####################################################################################################

############################### BUILD CONFIGURATION ##############################################

####################################################################################################

[build-system]

requires = ["setuptools >= 64", "pip >= 24"]

build-backend = "setuptools.build_meta"

####################################################################################################

############################### LINTING, FORMATTING AND TESTING CONFIGURATION ####################

####################################################################################################

[tool.isort]

line_length = 80

known_first_party = ["tensorrt_llm"]

known_third_party = ["triton_kernels"]

[tool.yapf]

based_on_style = "pep8"

column_limit = 80

[tool.codespell]

skip = ".git,3rdparty,triton_kernels,tests/integration/test_input_files**,**.jsonl,**.json"

ignore-words-list = "rouge,inout,atleast,strat,nd,subtile,thrid,improbe,NotIn,te,iteract,anythin,tru,Tracin,vEw,dOut,indext,asend,medias,thw,inh"

[tool.autoflake]

in-place = true

remove_all_unused_imports = true

remove_unused_variables = true

####################################################################################################

######################### RUFF CONFIGURATION ##########################

####################################################################################################

[tool.ruff]

line-length = 100 # Line length limit for code

# Supplemental lint approach: Group A files (not in legacy-files.txt) get full

# ruff check + format. Group B files (in legacy-files.txt) get only supplemental

# lint rules via ruff-legacy.toml, with formatting handled by yapf/isort/autoflake.

# See CODING_GUIDELINES.md for details.

fix = true

force-exclude = true

exclude = [

"**3rdparty/**",

"tensorrt_llm/_torch/attention/backends/prims_ts/**",

"tensorrt_llm/_torch/visual_gen/cute_dsl_kernels/blackwell/sol_attn/**",

"triton_kernels/**",

"tensorrt_llm/_torch/cute_dsl_kernels/rubin/moe/manual_mma_128dp.py",

"tensorrt_llm/_torch/cute_dsl_kernels/rubin/moe/rubin_contiguous_grouped_blockscaled_gemm_fused_fc12.py",

"tensorrt_llm/grpc/openengine/_generated/**",

]

[tool.ruff.format]

# Like Black, respect magic trailing commas.

skip-magic-trailing-comma = false

docstring-code-format = true

# Set the line length limit used when formatting code snippets in docstrings.

docstring-code-line-length = "dynamic"

# <<<< BEGIN AUTO-GENERATED by scripts/legacy_utils.py gen-configs >>>>

# Source of truth: legacy-files.txt

# To modify this block: edit legacy-files.txt, then run:

# python scripts/legacy_utils.py gen-configs

exclude = [

".devcontainer/make_env.py",

".github/scripts/label_community_user.py",

".github/scripts/pr_checklist_check.py",

"cpp/kernels/fmha_v2/conftest.py",

"cpp/kernels/fmha_v2/fmha_test.py",

"cpp/kernels/fmha_v2/setup.py",

"cpp/kernels/fmha_v2/test/conftest.py",

"cpp/kernels/fmha_v2/test/fmha/filter_rules.py",

"cpp/kernels/fmha_v2/test/fmha/test_fmha_exe.py",

"cpp/kernels/fmha_v2/test/fmha/test_fmhca_exe.py",

"cpp/kernels/fmha_v2/test/fmha/test_meta.py",

"cpp/kernels/fmha_v2/test/fmha/utils.py",

"cpp/kernels/fmha_v2/test/train_ops/test_train_ops.py",

"cpp/kernels/fmha_v2/train_ops/fmha_bmark.py",

"cpp/kernels/fmha_v2/train_ops/fmha_unit_test.py",

"cpp/kernels/fmha_v2/train_ops/my_utils.py",

"cpp/kernels/fmha_v2/train_ops/te_mha.py",

"cpp/kernels/fmha_v2/train_ops/train_setup.py",

"cpp/kernels/xqa/gen_cpp_header.py",

"cpp/kernels/xqa/gen_cubins.py",

"cpp/kernels/xqa/ref.py",

"cpp/micro_benchmarks/gen-moe-benchmark-file.py",

"cpp/tensorrt_llm/deep_ep/strip_nvshmem_helper.py",

"cpp/tensorrt_llm/kernels/cutlass_kernels/python/generate_kernels.py",

"cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/copy_cu.py",

"cpp/tests/resources/scripts/generate_test_lora_weights.py",

"docs/source/conf.py",

"docs/source/helper.py",

"examples/apps/chat.py",

"examples/apps/fastapi_server.py",

"examples/disaggregated/clients/disagg_client.py",

"examples/disaggregated/slurm/benchmark/submit.py",

"examples/infinitebench/args.py",

"examples/infinitebench/compute_scores.py",

"examples/infinitebench/construct_synthetic_dataset.py",

"examples/infinitebench/eval_utils.py",

"examples/llm-api/llm_guided_decoding.py",

"examples/llm-api/llm_inference.py",

"examples/llm-api/llm_inference_async.py",

"examples/llm-api/llm_inference_async_streaming.py",

"examples/llm-api/llm_inference_distributed.py",

"examples/llm-api/llm_kv_cache_connector.py",

"examples/llm-api/llm_kv_cache_offloading.py",

"examples/llm-api/llm_logits_processor.py",

"examples/llm-api/llm_multilora.py",

"examples/llm-api/llm_runtime.py",

"examples/llm-api/llm_sampling.py",

"examples/llm-api/llm_sparse_attention.py",

"examples/llm-api/llm_speculative_decoding.py",

"examples/llm-api/out_of_tree_example/main.py",

"examples/llm-api/out_of_tree_example/modeling_opt.py",

"examples/llm-api/quickstart_advanced.py",

"examples/llm-api/quickstart_example.py",

"examples/llm-api/quickstart_multimodal.py",

"examples/longbench/eval_longbench_v1.py",

"examples/models/core/gpt_oss/openai_chat_client_function_calling.py",

"examples/models/core/kimi_k2/kimi_k2_tool_calling_example.py",

"examples/quantization/quantize_mixed_precision_moe.py",

"examples/ray_orchestrator/llm_inference_async_ray.py",

"examples/ray_orchestrator/llm_inference_distributed_ray.py",

"examples/scaffolding/contrib/AsyncGeneration/stream_generation_controller.py",

"examples/scaffolding/contrib/DeepConf/run_generation.py",

"examples/scaffolding/contrib/Dynasor/scaffolding_dynasor_run.py",

"examples/scaffolding/contrib/TreeInference/run_mcts_example.py",

"examples/scaffolding/contrib/TreeInference/run_tot_example.py",

"examples/scaffolding/run_basic_generation.py",

"examples/scaffolding/run_best_of_n_with_reward.py",

"examples/scaffolding/run_majority_vote_aime24.py",

"examples/scaffolding/token_budget_majority_vote.py",

"examples/serve/openai_chat_client.py",

"examples/serve/openai_chat_client_for_multimodal.py",

"examples/serve/openai_completion_client.py",

"examples/serve/openai_completion_client_for_lora.py",

"examples/serve/openai_completion_client_json_schema.py",

"examples/wide_ep/ep_load_balancer/generate_eplb_config.py",

"examples/wide_ep/ep_load_balancer/report_load_statistics.py",

"examples/wide_ep/ep_load_balancer/utils.py",

"examples/wide_ep/slurm_scripts/process_gen_iterlog.py",

"jenkins/scripts/mergeWaiveList.py",

"jenkins/scripts/open_search_db.py",

"jenkins/scripts/test_rerun.py",

"scripts/build_wheel.py",

"scripts/check_test_list.py",

"scripts/dco_check.py",

"scripts/format_test_list.py",

"scripts/generate_lock_file.py",

"scripts/get_wheel_from_package.py",

"scripts/git_replace.py",

"scripts/package_trt_llm.py",

"scripts/release_check.py",

"scripts/rename_docker_images.py",

"scripts/test_to_stage_mapping.py",

"setup.py",

"tensorrt_llm/__init__.py",

"tensorrt_llm/_torch/__init__.py",

"tensorrt_llm/_torch/attention/attention.py",

"tensorrt_llm/_torch/attention/backends/__init__.py",

"tensorrt_llm/_torch/attention/backends/flashinfer.py",

"tensorrt_llm/_torch/attention/backends/interface.py",

"tensorrt_llm/_torch/attention/backends/sparse/__init__.py",

"tensorrt_llm/_torch/attention/backends/trtllm.py",

"tensorrt_llm/_torch/attention/backends/utils.py",

"tensorrt_llm/_torch/attention/backends/vanilla.py",

"tensorrt_llm/_torch/attention/qk_norm_attention.py",

"tensorrt_llm/_torch/attention/rotary_embedding.py",

"tensorrt_llm/_torch/autotuner.py",

"tensorrt_llm/_torch/compilation/__init__.py",

"tensorrt_llm/_torch/compilation/backend.py",

"tensorrt_llm/_torch/compilation/multi_stream/__init__.py",

"tensorrt_llm/_torch/compilation/multi_stream/auto_multi_stream.py",

"tensorrt_llm/_torch/compilation/patterns/__init__.py",

"tensorrt_llm/_torch/compilation/patterns/ar_residual_norm.py",

"tensorrt_llm/_torch/compilation/patterns/residual_add_norm.py",

"tensorrt_llm/_torch/compilation/piecewise_optimizer.py",

"tensorrt_llm/_torch/compilation/recover_pass.py",

"tensorrt_llm/_torch/compilation/remove_copy_pass.py",

"tensorrt_llm/_torch/compilation/utils.py",

"tensorrt_llm/_torch/configs/deepseek_v3.py",

"tensorrt_llm/_torch/cublaslt_utils.py",

"tensorrt_llm/_torch/custom_ops/__init__.py",

"tensorrt_llm/_torch/custom_ops/cpp_custom_ops.py",

"tensorrt_llm/_torch/custom_ops/cute_dsl_custom_ops.py",

"tensorrt_llm/_torch/custom_ops/flashinfer_custom_ops.py",

"tensorrt_llm/_torch/custom_ops/torch_custom_ops.py",

"tensorrt_llm/_torch/custom_ops/trtllm_gen_custom_ops.py",

"tensorrt_llm/_torch/custom_ops/userbuffers_custom_ops.py",

"tensorrt_llm/_torch/cute_dsl_kernels/__init__.py",

"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/__init__.py",

"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp16.py",

"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_decode_fp8.py",

"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/attention/mla/mla_helpers.py",

"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/custom_pipeline.py",

"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/dense_blockscaled_gemm_persistent.py",

"tensorrt_llm/_torch/cute_dsl_kernels/blackwell/utils.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/__init__.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/blocked_scale.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/contract.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/custom_ext.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/dynamic_mainloop.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/epilogue_refactor.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/fc1_fc2_fuse_sched.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/grid_sync.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/iket_compat.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/kernel_fc12.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/megamoe_constants.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/megamoe_kernel.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/moe_persistent_scheduler.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/moe_utils.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/ptx_helpers.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/sf_swizzle.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/sym_buffer.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/token_comm.py",

"tensorrt_llm/_torch/cute_dsl_kernels/mega_moe_nvfp4/topk_reduce.py",

"tensorrt_llm/_torch/cute_dsl_utils.py",

"tensorrt_llm/_torch/debug/__init__.py",

"tensorrt_llm/_torch/debug/debug_hook.py",

"tensorrt_llm/_torch/device_mesh.py",

"tensorrt_llm/_torch/disaggregation/kv_cache_transceiver.py",

"tensorrt_llm/_torch/distributed/__init__.py",

"tensorrt_llm/_torch/distributed/communicator.py",

"tensorrt_llm/_torch/distributed/ops.py",

"tensorrt_llm/_torch/distributed/pg_utils.py",

"tensorrt_llm/_torch/flashinfer_utils.py",

"tensorrt_llm/_torch/hostfunc.py",

"tensorrt_llm/_torch/llm.py",

"tensorrt_llm/_torch/memory_buffer_utils.py",

"tensorrt_llm/_torch/metadata.py",

"tensorrt_llm/_torch/model_config.py",

"tensorrt_llm/_torch/models/__init__.py",

"tensorrt_llm/_torch/models/checkpoints/__init__.py",

"tensorrt_llm/_torch/models/checkpoints/auto_mapper.py",

"tensorrt_llm/_torch/models/checkpoints/base_checkpoint_loader.py",

"tensorrt_llm/_torch/models/checkpoints/base_config_loader.py",

"tensorrt_llm/_torch/models/checkpoints/base_weight_loader.py",

"tensorrt_llm/_torch/models/checkpoints/base_weight_mapper.py",

"tensorrt_llm/_torch/models/checkpoints/hf/__init__.py",

"tensorrt_llm/_torch/models/checkpoints/hf/checkpoint_loader.py",

"tensorrt_llm/_torch/models/checkpoints/hf/config_loader.py",

"tensorrt_llm/_torch/models/checkpoints/hf/gemma3_weight_mapper.py",

"tensorrt_llm/_torch/models/checkpoints/hf/llama4_weight_mapper.py",

"tensorrt_llm/_torch/models/checkpoints/hf/mixtral_weight_mapper.py",

"tensorrt_llm/_torch/models/checkpoints/hf/nemotron_h_weight_mapper.py",

"tensorrt_llm/_torch/models/checkpoints/hf/qwen2_moe_weight_mapper.py",

"tensorrt_llm/_torch/models/checkpoints/hf/qwen2vl_weight_mapper.py",

"tensorrt_llm/_torch/models/checkpoints/hf/qwen3_moe_weight_mapper.py",

"tensorrt_llm/_torch/models/checkpoints/hf/qwen3_next_weight_mapper.py",

"tensorrt_llm/_torch/models/checkpoints/hf/weight_loader.py",

"tensorrt_llm/_torch/models/checkpoints/hf/weight_mapper.py",

"tensorrt_llm/_torch/models/modeling_auto.py",

"tensorrt_llm/_torch/models/modeling_bert.py",

"tensorrt_llm/_torch/models/modeling_clip.py",

"tensorrt_llm/_torch/models/modeling_deepseekv3.py",

"tensorrt_llm/_torch/models/modeling_exaone4.py",

"tensorrt_llm/_torch/models/modeling_gemma3.py",

"tensorrt_llm/_torch/models/modeling_gemma3vl.py",

"tensorrt_llm/_torch/models/modeling_gpt_oss.py",

"tensorrt_llm/_torch/models/modeling_hunyuan_dense.py",

"tensorrt_llm/_torch/models/modeling_hunyuan_moe.py",

"tensorrt_llm/_torch/models/modeling_hyperclovax.py",

"tensorrt_llm/_torch/models/modeling_llama.py",

"tensorrt_llm/_torch/models/modeling_llama_min_latency.py",

"tensorrt_llm/_torch/models/modeling_llava_next.py",

"tensorrt_llm/_torch/models/modeling_mistral.py",

"tensorrt_llm/_torch/models/modeling_mixtral.py",

"tensorrt_llm/_torch/models/modeling_mllama.py",

"tensorrt_llm/_torch/models/modeling_multimodal_encoder.py",

"tensorrt_llm/_torch/models/modeling_multimodal_utils.py",

"tensorrt_llm/_torch/models/modeling_nemotron.py",

"tensorrt_llm/_torch/models/modeling_nemotron_h.py",

"tensorrt_llm/_torch/models/modeling_nemotron_nas.py",

"tensorrt_llm/_torch/models/modeling_phi3.py",

"tensorrt_llm/_torch/models/modeling_phi4mm.py",

"tensorrt_llm/_torch/models/modeling_qwen.py",

"tensorrt_llm/_torch/models/modeling_qwen2vl.py",

"tensorrt_llm/_torch/models/modeling_qwen3.py",

"tensorrt_llm/_torch/models/modeling_qwen3_moe.py",

"tensorrt_llm/_torch/models/modeling_qwen3_next.py",

"tensorrt_llm/_torch/models/modeling_qwen_moe.py",

"tensorrt_llm/_torch/models/modeling_radio.py",

"tensorrt_llm/_torch/models/modeling_seedoss.py",

"tensorrt_llm/_torch/models/modeling_siglip.py",

"tensorrt_llm/_torch/models/modeling_speculative.py",

"tensorrt_llm/_torch/models/modeling_utils.py",

"tensorrt_llm/_torch/models/modeling_vila.py",

"tensorrt_llm/_torch/modules/__init__.py",

"tensorrt_llm/_torch/modules/decoder_layer.py",

"tensorrt_llm/_torch/modules/embedding.py",

"tensorrt_llm/_torch/modules/fla/__init__.py",

"tensorrt_llm/_torch/modules/fla/chunk.py",

"tensorrt_llm/_torch/modules/fla/chunk_delta_h.py",

"tensorrt_llm/_torch/modules/fla/chunk_o.py",

"tensorrt_llm/_torch/modules/fla/chunk_scaled_dot_kkt.py",

"tensorrt_llm/_torch/modules/fla/cumsum.py",

"tensorrt_llm/_torch/modules/fla/fused_recurrent.py",

"tensorrt_llm/_torch/modules/fla/fused_sigmoid_gating_recurrent.py",

"tensorrt_llm/_torch/modules/fla/index.py",

"tensorrt_llm/_torch/modules/fla/l2norm.py",

"tensorrt_llm/_torch/modules/fla/layernorm_gated.py",

"tensorrt_llm/_torch/modules/fla/op.py",

"tensorrt_llm/_torch/modules/fla/solve_tril.py",

"tensorrt_llm/_torch/modules/fla/utils.py",

"tensorrt_llm/_torch/modules/fla/wy_fast.py",

"tensorrt_llm/_torch/modules/gated_mlp.py",

"tensorrt_llm/_torch/modules/layer_norm.py",

"tensorrt_llm/_torch/modules/linear.py",

"tensorrt_llm/_torch/modules/logits_processor.py",

"tensorrt_llm/_torch/modules/mamba/__init__.py",

"tensorrt_llm/_torch/modules/mamba/causal_conv1d.py",

"tensorrt_llm/_torch/modules/mamba/layernorm_gated.py",

"tensorrt_llm/_torch/modules/mamba/mamba2_metadata.py",

"tensorrt_llm/_torch/modules/mamba/mamba2_mixer.py",

"tensorrt_llm/_torch/modules/mamba/selective_state_update.py",

"tensorrt_llm/_torch/modules/mamba/softplus.py",

"tensorrt_llm/_torch/modules/mamba/ssd_bmm.py",

"tensorrt_llm/_torch/modules/mamba/ssd_chunk_scan.py",

"tensorrt_llm/_torch/modules/mamba/ssd_chunk_state.py",

"tensorrt_llm/_torch/modules/mamba/ssd_combined.py",

"tensorrt_llm/_torch/modules/mamba/ssd_state_passing.py",

"tensorrt_llm/_torch/modules/mlp.py",

"tensorrt_llm/_torch/modules/multi_stream_utils.py",

"tensorrt_llm/_torch/modules/rms_norm.py",

"tensorrt_llm/_torch/modules/swiglu.py",

"tensorrt_llm/_torch/modules/triton_linear.py",

"tensorrt_llm/_torch/moe/expert_statistic.py",

"tensorrt_llm/_torch/moe/fused_moe/__init__.py",

"tensorrt_llm/_torch/moe/fused_moe/create_moe.py",

"tensorrt_llm/_torch/moe/fused_moe/deep_ep_utils.py",

"tensorrt_llm/_torch/moe/fused_moe/fused_moe_cute_dsl.py",

"tensorrt_llm/_torch/moe/fused_moe/fused_moe_cutlass.py",

"tensorrt_llm/_torch/moe/fused_moe/fused_moe_deepgemm.py",

"tensorrt_llm/_torch/moe/fused_moe/fused_moe_triton.py",

"tensorrt_llm/_torch/moe/fused_moe/fused_moe_trtllm_gen.py",

"tensorrt_llm/_torch/moe/fused_moe/fused_moe_vanilla.py",

"tensorrt_llm/_torch/moe/fused_moe/interface.py",

"tensorrt_llm/_torch/moe/fused_moe/moe_load_balancer.py",

"tensorrt_llm/_torch/moe/fused_moe/quantization.py",

"tensorrt_llm/_torch/moe/fused_moe/routing.py",

"tensorrt_llm/_torch/peft/__init__.py",

"tensorrt_llm/_torch/peft/lora/__init__.py",

"tensorrt_llm/_torch/peft/lora/config.py",

"tensorrt_llm/_torch/peft/lora/layer.py",

"tensorrt_llm/_torch/pyexecutor/__init__.py",

"tensorrt_llm/_torch/pyexecutor/_util.py",

"tensorrt_llm/_torch/pyexecutor/config_utils.py",

"tensorrt_llm/_torch/pyexecutor/cuda_graph_runner.py",

"tensorrt_llm/_torch/pyexecutor/executor_request_queue.py",

"tensorrt_llm/_torch/pyexecutor/finish_reason.py",

"tensorrt_llm/_torch/pyexecutor/grammar_matcher.py",

"tensorrt_llm/_torch/pyexecutor/guided_decoder.py",

"tensorrt_llm/_torch/pyexecutor/handle_additional_outputs.py",

"tensorrt_llm/_torch/pyexecutor/handle_logits.py",

"tensorrt_llm/_torch/pyexecutor/kv_cache/mamba_cache_manager.py",

"tensorrt_llm/_torch/pyexecutor/layerwise_nvtx_marker.py",

"tensorrt_llm/_torch/pyexecutor/llm_request.py",

"tensorrt_llm/_torch/pyexecutor/model_engine.py",

"tensorrt_llm/_torch/pyexecutor/model_loader.py",

"tensorrt_llm/_torch/pyexecutor/py_executor.py",

"tensorrt_llm/_torch/pyexecutor/py_executor_creator.py",

"tensorrt_llm/_torch/pyexecutor/resource_manager.py",

"tensorrt_llm/_torch/pyexecutor/seq_slot_manager.py",

"tensorrt_llm/_torch/shared_tensor/__init__.py",

"tensorrt_llm/_torch/shared_tensor/shared_tensor.py",

"tensorrt_llm/_torch/speculative/__init__.py",

"tensorrt_llm/_torch/speculative/auto_heuristic.py",

"tensorrt_llm/_torch/speculative/drafter.py",

"tensorrt_llm/_torch/speculative/eagle3.py",

"tensorrt_llm/_torch/speculative/interface.py",

"tensorrt_llm/_torch/speculative/mtp.py",

"tensorrt_llm/_torch/speculative/ngram.py",

"tensorrt_llm/_torch/speculative/save_hidden_state.py",

"tensorrt_llm/_torch/speculative/spec_tree_manager.py",

"tensorrt_llm/_torch/speculative/speculation_gate.py",

"tensorrt_llm/_torch/speculative/utils.py",

"tensorrt_llm/_torch/utils.py",

"tensorrt_llm/_torch/virtual_memory.py",

"tensorrt_llm/_utils.py",

"tensorrt_llm/bench/__init__.py",

"tensorrt_llm/bench/benchmark/__init__.py",

"tensorrt_llm/bench/benchmark/low_latency.py",

"tensorrt_llm/bench/benchmark/throughput.py",

"tensorrt_llm/bench/benchmark/utils/__init__.py",

"tensorrt_llm/bench/benchmark/utils/asynchronous.py",

"tensorrt_llm/bench/benchmark/utils/general.py",

"tensorrt_llm/bench/benchmark/utils/processes.py",

"tensorrt_llm/bench/dataclasses/__init__.py",

"tensorrt_llm/bench/dataclasses/configuration.py",

"tensorrt_llm/bench/dataclasses/engine.py",

"tensorrt_llm/bench/dataclasses/enums.py",

"tensorrt_llm/bench/dataclasses/general.py",

"tensorrt_llm/bench/dataclasses/reporting.py",

"tensorrt_llm/bench/dataclasses/statistics.py",

"tensorrt_llm/bench/utils/__init__.py",

"tensorrt_llm/bench/utils/data.py",

"tensorrt_llm/commands/__init__.py",

"tensorrt_llm/commands/bench.py",

"tensorrt_llm/commands/eval.py",

"tensorrt_llm/commands/serve.py",

"tensorrt_llm/evaluate/__init__.py",

"tensorrt_llm/evaluate/cnn_dailymail.py",

"tensorrt_llm/evaluate/interface.py",

"tensorrt_llm/evaluate/json_mode_eval.py",

"tensorrt_llm/evaluate/lm_eval.py",

"tensorrt_llm/evaluate/lm_eval_tasks/gpqa/cot_zeroshot_aa/_generate_configs.py",

"tensorrt_llm/evaluate/lm_eval_tasks/gpqa/cot_zeroshot_aa/utils.py",

"tensorrt_llm/evaluate/longbench_v2.py",

"tensorrt_llm/evaluate/mmlu.py",

"tensorrt_llm/executor/__init__.py",

"tensorrt_llm/executor/base_worker.py",

"tensorrt_llm/executor/executor.py",

"tensorrt_llm/executor/ipc.py",

"tensorrt_llm/executor/postproc_worker.py",

"tensorrt_llm/executor/proxy.py",

"tensorrt_llm/executor/ray/executor.py",

"tensorrt_llm/executor/ray/gpu_worker.py",

"tensorrt_llm/executor/ray/stub.py",

"tensorrt_llm/executor/ray/utils.py",

"tensorrt_llm/executor/request.py",

"tensorrt_llm/executor/result.py",

"tensorrt_llm/executor/rpc/__init__.py",

"tensorrt_llm/executor/rpc/rpc_client.py",

"tensorrt_llm/executor/rpc/rpc_common.py",

"tensorrt_llm/executor/rpc/rpc_server.py",

"tensorrt_llm/executor/rpc_proxy.py",

"tensorrt_llm/executor/rpc_worker.py",

"tensorrt_llm/executor/utils.py",

"tensorrt_llm/executor/worker.py",

"tensorrt_llm/functional.py",

"tensorrt_llm/inputs/__init__.py",

"tensorrt_llm/inputs/data.py",

"tensorrt_llm/inputs/evs.py",

"tensorrt_llm/inputs/multimodal.py",

"tensorrt_llm/inputs/registry.py",

"tensorrt_llm/inputs/utils.py",

"tensorrt_llm/llmapi/__init__.py",

"tensorrt_llm/llmapi/disagg_utils.py",

"tensorrt_llm/llmapi/kv_cache_type.py",

"tensorrt_llm/llmapi/llm.py",

"tensorrt_llm/llmapi/llm_args.py",

"tensorrt_llm/llmapi/llm_utils.py",

"tensorrt_llm/llmapi/mgmn_leader_node.py",

"tensorrt_llm/llmapi/mgmn_worker_node.py",

"tensorrt_llm/llmapi/mm_encoder.py",

"tensorrt_llm/llmapi/mpi_session.py",

"tensorrt_llm/llmapi/reasoning_parser.py",

"tensorrt_llm/llmapi/serialization.py",

"tensorrt_llm/llmapi/tokenizer.py",

"tensorrt_llm/llmapi/tracer.py",

"tensorrt_llm/llmapi/tracing.py",

"tensorrt_llm/llmapi/utils.py",

"tensorrt_llm/mapping.py",

"tensorrt_llm/math_utils.py",

"tensorrt_llm/metrics/__init__.py",

"tensorrt_llm/metrics/collector.py",

"tensorrt_llm/metrics/enums.py",

"tensorrt_llm/models/__init__.py",

"tensorrt_llm/models/automodel.py",

"tensorrt_llm/models/convert_utils.py",

"tensorrt_llm/models/modeling_utils.py",

"tensorrt_llm/quantization/__init__.py",

"tensorrt_llm/quantization/functional.py",

"tensorrt_llm/quantization/mode.py",

"tensorrt_llm/quantization/utils/__init__.py",

"tensorrt_llm/quantization/utils/fp4_utils.py",

"tensorrt_llm/quantization/utils/fp8_utils.py",

"tensorrt_llm/runtime/__init__.py",

"tensorrt_llm/runtime/memory_pools/__init__.py",

"tensorrt_llm/scaffolding/__init__.py",

"tensorrt_llm/scaffolding/benchmark.py",

"tensorrt_llm/scaffolding/contrib/AsyncGeneration/stream_generation.py",

"tensorrt_llm/scaffolding/contrib/DeepConf/__init__.py",

"tensorrt_llm/scaffolding/contrib/DeepConf/deep_conf_controller.py",

"tensorrt_llm/scaffolding/contrib/DeepConf/deep_conf_utils.py",

"tensorrt_llm/scaffolding/contrib/Dynasor/__init__.py",

"tensorrt_llm/scaffolding/contrib/Dynasor/dynasor_controller.py",

"tensorrt_llm/scaffolding/contrib/Dynasor/evaluator.py",

"tensorrt_llm/scaffolding/contrib/TreeInference/__init__.py",

"tensorrt_llm/scaffolding/contrib/TreeInference/tree_controllers.py",

"tensorrt_llm/scaffolding/contrib/__init__.py",

"tensorrt_llm/scaffolding/contrib/mcp/__init__.py",

"tensorrt_llm/scaffolding/contrib/mcp/chat_handler.py",

"tensorrt_llm/scaffolding/contrib/mcp/chat_task.py",

"tensorrt_llm/scaffolding/contrib/mcp/mcp_controller.py",

"tensorrt_llm/scaffolding/contrib/mcp/mcp_task.py",

"tensorrt_llm/scaffolding/contrib/mcp/mcp_utils.py",

"tensorrt_llm/scaffolding/contrib/mcp/mcp_worker.py",

"tensorrt_llm/scaffolding/controller.py",

"tensorrt_llm/scaffolding/math_utils.py",

"tensorrt_llm/scaffolding/result.py",

"tensorrt_llm/scaffolding/scaffolding_llm.py",

"tensorrt_llm/scaffolding/task.py",

"tensorrt_llm/scaffolding/task_collection.py",

"tensorrt_llm/scaffolding/worker.py",

"tensorrt_llm/scheduling_params.py",

"tensorrt_llm/serve/__init__.py",

"tensorrt_llm/serve/chat_utils.py",

"tensorrt_llm/serve/cluster_storage.py",

"tensorrt_llm/serve/disagg_auto_scaling.py",

"tensorrt_llm/serve/harmony_adapter.py",

"tensorrt_llm/serve/metadata_server.py",

"tensorrt_llm/serve/openai_disagg_server.py",

"tensorrt_llm/serve/openai_protocol.py",

"tensorrt_llm/serve/openai_server.py",

"tensorrt_llm/serve/postprocess_handlers.py",

"tensorrt_llm/serve/responses_utils.py",

"tensorrt_llm/serve/router.py",

"tensorrt_llm/serve/scripts/__init__.py",

"tensorrt_llm/serve/scripts/backend_request_func.py",

"tensorrt_llm/serve/scripts/benchmark_dataset.py",

"tensorrt_llm/serve/scripts/benchmark_serving.py",

"tensorrt_llm/serve/scripts/benchmark_utils.py",

"tensorrt_llm/serve/scripts/time_breakdown/__init__.py",

"tensorrt_llm/serve/scripts/time_breakdown/__main__.py",

"tensorrt_llm/serve/scripts/time_breakdown/time_breakdown.py",

"tensorrt_llm/serve/tool_parser/base_tool_parser.py",

"tensorrt_llm/serve/tool_parser/qwen3_tool_parser.py",

"tensorrt_llm/serve/tool_parser/utils.py",

"tensorrt_llm/tokenizer/tokenizer.py",

"tensorrt_llm/tools/__init__.py",

"tensorrt_llm/tools/importlib_utils.py",

"tensorrt_llm/tools/plugin_gen/__init__.py",

"tensorrt_llm/tools/ppl.py",

"tensorrt_llm/tools/profiler/nsys_profile_tools/gputrc2graph.py",

"tensorrt_llm/version.py",

"tests/integration/defs/__init__.py",

"tests/integration/defs/accuracy/__init__.py",

"tests/integration/defs/accuracy/accuracy_core.py",

"tests/integration/defs/accuracy/scripts/collect_evaluated_accuracies.py",

"tests/integration/defs/accuracy/scripts/compute_theta_and_thresholds.py",

"tests/integration/defs/accuracy/test_cli_flow.py",

"tests/integration/defs/accuracy/test_disaggregated_serving.py",

"tests/integration/defs/accuracy/test_llm_api_pytorch.py",

"tests/integration/defs/accuracy/test_llm_api_pytorch_ray.py",

"tests/integration/defs/ci_profiler.py",

"tests/integration/defs/common.py",

"tests/integration/defs/conftest.py",

"tests/integration/defs/cpp/conftest.py",

"tests/integration/defs/cpp/cpp_common.py",

"tests/integration/defs/cpp/test_multi_gpu.py",

"tests/integration/defs/cpp/test_unit_tests.py",

"tests/integration/defs/disaggregated/test_auto_scaling.py",

"tests/integration/defs/disaggregated/test_disaggregated.py",

"tests/integration/defs/disaggregated/test_disaggregated_etcd.py",

"tests/integration/defs/disaggregated/test_disaggregated_single_gpu.py",

"tests/integration/defs/disaggregated/test_workers.py",

"tests/integration/defs/examples/run_llm_quickstart_atexit.py",

"tests/integration/defs/examples/serve/test_serve.py",

"tests/integration/defs/examples/serve/test_serve_negative.py",

"tests/integration/defs/examples/test_gpt.py",

"tests/integration/defs/examples/test_llm_api_with_mpi.py",

"tests/integration/defs/examples/test_phi.py",

"tests/integration/defs/examples/test_ray.py",

"tests/integration/defs/llmapi/__init__.py",

"tests/integration/defs/llmapi/_run_llmapi_llm.py",

"tests/integration/defs/llmapi/test_llm_api_connector.py",

"tests/integration/defs/llmapi/test_llm_api_qa.py",

"tests/integration/defs/llmapi/test_llm_examples.py",

"tests/integration/defs/local_venv.py",

"tests/integration/defs/perf/__init__.py",

"tests/integration/defs/perf/allowed_configs.py",

"tests/integration/defs/perf/create_perf_comparison_report.py",

"tests/integration/defs/perf/data.py",

"tests/integration/defs/perf/data_export.py",

"tests/integration/defs/perf/diff_tools.py",

"tests/integration/defs/perf/gpu_clock_lock.py",

"tests/integration/defs/perf/misc.py",

"tests/integration/defs/perf/open_search_db_utils.py",

"tests/integration/defs/perf/pytorch_model_config.py",

"tests/integration/defs/perf/sampler_options_config.py",

"tests/integration/defs/perf/sanity_perf_check.py",

"tests/integration/defs/perf/session_data_writer.py",

"tests/integration/defs/perf/test_perf.py",

"tests/integration/defs/perf/utils.py",

"tests/integration/defs/runner_interface.py",

"tests/integration/defs/stress_test/stress_test.py",

"tests/integration/defs/sysinfo/get_sysinfo.py",

"tests/integration/defs/test_e2e.py",

"tests/integration/defs/test_fmha.py",

"tests/integration/defs/test_list_parser.py",

"tests/integration/defs/test_list_validation.py",

"tests/integration/defs/test_sanity.py",

"tests/integration/defs/test_unittests.py",

"tests/integration/defs/triton_server/__init__.py",

"tests/integration/defs/triton_server/common.py",

"tests/integration/defs/triton_server/conftest.py",

"tests/integration/defs/triton_server/test_list_parser.py",

"tests/integration/defs/triton_server/trt_test_alternative.py",

"tests/integration/defs/trt_test_alternative.py",

"tests/integration/defs/utils/__init__.py",

"tests/integration/defs/utils/periodic_junit.py",

"tests/integration/defs/utils/timeout_manager.py",

"tests/microbenchmarks/all_reduce.py",

"tests/scripts/allreduce_perf/allreduce_heuristic_code_gen.py",

"tests/scripts/allreduce_perf/allreduce_perf_viz.py",

"tests/scripts/iteration_log_parser.py",

"tests/unittest/_torch/attention/sparse/test_sparse_mla_forward.py",

"tests/unittest/_torch/attention/test_attention.py",

"tests/unittest/_torch/attention/test_attention_mla.py",

"tests/unittest/_torch/attention/test_attention_no_cache.py",

"tests/unittest/_torch/attention/test_flashinfer_attention.py",

"tests/unittest/_torch/attention/test_rotary_embedding.py",

"tests/unittest/_torch/attention/test_vanilla_attention.py",

"tests/unittest/_torch/compilation/test_add_norm.py",

"tests/unittest/_torch/debugger/test_debugger_addon.py",

"tests/unittest/_torch/executor/test_chunked_logits.py",

"tests/unittest/_torch/executor/test_executor_request_queue.py",

"tests/unittest/_torch/executor/test_overlap_scheduler.py",

"tests/unittest/_torch/executor/test_pytorch_model_engine.py",

"tests/unittest/_torch/executor/test_resource_manager.py",

"tests/unittest/_torch/executor/test_router_dealer_ipc.py",

"tests/unittest/_torch/helpers.py",

"tests/unittest/_torch/misc/test_autotuner.py",

"tests/unittest/_torch/misc/test_share_tensor.py",

"tests/unittest/_torch/misc/test_virtual_memory.py",

"tests/unittest/_torch/modeling/test_modeling_bert.py",

"tests/unittest/_torch/modeling/test_modeling_clip.py",

"tests/unittest/_torch/modeling/test_modeling_gemma3.py",

"tests/unittest/_torch/modeling/test_modeling_gpt_oss.py",

"tests/unittest/_torch/modeling/test_modeling_llama.py",

"tests/unittest/_torch/modeling/test_modeling_llama_min_latency.py",

"tests/unittest/_torch/modeling/test_modeling_mixtral.py",

"tests/unittest/_torch/modeling/test_modeling_mllama.py",

"tests/unittest/_torch/modeling/test_modeling_nemotron.py",

"tests/unittest/_torch/modeling/test_modeling_nemotron_h.py",

"tests/unittest/_torch/modeling/test_modeling_nemotron_nas.py",

"tests/unittest/_torch/modeling/test_modeling_out_of_tree.py",

"tests/unittest/_torch/modeling/test_modeling_phi3.py",

"tests/unittest/_torch/modeling/test_modeling_qwen.py",

"tests/unittest/_torch/modeling/test_modeling_qwen2_5vl.py",

"tests/unittest/_torch/modeling/test_modeling_qwen_moe.py",

"tests/unittest/_torch/modeling/test_modeling_siglip.py",

"tests/unittest/_torch/modeling/test_modeling_vila.py",

"tests/unittest/_torch/modules/test_group_rmn_norm.py",

"tests/unittest/_torch/modules/test_triton_linear.py",

"tests/unittest/_torch/moe/test_fused_moe.py",

"tests/unittest/_torch/moe/test_moe_host_sharer.py",

"tests/unittest/_torch/moe/test_moe_load_balancer.py",

"tests/unittest/_torch/moe/test_moe_routing.py",

"tests/unittest/_torch/multi_gpu/test_allreduce.py",

"tests/unittest/_torch/multi_gpu/test_alltoall.py",

"tests/unittest/_torch/multi_gpu/test_ar_residual_norm.py",

"tests/unittest/_torch/multi_gpu/test_embedding.py",

"tests/unittest/_torch/multi_gpu/test_linear.py",

"tests/unittest/_torch/multi_gpu/test_lowprecision_allreduce.py",

"tests/unittest/_torch/multi_gpu/test_mnnvl_allreduce.py",

"tests/unittest/_torch/multi_gpu/test_mnnvl_memory.py",

"tests/unittest/_torch/multi_gpu/test_user_buffers.py",

"tests/unittest/_torch/multi_gpu_modeling/test_deepseek.py",

"tests/unittest/_torch/multimodal/test_external_embedding.py",

"tests/unittest/_torch/multimodal/test_find_num_image_tokens.py",

"tests/unittest/_torch/multimodal/test_fuse_input_embeds.py",

"tests/unittest/_torch/multimodal/test_mm_encoder_standalone.py",

"tests/unittest/_torch/multimodal/test_multimodal_runtime.py",

"tests/unittest/_torch/multimodal/test_share_multiparams.py",

"tests/unittest/_torch/pattern_watcher.py",

"tests/unittest/_torch/ray_orchestrator/conftest.py",

"tests/unittest/_torch/ray_orchestrator/multi_gpu/test_executor.py",

"tests/unittest/_torch/ray_orchestrator/multi_gpu/test_mapping.py",

"tests/unittest/_torch/ray_orchestrator/multi_gpu/test_ops.py",

"tests/unittest/_torch/ray_orchestrator/single_gpu/test_cache_transceiver_comm.py",

"tests/unittest/_torch/sampler/test_beam_search.py",

"tests/unittest/_torch/sampler/test_best_of_n.py",

"tests/unittest/_torch/speculative/test_eagle3.py",

"tests/unittest/_torch/test_connector.py",

"tests/unittest/_torch/test_torch_multi_arange.py",

"tests/unittest/_torch/thop/parallel/deep_gemm_tests.py",

"tests/unittest/_torch/thop/parallel/test_dsv3_fused_a_gemm.py",

"tests/unittest/_torch/thop/parallel/test_dsv3_router_gemm.py",

"tests/unittest/_torch/thop/parallel/test_finegrained_mixed_dtype_gemm.py",

"tests/unittest/_torch/thop/parallel/test_fp4_bmm_quantize.py",

"tests/unittest/_torch/thop/parallel/test_fp4_calculate_global_scale.py",

"tests/unittest/_torch/thop/parallel/test_fp4_gemm_quantize.py",

"tests/unittest/_torch/thop/parallel/test_fp4_linear.py",

"tests/unittest/_torch/thop/parallel/test_fp4_swizzle.py",

"tests/unittest/_torch/thop/parallel/test_fp8_block_scale_gemm.py",

"tests/unittest/_torch/thop/parallel/test_fp8_linear.py",

"tests/unittest/_torch/thop/parallel/test_fp8_per_tensor_scale_tllmg_gemm.py",

"tests/unittest/_torch/thop/parallel/test_fp8_quantize.py",

"tests/unittest/_torch/thop/parallel/test_fp8_rowwise_linear.py",

"tests/unittest/_torch/thop/parallel/test_scaled_mm.py",

"tests/unittest/_torch/thop/parallel/test_selective_scan_op.py",

"tests/unittest/_torch/thop/parallel/test_tinygemm2.py",

"tests/unittest/_torch/thop/parallel/test_tllmg_bmm.py",

"tests/unittest/_torch/thop/parallel/test_w4a16_linear.py",

"tests/unittest/_torch/thop/parallel/test_w4a8_linear.py",

"tests/unittest/_torch/thop/parallel/test_w4a8_mxfp4_mxfp8_gemm.py",

"tests/unittest/_torch/thop/parallel/test_weight_only_quant_gemm.py",

"tests/unittest/_torch/thop/parallel/test_weight_only_quant_linear.py",

"tests/unittest/_torch/thop/serial/test_moe.py",

"tests/unittest/_torch/thop/serial/test_moe_alltoall.py",

"tests/unittest/api_stability/api_stability_core.py",

"tests/unittest/api_stability/test_llm_api.py",

"tests/unittest/bindings/test_bindings_moe.py",

"tests/unittest/bindings/test_bindings_ut.py",

"tests/unittest/bindings/test_executor_bindings.py",

"tests/unittest/bindings/test_hostfunc.py",

"tests/unittest/check_pip_install.py",

"tests/unittest/conftest.py",

"tests/unittest/disaggregated/test_cluster_storage.py",

"tests/unittest/disaggregated/test_disagg_cluster_manager_worker.py",

"tests/unittest/disaggregated/test_disagg_utils.py",

"tests/unittest/disaggregated/test_remoteDictionary.py",

"tests/unittest/disaggregated/test_router.py",

"tests/unittest/dump_checkpoint_stats.py",

"tests/unittest/executor/test_base_worker.py",

"tests/unittest/executor/test_rpc.py",

"tests/unittest/executor/test_rpc_proxy.py",

"tests/unittest/executor/test_rpc_worker.py",

"tests/unittest/gc_utils.py",

"tests/unittest/llmapi/__init__.py",

"tests/unittest/llmapi/_run_mpi_comm_task.py",

"tests/unittest/llmapi/_run_multi_llm_tasks.py",

"tests/unittest/llmapi/_run_multi_mpi_comm_tasks.py",

"tests/unittest/llmapi/apps/__init__.py",

"tests/unittest/llmapi/apps/_test_disagg_serving_multi_nodes.py",

"tests/unittest/llmapi/apps/_test_llm_chat.py",

"tests/unittest/llmapi/apps/_test_llm_server.py",

"tests/unittest/llmapi/apps/_test_openai_cache_salt.py",

"tests/unittest/llmapi/apps/_test_openai_chat.py",

"tests/unittest/llmapi/apps/_test_openai_chat_guided_decoding.py",

"tests/unittest/llmapi/apps/_test_openai_chat_harmony.py",

"tests/unittest/llmapi/apps/_test_openai_chat_multimodal.py",

"tests/unittest/llmapi/apps/_test_openai_completions.py",

"tests/unittest/llmapi/apps/_test_openai_lora.py",

"tests/unittest/llmapi/apps/_test_openai_metrics.py",

"tests/unittest/llmapi/apps/_test_openai_misc.py",

"tests/unittest/llmapi/apps/_test_openai_mmencoder.py",

"tests/unittest/llmapi/apps/_test_openai_multi_gpu.py",

"tests/unittest/llmapi/apps/_test_openai_multi_nodes.py",

"tests/unittest/llmapi/apps/_test_openai_perf_metrics.py",

"tests/unittest/llmapi/apps/_test_openai_prometheus.py",

"tests/unittest/llmapi/apps/_test_openai_reasoning.py",

"tests/unittest/llmapi/apps/_test_openai_responses.py",

"tests/unittest/llmapi/apps/_test_openai_tool_call.py",

"tests/unittest/llmapi/apps/_test_trtllm_serve_benchmark.py",

"tests/unittest/llmapi/apps/_test_trtllm_serve_example.py",

"tests/unittest/llmapi/apps/_test_trtllm_serve_lora.py",

"tests/unittest/llmapi/apps/_test_trtllm_serve_multimodal_benchmark.py",

"tests/unittest/llmapi/apps/_test_trtllm_serve_multimodal_example.py",

"tests/unittest/llmapi/apps/_test_trtllm_serve_top_logprobs.py",

"tests/unittest/llmapi/apps/openai_server.py",

"tests/unittest/llmapi/apps/test_tool_parsers.py",

"tests/unittest/llmapi/apps/utils.py",

"tests/unittest/llmapi/lora_test_utils.py",

"tests/unittest/llmapi/run_llm.py",

"tests/unittest/llmapi/run_llm_exit.py",

"tests/unittest/llmapi/run_llm_with_postproc.py",

"tests/unittest/llmapi/test_additional_model_outputs.py",

"tests/unittest/llmapi/test_executor.py",

"tests/unittest/llmapi/test_gc_utils.py",

"tests/unittest/llmapi/test_llm.py",

"tests/unittest/llmapi/test_llm_args.py",

"tests/unittest/llmapi/test_llm_download.py",

"tests/unittest/llmapi/test_llm_kv_cache_events.py",

"tests/unittest/llmapi/test_llm_multi_gpu_pytorch.py",

"tests/unittest/llmapi/test_llm_pytorch.py",

"tests/unittest/llmapi/test_llm_quant.py",

"tests/unittest/llmapi/test_llm_utils.py",

"tests/unittest/llmapi/test_memory_profiling.py",

"tests/unittest/llmapi/test_mpi_session.py",

"tests/unittest/llmapi/test_reasoning_parser.py",

"tests/unittest/llmapi/test_serialization.py",

"tests/unittest/llmapi/test_utils.py",

"tests/unittest/others/__init__.py",

"tests/unittest/others/test_exception.py",

"tests/unittest/others/test_export.py",

"tests/unittest/others/test_kv_cache_transceiver.py",

"tests/unittest/others/test_kv_cache_update.py",

"tests/unittest/others/test_mapping.py",

"tests/unittest/others/test_multimodal_registry.py",

"tests/unittest/others/test_pretrained_config.py",

"tests/unittest/others/test_time_breakdown.py",

"tests/unittest/profile_utils.py",

"tests/unittest/scaffolding/__init__.py",

"tests/unittest/scaffolding/test_bench.py",

"tests/unittest/scaffolding/test_parallel_process.py",

"tests/unittest/scaffolding/test_scaffolding.py",

"tests/unittest/scaffolding/test_task_collection.py",

"tests/unittest/scaffolding/test_worker.py",

"tests/unittest/tools/__init__.py",

"tests/unittest/tools/test_prepare_dataset.py",

"tests/unittest/tools/test_test_to_stage_mapping.py",

"tests/unittest/utils/__init__.py",

"tests/unittest/utils/cpp_paths.py",

"tests/unittest/utils/llm_data.py",

"tests/unittest/utils/runtime_defaults.py",

"tests/unittest/utils/test_prebuilt_whl_cpp_extensions.py",

"tests/unittest/utils/test_util.py",

"tests/unittest/utils/torch_ref.py",

"tests/unittest/utils/util.py",

"triton_backend/all_models/llmapi/tensorrt_llm/1/helpers.py",

"triton_backend/all_models/llmapi/tensorrt_llm/1/model.py",

"triton_backend/all_models/tests/test_llmapi_python_backend.py",

"triton_backend/scripts/launch_triton_server.py",

"triton_backend/tools/__init__.py",

"triton_backend/tools/fill_template.py",

"triton_backend/tools/inflight_batcher_llm/benchmark_core_model.py",

"triton_backend/tools/inflight_batcher_llm/end_to_end_test.py",

"triton_backend/tools/inflight_batcher_llm/speculative_decoding_test.py",

"triton_backend/tools/inflight_batcher_llm/test_max_queue_size.py",

"triton_backend/tools/llmapi_client.py",

"triton_backend/tools/tests/__init__.py",

"triton_backend/tools/tests/test_fill_template.py",

"triton_backend/tools/tests/test_llmapi_cancel.py",

"triton_backend/tools/utils/__init__.py",

"triton_backend/tools/utils/utils.py",

]

# <<<< END AUTO-GENERATED >>>>

[tool.ruff.lint]

# See available rules at https://docs.astral.sh/ruff/rules/

# Flake8 is equivalent to pycodestyle + pyflakes + mccabe.

select = [

"D", # pydocstyle --> enforcing correct docstrings for existing docstrings

"E", # pycodestyle errors

"F", # pyflakes

"I", # isort

# "N", # pep8 naming # no naming convention enforced for now the reduce the burden

"PLE", # pylint errors

"W", # pycodestyle warnings

]

extend-ignore = [

# we don't enforce writing docstrings for public code to reduce the burden

"D100",

"D101",

"D102",

"D103",

"D104",

"D105",

"D106",

"D107",

"D417",

]

[tool.ruff.lint.per-file-ignores]

"__init__.py" = ["F401", "F403"]

"*/_[a-zA-Z]*" = ["D"] # Private packages (_abc/*.py) or modules (_xyz.py)

[tool.ruff.lint.pycodestyle]

max-line-length = 120 # Line length limit for comments and docstrings

[tool.ruff.lint.pydocstyle]

convention = "google"

[tool.ruff.lint.isort]

known-first-party = ["tensorrt_llm"]

known-third-party = ["triton_kernels"]

split-on-trailing-comma = false

[tool.ruff.lint.pylint]

max-args = 10

[tool.mypy]

install_types = true

non_interactive = true

follow_imports = "silent"

explicit_package_bases = true

namespace_packages = true

strict = true

show_error_codes = true

# Files checked when mypy runs with no explicit paths. This is the single source

# of truth for the type-check file set. Both the CI build stage (which invokes

# scripts/run_mypy.sh directly) and the local pre-commit hook run mypy without

# explicit paths (the hook sets `pass_filenames: false`), so both read this list.

files = [

"tensorrt_llm/_torch/pyexecutor/sampler/sampler.py",

"tensorrt_llm/_torch/pyexecutor/sampler/sampler_common.py",

"tensorrt_llm/_torch/pyexecutor/sampler/sampler_strategy.py",

"tensorrt_llm/_torch/pyexecutor/sampler/logprobs.py",

"tensorrt_llm/_torch/pyexecutor/sampler/sampler_features.py",

"tensorrt_llm/_torch/pyexecutor/sampler/seed_manager.py",

"tensorrt_llm/_torch/pyexecutor/sampler/two_model_spec_dec.py",

"tensorrt_llm/_torch/pyexecutor/sampler/finish_reasons.py",

"tensorrt_llm/_torch/pyexecutor/sampler/top_p_decay.py",

"tensorrt_llm/_torch/pyexecutor/sampler/penalties.py",

"tensorrt_llm/_torch/pyexecutor/sampler/token_ban.py",

"tensorrt_llm/_torch/pyexecutor/sampler/ops/flashinfer.py",

"tensorrt_llm/_torch/pyexecutor/sampler/ops/vanilla.py",

"tests/unittest/_torch/sampler/test_torch_sampler.py",

"tests/unittest/_torch/sampler/test_token_ban.py",

"tests/unittest/_torch/sampler/test_beam_search.py",

"tests/unittest/_torch/sampler/test_beam_search_util.py",

]

# NB:

# . -> 'tensorrt_llm'

# tests/unittest -> 'utils'

# tests/unittest/_torch/sampler -> for 'test_beam_search_util'

mypy_path = ".:tests/unittest:tests/unittest/_torch/sampler"

[[tool.mypy.overrides]]

module = ["tensorrt_llm.bindings.*"]

ignore_errors = true

# Generated pybind11 stub; DeepGEMM returns a bare py::dict from

# get_bf16_mega_gate_config, which stubgen renders without type parameters.

[[tool.mypy.overrides]]

module = ["tensorrt_llm.deep_gemm_cpp_tllm", "deep_gemm_cpp_tllm"]

disallow_any_generics = false

[[tool.mypy.overrides]]

module = [

"tensorrt_llm._torch.pyexecutor.sampler",

"tensorrt_llm._torch.pyexecutor.sampler.*",

]

disable_error_code = [

"no-untyped-call",

# TODO(TRTLLM-15310): strict mode's warn_redundant_casts flags several cast(...) calls

# in sampler_strategy.py (introduced by #16620). Whether a cast is "redundant" is

# binding-dependent -- the full build check (compiled bindings + stubs) flags 2,

# the bindings-less local/pre-commit check flags ~20 -- so removing casts is a

# fragile WAR. Suppress redundant-cast for the sampler module until the casts are

# audited and the annotations tightened, rather than churn the source.

"redundant-cast",

]

[[tool.mypy.overrides]]

module = [

"tests.*",

"_torch.*", # tests/unittest/_torch/*, cf. mypy_path

"test_torch_sampler", # tests/unittest/_torch/sampler/..., cf. mypy_path

"test_token_ban", # tests/unittest/_torch/sampler/..., cf. mypy_path

"test_beam_search", # tests/unittest/_torch/sampler/..., cf. mypy_path

"test_beam_search_util", # tests/unittest/_torch/sampler/..., cf. mypy_path

]

disable_error_code = [

"no-untyped-def",

"no-untyped-call",

]