundary.py
tests/e2e/weekly/single_node/engine_func_test_robot/tests/chat_template_kwargs/test_chat_template_kwargs_normal.py
tests/e2e/weekly/single_node/engine_func_test_robot/tests/chat_template_kwargs/test_chat_template_kwargs_thinking.py
tests/e2e/weekly/single_node/engine_func_test_robot/tests/content/__init__.py
tests/e2e/weekly/single_node/engine_func_test_robot/tests/content/test_content_abnormal.py
tests/e2e/weekly/single_node/engine_func_test_robot/tests/content/test_content_boundary.py
tests/e2e/weekly/single_node/engine_func_test_robot/tests/content/test_content_normal.py
tests/e2e/weekly/single_node/engine_func_test_robot/utility/__init__.py
tests/e2e/weekly/single_node/engine_func_test_robot/utility/assertion.py
tests/e2e/weekly/single_node/engine_func_test_robot/utility/http_client.py
tests/e2e/weekly/single_node/engine_func_test_robot/utility/request_helper.py
tests/e2e/weekly/single_node/models/test_qwen3_30b_acc.py
tests/ut/__init__.py
tests/ut/base.py
tests/ut/conftest.py
tests/ut/test_ascend_config.py
tests/ut/test_ascend_forward_context.py
tests/ut/test_batch_invariant.py
tests/ut/test_compressed_prefix_cache.py
tests/ut/test_cpu_binding.py
tests/ut/test_envs.py
tests/ut/test_flash_common3_context.py
tests/ut/test_logger.py
tests/ut/test_meta_registration.py
tests/ut/test_platform.py
tests/ut/test_profiling_config.py
tests/ut/test_utils.py
tests/ut/_310p/__init__.py
tests/ut/_310p/test_block_table_310p.py
tests/ut/_310p/test_kv_block_zeroer_310p.py
tests/ut/_310p/test_mamba_align_fallback_310p_source.py
tests/ut/_310p/test_model_runner_310p.py
tests/ut/_310p/test_sharded_state_loader_310p.py
tests/ut/_310p/attention/__init__.py
tests/ut/_310p/attention/test_attention_mask_310.py
tests/ut/_310p/attention/test_attention_v1_310.py
tests/ut/_310p/fused_moe/__init__.py
tests/ut/_310p/fused_moe/test_experts_selector_310.py
tests/ut/_310p/fused_moe/test_moe_mlp_310.py
tests/ut/_310p/fused_moe/test_shared_fused_moe_310.py
tests/ut/_310p/ops/__init__.py
tests/ut/_310p/ops/test_chunk_gated_delta_rule_310.py
tests/ut/_310p/ops/test_conv_310.py
tests/ut/_310p/ops/test_gdn_310.py
tests/ut/_310p/ops/test_layernorm_310.py
tests/ut/_310p/ops/test_mm_encoder_attention_310.py
tests/ut/_310p/ops/test_rotary_embedding_310.py
tests/ut/_310p/quantization/__init__.py
tests/ut/_310p/quantization/test_modelslim_config_310.py
tests/ut/_310p/quantization/test_w8a8_dynamic_310.py
tests/ut/_310p/quantization/test_w8a8_static_310.py
tests/ut/_310p/quantization/test_w8a8s_310.py
tests/ut/_310p/quantization/test_w8a8sc_310.py
tests/ut/_310p/sample/__init__.py
tests/ut/_310p/sample/test_sampler_310.py
tests/ut/_310p/spec_decode/test_llm_base_proposer_310.py
tests/ut/_fake_weight/__init__.py
tests/ut/_fake_weight/config.json
tests/ut/_tools/__init__.py
tests/ut/_tools/test_ai_qos_tool.py
tests/ut/_tools/test_docs_codegen.py
tests/ut/attention/__init__.py
tests/ut/attention/test_attention_fa3.py
tests/ut/attention/test_attention_mask.py
tests/ut/attention/test_sfa_cp.py
tests/ut/attention/test_sfa_o_proj_tp.py
tests/ut/attention/utils.py
tests/ut/attention/a2/__init__.py
tests/ut/attention/a2/test_attention_cp.py
tests/ut/attention/a2/test_attention_cp_precision.py
tests/ut/attention/a2/test_attention_v1.py
tests/ut/attention/a2/test_attention_v1_precision.py
tests/ut/attention/a2/test_common_cp.py
tests/ut/attention/a2/test_mla_cp.py
tests/ut/attention/a2/test_mla_cp_precision.py
tests/ut/attention/a2/test_mla_precision.py
tests/ut/attention/a2/test_mla_v1.py
tests/ut/attention/a2/test_sfa_cp_precision.py
tests/ut/attention/a2/test_sfa_v1.py
tests/ut/attention/a2/test_sfa_v1_precision.py
tests/ut/compilation/__init__.py
tests/ut/compilation/test_npugraph_ex_utils_check.py
tests/ut/compilation/a2/__init__.py
tests/ut/compilation/a2/test_acl_graph.py
tests/ut/core/__init__.py
tests/ut/core/test_profiling_chunk.py
tests/ut/core/test_recompute_scheduler.py
tests/ut/device/__init__.py
tests/ut/device/test_device_op.py
tests/ut/device_allocator/__init__.py
tests/ut/device_allocator/test_camem.py
tests/ut/device_allocator/test_cpu_binding.py
tests/ut/device_allocator/test_sleep_mem_optimized.py
tests/ut/device_allocator/a2/__init__.py
tests/ut/device_allocator/a2/test_find_loaded_library.py
tests/ut/distributed/__init__.py
tests/ut/distributed/test_communicator.py
tests/ut/distributed/test_parallel_state.py
tests/ut/distributed/ascend_store/__init__.py
tests/ut/distributed/ascend_store/_mock_deps.py
tests/ut/distributed/ascend_store/test_ascend_store_connector.py
tests/ut/distributed/ascend_store/test_backend.py
tests/ut/distributed/ascend_store/test_config_data.py
tests/ut/distributed/ascend_store/test_coordinator.py
tests/ut/distributed/ascend_store/test_kv_transfer.py
tests/ut/distributed/ascend_store/test_pool_scheduler.py
tests/ut/distributed/ascend_store/test_pool_worker.py
tests/ut/distributed/device_communicators/__init__.py
tests/ut/distributed/device_communicators/test_pyhccl.py
tests/ut/distributed/device_communicators/test_pyhccl_wrapper.py
tests/ut/distributed/kv_transfer/test_kv_transfer_failures.py
tests/ut/distributed/mooncake/__init__.py
tests/ut/distributed/mooncake/test_mooncake_config_data.py
tests/ut/distributed/mooncake/test_mooncake_kv_transfer.py
tests/ut/distributed/weight_transfer/__init__.py
tests/ut/distributed/weight_transfer/test_npu_ipc_engine.py
tests/ut/eplb/__init__.py
tests/ut/eplb/test_eplb_updator.py
tests/ut/eplb/adaptor/__init__.py
tests/ut/eplb/adaptor/test_vllm_adaptor.py
tests/ut/eplb/core/__init__.py
tests/ut/eplb/core/test_eplb_device_transfer_loader.py
tests/ut/eplb/core/a2/__init__.py
tests/ut/eplb/core/a2/expert_map.json
tests/ut/eplb/core/a2/test_eplb_utils.py
tests/ut/eplb/core/policy/__init__.py
tests/ut/eplb/core/policy/test_policy_factory.py
tests/ut/kv_offload/__init__.py
tests/ut/kv_offload/test_mooncake_connector.py
tests/ut/kv_offload/test_mooncake_hybrid_connector.py
tests/ut/kv_offload/test_mooncake_layerwise_connector.py
tests/ut/kv_offload/test_recompute_cpu_offload.py
tests/ut/kv_offload/utils.py
tests/ut/kv_offload/a2/__init__.py
tests/ut/kv_offload/a2/test_remote_decode_lifecycle.py
tests/ut/kv_offload/a2/test_remote_prefill_lifecycle.py
tests/ut/lora/__init__.py
tests/ut/lora/test_lora.py
tests/ut/model_loader/__init__.py
tests/ut/model_loader/netloader/__init__.py
tests/ut/model_loader/netloader/test_netloader.py
tests/ut/model_loader/netloader/test_netloader_elastic.py
tests/ut/model_loader/netloader/test_netloader_load.py
tests/ut/model_loader/netloader/test_netloader_utils.py
tests/ut/model_loader/rfork/test_rfork_loader.py
tests/ut/model_loader/rfork/test_transfer_backend.py
tests/ut/ops/__init__.py
tests/ut/ops/test_comm_utils.py
tests/ut/ops/test_flashcomm2_oshard_manager.py
tests/ut/ops/test_fused_moe.py
tests/ut/ops/test_gate_linear.py
tests/ut/ops/test_gdn_attn_builder.py
tests/ut/ops/test_layer_shard_linear.py
tests/ut/ops/test_layernorm.py
tests/ut/ops/test_linear.py
tests/ut/ops/test_mla.py
tests/ut/ops/test_mm_encoder_attention.py
tests/ut/ops/test_moe_comm_method.py
tests/ut/ops/test_moe_mlp.py
tests/ut/ops/test_moe_runtime_args.py
tests/ut/ops/test_prepare_finalize.py
tests/ut/ops/test_rotary_embedding.py
tests/ut/ops/test_vocab_parallel_embedding.py
tests/ut/ops/a2/__init__.py
tests/ut/ops/a2/test_gdn_chunk_meta.py
tests/ut/ops/a2/test_token_dispatcher.py
tests/ut/ops/a2/test_weight_prefetch.py
tests/ut/ops/a3_2/__init__.py
tests/ut/ops/a3_2/test_activation.py
tests/ut/ops/a3_2/test_select_experts.py
tests/ut/patch/__init__.py
tests/ut/patch/platform/__init__.py
tests/ut/patch/platform/test_deepseek_v4_thinking.py
tests/ut/patch/platform/test_patch_async_swa_kv_lifetime.py
tests/ut/patch/platform/test_patch_balance_schedule.py
tests/ut/patch/platform/test_patch_deepseek_v4_tool_call_parser.py
tests/ut/patch/platform/test_patch_glm47_tool_call_parser.py
tests/ut/patch/platform/test_patch_glm_tool_call_streaming.py
tests/ut/patch/platform/test_patch_minimax_m2_tool_call_parser.py
tests/ut/patch/platform/test_patch_minimax_usage_accounting.py
tests/ut/patch/platform/test_patch_pp_mtp.py
tests/ut/patch/platform/test_patch_shm_broadcast.py
tests/ut/patch/platform/test_patch_structured_output.py
tests/ut/patch/platform/test_patch_tool_choice_none_content.py
tests/ut/patch/platform/test_prefix_cache_cp_patches.py
tests/ut/patch/worker/__init__.py
tests/ut/patch/worker/test_patch_deepseek_v2.py
tests/ut/patch/worker/test_patch_eagle3_pp_aux.py
tests/ut/patch/worker/test_patch_qwen3_5_mtp.py
tests/ut/patch/worker/test_patch_routed_experts_capture.py
tests/ut/patch/worker/patch_common/__init__.py
tests/ut/patch/worker/patch_common/test_hccl_pg_registry.py
tests/ut/patch/worker/patch_common/test_patch_distributed.py
tests/ut/profiler/__init__.py
tests/ut/profiler/test_torch_npu_profiler.py
tests/ut/quantization/__init__.py
tests/ut/quantization/conftest_quantization.py
tests/ut/quantization/test_compressed_tensors_config.py
tests/ut/quantization/test_method_adapters.py
tests/ut/quantization/test_modelslim_config.py
tests/ut/quantization/test_quant_parser.py
tests/ut/quantization/test_utils.py
tests/ut/quantization/methods/__init__.py
tests/ut/quantization/methods/test_kv_c8.py
tests/ut/quantization/methods/test_moe_logical_experts.py
tests/ut/quantization/methods/test_registry.py
tests/ut/quantization/methods/test_w4a16_mxfp4.py
tests/ut/quantization/methods/test_w4a4_mxfp4.py
tests/ut/quantization/methods/test_w4a4_mxfp4_flatquant_dynamic.py
tests/ut/quantization/methods/test_w8a8_mxfp8.py
tests/ut/quantization/methods/test_w8a8_pdmix.py
tests/ut/quantization/methods/test_w8a8fp8_dynamic.py
tests/ut/quantization/methods/a2/__init__.py
tests/ut/quantization/methods/a2/test_w4a16.py
tests/ut/quantization/methods/a2/test_w4a4_flatquant.py
tests/ut/quantization/methods/a2/test_w4a4_laos_dynamic.py
tests/ut/quantization/methods/a2/test_w4a8.py
tests/ut/quantization/methods/a2/test_w8a16.py
tests/ut/quantization/methods/a2/test_w8a8_dynamic.py
tests/ut/quantization/methods/a2/test_w8a8_static.py
tests/ut/sample/__init__.py
tests/ut/sample/test_rejection_sampler.py
tests/ut/sample/test_sampler.py
tests/ut/sample/a2/test_gumbel_sampling.py
tests/ut/spec_decode/__init__.py
tests/ut/spec_decode/test_extract_hidden_states_proposer.py
tests/ut/spec_decode/test_llm_base_proposer.py
tests/ut/spec_decode/test_speculators_vwn_eagle3.py
tests/ut/spec_decode/test_step3p5_source_regression.py
tests/ut/spec_decode/test_utils.py
tests/ut/spec_decode/a2/__init__.py
tests/ut/spec_decode/a2/test_eagle_proposer.py
tests/ut/worker/__init__.py
tests/ut/worker/test_dsv4_compressed_positions.py
tests/ut/worker/test_encoder_acl_graph.py
tests/ut/worker/test_pcp_manager.py
tests/ut/worker/test_utils.py
tests/ut/worker/a2/__init__.py
tests/ut/worker/a2/test_block_table.py
tests/ut/worker/a2/test_kvcomp_utils.py
tests/ut/worker/a2/test_model_runner_v1.py
tests/ut/worker/a2/test_model_runner_v1_with_device.py
tests/ut/worker/a2/test_worker_multi_instance.py
tests/ut/worker/a2/test_worker_v1.py
tests/ut/xlite/__init__.py
tests/ut/xlite/test_xlite.py
tools/actionlint.sh
tools/ai_qos.py
tools/aisbench.py
tools/check_boolean_context_manager.py
tools/check_forbidden_imports.py
tools/check_logger.sh
tools/check_long_functions.py
tools/check_python_src_init.py
tools/check_repo.sh
tools/collect_user_first_contribution.sh
tools/format_contributors.py
tools/mooncake_installer.sh
tools/mypy.sh
tools/png-lint.sh
tools/send_mm_request.py
tools/send_request.py
tools/shellcheck.sh
tools/sphinx-lint.sh
tools/vllm_bench.py
tools/ai_qos/CMakeLists.txt
tools/ai_qos/ai_qos.cpp
tools/docs_codegen/__init__.py
tools/docs_codegen/cli.py
tools/docs_codegen/converters.py
tools/docs_codegen/errors.py
tools/docs_codegen/generator.py
tools/docs_codegen/scanner.py
tools/docs_codegen/sphinx_extension.py
tools/docs_codegen/utils.py
tools/docs_codegen/yaml_loader.py
tools/docs_i18n/__init__.py
tools/docs_i18n/sphinx_extension.py
vllm_ascend/__init__.py
vllm_ascend/_version.py
vllm_ascend/ascend_config.py
vllm_ascend/ascend_forward_context.py
vllm_ascend/batch_invariant.py
vllm_ascend/cpu_binding.py
vllm_ascend/envs.py
vllm_ascend/flash_common3_context.py
vllm_ascend/logger.py
vllm_ascend/memcache_comm_fence.py
vllm_ascend/meta_registration.py
vllm_ascend/platform.py
vllm_ascend/profiling_config.py
vllm_ascend/utils.py
vllm_ascend.egg-info/PKG-INFO
vllm_ascend.egg-info/SOURCES.txt
vllm_ascend.egg-info/dependency_links.txt
vllm_ascend.egg-info/entry_points.txt
vllm_ascend.egg-info/requires.txt
vllm_ascend.egg-info/top_level.txt
vllm_ascend/_310p/__init__.py
vllm_ascend/_310p/block_table.py
vllm_ascend/_310p/kv_block_zeroer.py
vllm_ascend/_310p/model_runner_310p.py
vllm_ascend/_310p/npu_input_batch.py
vllm_ascend/_310p/sharded_state_loader_310p.py
vllm_ascend/_310p/worker_310p.py
vllm_ascend/_310p/attention/__init__.py
vllm_ascend/_310p/attention/attention_mask.py
vllm_ascend/_310p/attention/attention_v1.py
vllm_ascend/_310p/attention/metadata_builder.py
vllm_ascend/_310p/fused_moe/__init__.py
vllm_ascend/_310p/fused_moe/experts_selector.py
vllm_ascend/_310p/fused_moe/fused_moe.py
vllm_ascend/_310p/fused_moe/moe_comm_method.py
vllm_ascend/_310p/fused_moe/moe_mlp.py
vllm_ascend/_310p/fused_moe/token_dispatcher.py
vllm_ascend/_310p/ops/__init__.py
vllm_ascend/_310p/ops/activation.py
vllm_ascend/_310p/ops/causal_conv1d.py
vllm_ascend/_310p/ops/conv.py
vllm_ascend/_310p/ops/gdn_attn_builder_310.py
vllm_ascend/_310p/ops/layernorm.py
vllm_ascend/_310p/ops/mm_encoder_attention.py
vllm_ascend/_310p/ops/qwen3vl_310.py
vllm_ascend/_310p/ops/rotary_embedding.py
vllm_ascend/_310p/ops/vocab_parallel_embedding.py
vllm_ascend/_310p/ops/fla/__init__.py
vllm_ascend/_310p/ops/fla/chunk_gated_delta_rule.py
vllm_ascend/_310p/ops/fla/cumpute_causal_conv1d_metadata_310.py
vllm_ascend/_310p/ops/fla/fused_gdn_gating.py
vllm_ascend/_310p/ops/fla/fused_recurrent_gated_delta_rule.py
vllm_ascend/_310p/ops/fla/gdn_310.py
vllm_ascend/_310p/ops/fla/idex.py
vllm_ascend/_310p/ops/fla/l2norm.py
vllm_ascend/_310p/quantization/__init__.py
vllm_ascend/_310p/quantization/modelslim_config.py
vllm_ascend/_310p/quantization/methods/__init__.py
vllm_ascend/_310p/quantization/methods/registry.py
vllm_ascend/_310p/quantization/methods/w8a8_base.py
vllm_ascend/_310p/quantization/methods/w8a8_dynamic.py
vllm_ascend/_310p/quantization/methods/w8a8_static.py
vllm_ascend/_310p/quantization/methods/w8a8s.py
vllm_ascend/_310p/quantization/methods/w8a8sc.py
vllm_ascend/_310p/sample/__init__.py
vllm_ascend/_310p/sample/rejection_sampler.py
vllm_ascend/_310p/sample/sampler.py
vllm_ascend/_310p/spec_decode/__init__.py
vllm_ascend/_310p/spec_decode/llm_base_proposer_310.py
vllm_ascend/_cann_ops_custom/.gitkeep
vllm_ascend/attention/__init__.py
vllm_ascend/attention/abstract.py
vllm_ascend/attention/attention_mask.py
vllm_ascend/attention/attention_v1.py
vllm_ascend/attention/dsa_v1.py
vllm_ascend/attention/fa3_v1.py
vllm_ascend/attention/mla_v1.py
vllm_ascend/attention/sfa_v1.py
vllm_ascend/attention/utils.py
vllm_ascend/attention/context_parallel/__init__.py
vllm_ascend/attention/context_parallel/attention_cp.py
vllm_ascend/attention/context_parallel/common_cp.py
vllm_ascend/attention/context_parallel/dsa_cp.py
vllm_ascend/attention/context_parallel/mla_cp.py
vllm_ascend/attention/context_parallel/sfa_cp.py
vllm_ascend/attention/kvcomp_attn/__init__.py
vllm_ascend/attention/kvcomp_attn/attention_utils.py
vllm_ascend/compilation/__init__.py
vllm_ascend/compilation/acl_graph.py
vllm_ascend/compilation/compiler_interface.py
vllm_ascend/compilation/graph_fusion_pass_manager.py
vllm_ascend/compilation/passes/__init__.py
vllm_ascend/compilation/passes/allgather_chunk_noop_pass.py
vllm_ascend/compilation/passes/allreduce_rmsnorm_fusion_pass.py
vllm_ascend/compilation/passes/base_pattern.py
vllm_ascend/compilation/passes/muls_add_pass.py
vllm_ascend/compilation/passes/noop_elimination.py
vllm_ascend/compilation/passes/norm_quant_fusion_pass.py
vllm_ascend/compilation/passes/qknorm_rope_fusion_pass.py
vllm_ascend/compilation/passes/sequence_parallelism.py
vllm_ascend/compilation/passes/sequence_parallelism_moe.py
vllm_ascend/compilation/passes/utils/__init__.py
vllm_ascend/compilation/passes/utils/npugraph_ex_utils_check.py
vllm_ascend/core/__init__.py
vllm_ascend/core/kv_cache_interface.py
vllm_ascend/core/profiling_chunk_predictor.py
vllm_ascend/core/recompute_scheduler.py
vllm_ascend/core/scheduler_dynamic_batch.py
vllm_ascend/core/scheduler_profiling_chunk.py
vllm_ascend/core/single_type_kv_cache_manager.py
vllm_ascend/device/__init__.py
vllm_ascend/device/device_op.py
vllm_ascend/device/mxfp_compat.py
vllm_ascend/device/utils.py
vllm_ascend/device_allocator/__init__.py
vllm_ascend/device_allocator/camem.py
vllm_ascend/device_allocator/sleep_mem_optimized.py
vllm_ascend/distributed/__init__.py
vllm_ascend/distributed/parallel_state.py
vllm_ascend/distributed/utils.py
vllm_ascend/distributed/device_communicators/__init__.py
vllm_ascend/distributed/device_communicators/npu_communicator.py
vllm_ascend/distributed/device_communicators/pyhccl.py
vllm_ascend/distributed/device_communicators/pyhccl_wrapper.py
vllm_ascend/distributed/kv_transfer/__init__.py
vllm_ascend/distributed/kv_transfer/ascend_multi_connector.py
vllm_ascend/distributed/kv_transfer/kv_p2p/__init__.py
vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake_connector.py
vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake_hybrid_connector.py
vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake_layerwise_connector.py
vllm_ascend/distributed/kv_transfer/kv_pool/__init__.py
vllm_ascend/distributed/kv_transfer/kv_pool/lmcache_ascend_connector.py
vllm_ascend/distributed/kv_transfer/kv_pool/ucm_connector.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/__init__.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/ascend_store_connector.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/config_data.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/coordinator.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/kv_transfer.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/pool_scheduler.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/pool_worker.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/backend/__init__.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/backend/backend.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/backend/memcache_backend.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/backend/mooncake_backend.py
vllm_ascend/distributed/kv_transfer/kv_pool/ascend_store/backend/yuanrong_backend.py
vllm_ascend/distributed/kv_transfer/kv_pool/cpu_offload/__init__.py
vllm_ascend/distributed/kv_transfer/kv_pool/cpu_offload/cpu_kv_cache_manager.py
vllm_ascend/distributed/kv_transfer/kv_pool/cpu_offload/cpu_offload_connector.py
vllm_ascend/distributed/kv_transfer/kv_pool/cpu_offload/metadata.py
vllm_ascend/distributed/kv_transfer/kv_pool/recompute_cpu_offload/__init__.py
vllm_ascend/distributed/kv_transfer/kv_pool/recompute_cpu_offload/manager.py
vllm_ascend/distributed/kv_transfer/kv_pool/recompute_cpu_offload/metadata.py
vllm_ascend/distributed/kv_transfer/kv_pool/recompute_cpu_offload/recompute_cpu_offload_connector.py
vllm_ascend/distributed/kv_transfer/kv_pool/recompute_cpu_offload/worker.py
vllm_ascend/distributed/kv_transfer/kv_pool/simple_cpu_offload/__init__.py
vllm_ascend/distributed/kv_transfer/kv_pool/simple_cpu_offload/simple_cpu_offload_connector.py
vllm_ascend/distributed/kv_transfer/utils/__init__.py
vllm_ascend/distributed/kv_transfer/utils/mooncake_transfer_engine.py
vllm_ascend/distributed/kv_transfer/utils/utils.py
vllm_ascend/distributed/weight_transfer/__init__.py
vllm_ascend/distributed/weight_transfer/hccl_engine.py
vllm_ascend/distributed/weight_transfer/npu_ipc_engine.py
vllm_ascend/distributed/weight_transfer/packed_tensor.py
vllm_ascend/eplb/__init__.py
vllm_ascend/eplb/eplb_updator.py
vllm_ascend/eplb/adaptor/__init__.py
vllm_ascend/eplb/adaptor/vllm_adaptor.py
vllm_ascend/eplb/core/__init__.py
vllm_ascend/eplb/core/eplb_device_transfer_loader.py
vllm_ascend/eplb/core/eplb_utils.py
vllm_ascend/eplb/core/eplb_worker.py
vllm_ascend/eplb/core/policy/__init__.py
vllm_ascend/eplb/core/policy/policy_abstract.py
vllm_ascend/eplb/core/policy/policy_default_eplb.py
vllm_ascend/eplb/core/policy/policy_factory.py
vllm_ascend/eplb/core/policy/policy_flashlb.py
vllm_ascend/eplb/core/policy/policy_random.py
vllm_ascend/eplb/core/policy/policy_swift_balancer.py
vllm_ascend/kv_offload/__init__.py
vllm_ascend/kv_offload/cpu_npu.py
vllm_ascend/kv_offload/npu.py
vllm_ascend/lora/__init__.py
vllm_ascend/lora/fused_moe.py
vllm_ascend/lora/lora_ops.py
vllm_ascend/lora/punica_npu.py
vllm_ascend/lora/utils.py
vllm_ascend/model_executor/__init__.py
vllm_ascend/model_executor/offloader/__init__.py
vllm_ascend/model_executor/offloader/prefetch.py
vllm_ascend/model_loader/__init__.py
vllm_ascend/model_loader/netloader/__init__.py
vllm_ascend/model_loader/netloader/load.py
vllm_ascend/model_loader/netloader/netloader.py
vllm_ascend/model_loader/netloader/utils.py
vllm_ascend/model_loader/netloader/executor/__init__.py
vllm_ascend/model_loader/netloader/executor/elastic_load.py
vllm_ascend/model_loader/netloader/executor/netloader_pg.py
vllm_ascend/model_loader/netloader/interaction/__init__.py
vllm_ascend/model_loader/netloader/interaction/elastic.py
vllm_ascend/model_loader/rfork/__init__.py
vllm_ascend/model_loader/rfork/rfork_loader.py
vllm_ascend/model_loader/rfork/rfork_worker.py
vllm_ascend/model_loader/rfork/seed_protocol.py
vllm_ascend/model_loader/rfork/seed_server.py
vllm_ascend/model_loader/rfork/transfer_backend.py
vllm_ascend/models/__init__.py
vllm_ascend/models/deepseek_v4.py
vllm_ascend/models/deepseek_v4_mtp.py
vllm_ascend/models/llama_eagle3_vwn.py
vllm_ascend/models/layer/__init__.py
vllm_ascend/models/layer/attention/__init__.py
vllm_ascend/models/layer/attention/layer.py
vllm_ascend/ops/__init__.py
vllm_ascend/ops/activation.py
vllm_ascend/ops/bailing_moe_linear_attn.py
vllm_ascend/ops/conv.py
vllm_ascend/ops/cv_linear.py
vllm_ascend/ops/dsa.py
vllm_ascend/ops/flashcomm2_oshard_manager.py
vllm_ascend/ops/gdn.py
vllm_ascend/ops/gdn_attn_builder.py
vllm_ascend/ops/layer_shard_linear.py
vllm_ascend/ops/layernorm.py
vllm_ascend/ops/linear.py
vllm_ascend/ops/linear_op.py
vllm_ascend/ops/mhc.py
vllm_ascend/ops/mla.py
vllm_ascend/ops/mm_encoder_attention.py
vllm_ascend/ops/qwen2_decoder.py
vllm_ascend/ops/register_custom_ops.py
vllm_ascend/ops/rel_pos_attention.py
vllm_ascend/ops/rope_dsv4.py
vllm_ascend/ops/rotary_embedding.py
vllm_ascend/ops/vocab_parallel_embedding.py
vllm_ascend/ops/weight_prefetch.py
vllm_ascend/ops/fused_moe/__init__.py
vllm_ascend/ops/fused_moe/comm_utils.py
vllm_ascend/ops/fused_moe/experts_selector.py
vllm_ascend/ops/fused_moe/fused_moe.py
vllm_ascend/ops/fused_moe/fused_moe_0_23_0.py
vllm_ascend/ops/fused_moe/gate_linear.py
vllm_ascend/ops/fused_moe/moe_comm_method.py
vllm_ascend/ops/fused_moe/moe_mlp.py
vllm_ascend/ops/fused_moe/moe_runtime_args.py
vllm_ascend/ops/fused_moe/moe_stage_contracts.py
vllm_ascend/ops/fused_moe/moe_stage_params.py
vllm_ascend/ops/fused_moe/prepare_finalize.py
vllm_ascend/ops/fused_moe/token_dispatcher.py
vllm_ascend/ops/triton/__init__.py
vllm_ascend/ops/triton/batch_memcpy.py
vllm_ascend/ops/triton/bincount.py
vllm_ascend/ops/triton/fused_gdn_gating.py
vllm_ascend/ops/triton/layernorm_gated.py
vllm_ascend/ops/triton/mul_add.py
vllm_ascend/ops/triton/muls_add.py
vllm_ascend/ops/triton/penalty.py
vllm_ascend/ops/triton/reject_sample.py
vllm_ascend/ops/triton/rms_norm.py
vllm_ascend/ops/triton/rope.py
vllm_ascend/ops/triton/triton_utils.py
vllm_ascend/ops/triton/activation/__init__.py
vllm_ascend/ops/triton/activation/swiglu_quant.py
vllm_ascend/ops/triton/batch_invariant/__init__.py
vllm_ascend/ops/triton/batch_invariant/matmul.py
vllm_ascend/ops/triton/batch_invariant/mean.py
vllm_ascend/ops/triton/batch_invariant/rmsnorm.py
vllm_ascend/ops/triton/batch_invariant/softmax.py
vllm_ascend/ops/triton/fla/__init__.py
vllm_ascend/ops/triton/fla/chunk.py
vllm_ascend/ops/triton/fla/chunk_delta_h.py
vllm_ascend/ops/triton/fla/chunk_delta_hupdate.py
vllm_ascend/ops/triton/fla/chunk_o.py
vllm_ascend/ops/triton/fla/chunk_o_update.py
vllm_ascend/ops/triton/fla/chunk_scaled_dot_kkt.py
vllm_ascend/ops/triton/fla/cumsum.py
vllm_ascend/ops/triton/fla/fused_qkvzba_split_reshape.py
vllm_ascend/ops/triton/fla/l2norm.py
vllm_ascend/ops/triton/fla/layernorm_guard.py
vllm_ascend/ops/triton/fla/sigmoid_gating.py
vllm_ascend/ops/triton/fla/solve_tril.py
vllm_ascend/ops/triton/fla/utils.py
vllm_ascend/ops/triton/fla/wy_fast.py
vllm_ascend/ops/triton/kda/__init__.py
vllm_ascend/ops/triton/kda/chunk_delta_h.py
vllm_ascend/ops/triton/kda/cumsum.py
vllm_ascend/ops/triton/kda/fused_recurrent_kda.py
vllm_ascend/ops/triton/kda/kda.py
vllm_ascend/ops/triton/kda/l2norm.py
vllm_ascend/ops/triton/kda/solve_tril.py
vllm_ascend/ops/triton/kda/utils.py
vllm_ascend/ops/triton/linearnorm/__init__.py
vllm_ascend/ops/triton/linearnorm/split_qkv_rmsnorm_mrope.py
vllm_ascend/ops/triton/linearnorm/split_qkv_rmsnorm_rope.py
vllm_ascend/ops/triton/linearnorm/split_qkv_rmsnorm_rope_simt.py
vllm_ascend/ops/triton/linearnorm/split_qkv_tp_rmsnorm_rope.py
vllm_ascend/ops/triton/mamba/__init__.py
vllm_ascend/ops/triton/mamba/causal_conv1d.py
vllm_ascend/ops/triton/mamba/lightning_attn.py
vllm_ascend/ops/triton/mamba/postprocess.py
vllm_ascend/ops/triton/spec_decode/__init__.py
vllm_ascend/ops/triton/spec_decode/utils.py
vllm_ascend/patch/__init__.py
vllm_ascend/patch/platform/__init__.py
vllm_ascend/patch/platform/patch_async_swa_kv_lifetime.py
vllm_ascend/patch/platform/patch_balance_schedule.py
vllm_ascend/patch/platform/patch_camem_allocator.py
vllm_ascend/patch/platform/patch_deepseek_v4_tool_call_parser.py
vllm_ascend/patch/platform/patch_distributed.py
vllm_ascend/patch/platform/patch_dp_device_ids.py
vllm_ascend/patch/platform/patch_fused_moe.py
vllm_ascend/patch/platform/patch_glm47_tool_call_parser.py
vllm_ascend/patch/platform/patch_glm_tool_call_streaming.py
vllm_ascend/patch/platform/patch_kv_cache_coordinator.py
vllm_ascend/patch/platform/patch_kv_cache_utils.py
vllm_ascend/patch/platform/patch_mamba_config.py
vllm_ascend/patch/platform/patch_mamba_config_310.py
vllm_ascend/patch/platform/patch_mamba_manager.py
vllm_ascend/patch/platform/patch_minimax_m2_config.py
vllm_ascend/patch/platform/patch_minimax_m2_tool_call_parser.py
vllm_ascend/patch/platform/patch_minimax_usage_accounting.py
vllm_ascend/patch/platform/patch_mla_prefill_backend.py
vllm_ascend/patch/platform/patch_multiproc_executor.py
vllm_ascend/patch/platform/patch_pp_mtp.py
vllm_ascend/patch/platform/patch_profiling_chunk.py
vllm_ascend/patch/platform/patch_shm_broadcast.py
vllm_ascend/patch/platform/patch_speculative_config.py
vllm_ascend/patch/platform/patch_structured_output.py
vllm_ascend/patch/platform/patch_tool_choice_none_content.py
vllm_ascend/patch/platform/patch_torch_accelerator.py
vllm_ascend/patch/platform/patch_use_v2_model_runner.py
vllm_ascend/patch/platform/patch_weight_transfer_engine.py
vllm_ascend/patch/worker/__init__.py
vllm_ascend/patch/worker/_hccl_pg_registry.py
vllm_ascend/patch/worker/patch_cudagraph.py
vllm_ascend/patch/worker/patch_deepseek_mtp.py
vllm_ascend/patch/worker/patch_deepseek_v2.py
vllm_ascend/patch/worker/patch_distributed.py
vllm_ascend/patch/worker/patch_draft_quarot.py
vllm_ascend/patch/worker/patch_eagle3_init.py
vllm_ascend/patch/worker/patch_eagle3_pp_aux.py
vllm_ascend/patch/worker/patch_fused_moe.py
vllm_ascend/patch/worker/patch_gqa_c8.py
vllm_ascend/patch/worker/patch_idex_310.py
vllm_ascend/patch/worker/patch_kimi_k25.py
vllm_ascend/patch/worker/patch_mamba_utils.py
vllm_ascend/patch/worker/patch_minimax_m2.py
vllm_ascend/patch/worker/patch_minimax_m2_linear_attn.py
vllm_ascend/patch/worker/patch_npugraph_ex_triton.py
vllm_ascend/patch/worker/patch_process_weights_after_loading.py
vllm_ascend/patch/worker/patch_qwen3_5.py
vllm_ascend/patch/worker/patch_qwen3_dflash.py
vllm_ascend/patch/worker/patch_qwen3_next_mtp.py
vllm_ascend/patch/worker/patch_qwen3vl.py
vllm_ascend/patch/worker/patch_rejection_sampler.py
vllm_ascend/patch/worker/patch_routed_experts_capture.py
vllm_ascend/patch/worker/patch_triton.py
vllm_ascend/patch/worker/patch_weight_utils.py
vllm_ascend/patch/worker/patch_v2/__init__.py
vllm_ascend/patch/worker/patch_v2/patch_attn_utils.py
vllm_ascend/patch/worker/patch_v2/patch_block_table.py
vllm_ascend/patch/worker/patch_v2/patch_input_batch.py
vllm_ascend/patch/worker/patch_v2/patch_model_state.py
vllm_ascend/patch/worker/patch_v2/patch_triton.py
vllm_ascend/patch/worker/patch_v2/patch_use_v2_model_runner.py
vllm_ascend/patch/worker/patch_v2/patch_uva.py
vllm_ascend/profiler/__init__.py
vllm_ascend/profiler/torch_npu_profiler.py
vllm_ascend/quantization/__init__.py
vllm_ascend/quantization/compressed_tensors_config.py
vllm_ascend/quantization/fp8_config.py
vllm_ascend/quantization/method_adapters.py
vllm_ascend/quantization/modelslim_config.py
vllm_ascend/quantization/quant_parser.py
vllm_ascend/quantization/quant_type.py
vllm_ascend/quantization/utils.py
vllm_ascend/quantization/methods/__init__.py
vllm_ascend/quantization/methods/base.py
vllm_ascend/quantization/methods/fp8.py
vllm_ascend/quantization/methods/kv_c8.py
vllm_ascend/quantization/methods/registry.py
vllm_ascend/quantization/methods/w4a16.py
vllm_ascend/quantization/methods/w4a16_mxfp4.py
vllm_ascend/quantization/methods/w4a4_flatquant.py
vllm_ascend/quantization/methods/w4a4_laos_dynamic.py
vllm_ascend/quantization/methods/w4a4_mxfp4.py
vllm_ascend/quantization/methods/w4a4_mxfp4_flatquant.py
vllm_ascend/quantization/methods/w4a8.py
vllm_ascend/quantization/methods/w4a8_mxfp4.py
vllm_ascend/quantization/methods/w8a16.py
vllm_ascend/quantization/methods/w8a8_dynamic.py
vllm_ascend/quantization/methods/w8a8_mxfp8.py
vllm_ascend/quantization/methods/w8a8_pdmix.py
vllm_ascend/quantization/methods/w8a8_static.py
vllm_ascend/quantization/methods/w8a8fp8_dynamic.py
vllm_ascend/sample/__init__.py
vllm_ascend/sample/penalties.py
vllm_ascend/sample/rejection_sampler.py
vllm_ascend/sample/sampler.py
vllm_ascend/simple_kv_offload/__init__.py
vllm_ascend/simple_kv_offload/copy_backend.py
vllm_ascend/simple_kv_offload/npu_mem_ops.py
vllm_ascend/simple_kv_offload/worker.py
vllm_ascend/spec_decode/__init__.py
vllm_ascend/spec_decode/dflash_proposer.py
vllm_ascend/spec_decode/draft_proposer.py
vllm_ascend/spec_decode/eagle_proposer.py
vllm_ascend/spec_decode/extract_hidden_states_proposer.py
vllm_ascend/spec_decode/llm_base_proposer.py
vllm_ascend/spec_decode/medusa_proposer.py
vllm_ascend/spec_decode/ngram_proposer.py
vllm_ascend/spec_decode/ngram_proposer_npu.py
vllm_ascend/spec_decode/step3p5.py
vllm_ascend/spec_decode/suffix_proposer.py
vllm_ascend/spec_decode/utils.py
vllm_ascend/worker/__init__.py
vllm_ascend/worker/block_table.py
vllm_ascend/worker/encoder_acl_graph.py
vllm_ascend/worker/kvcomp_utils.py
vllm_ascend/worker/model_runner_v1.py
vllm_ascend/worker/npu_input_batch.py
vllm_ascend/worker/pcp_utils.py
vllm_ascend/worker/utils.py
vllm_ascend/worker/worker.py
vllm_ascend/worker/v2/README.md
vllm_ascend/worker/v2/__init__.py
vllm_ascend/worker/v2/aclgraph_utils.py
vllm_ascend/worker/v2/attn_utils.py
vllm_ascend/worker/v2/block_table.py
vllm_ascend/worker/v2/input_batch.py
vllm_ascend/worker/v2/model_runner.py
vllm_ascend/worker/v2/states.py
vllm_ascend/worker/v2/structured_outputs.py
vllm_ascend/worker/v2/utils.py
vllm_ascend/worker/v2/model_states/__init__.py
vllm_ascend/worker/v2/model_states/default.py
vllm_ascend/worker/v2/sample/__init__.py
vllm_ascend/worker/v2/sample/bad_words.py
vllm_ascend/worker/v2/sample/gumbel.py
vllm_ascend/worker/v2/sample/logprob.py
vllm_ascend/worker/v2/sample/min_p.py
vllm_ascend/worker/v2/sample/penalties.py
vllm_ascend/worker/v2/spec_decode/__init__.py
vllm_ascend/worker/v2/spec_decode/rejection_sampler_utils.py
vllm_ascend/worker/v2/spec_decode/eagle/__init__.py
vllm_ascend/worker/v2/spec_decode/eagle/aclgraph.py
vllm_ascend/worker/v2/spec_decode/eagle/speculator.py
vllm_ascend/xlite/__init__.py
vllm_ascend/xlite/utils.py
vllm_ascend/xlite/xlite.py
vllm_ascend/xlite/xlite_model_runner.py
vllm_ascend/xlite/xlite_worker.py