# This file defines code ownership rules for the repository.

## TensorRT-LLM QA
### Integration Tests
/tests/integration/test_lists/qa @NVIDIA/trt-llm-qa
/tests/integration/defs/examples/test_ray.py @NVIDIA/trt-llm-qa-function
/tests/integration/defs/examples/test_redrafter.py @NVIDIA/trt-llm-qa-function
/tests/integration/defs/accuracy @NVIDIA/trt-llm-qa-function
/tests/integration/defs/stress_test @NVIDIA/trt-llm-qa-function
/tests/integration/defs/triton_server @NVIDIA/trt-llm-qa-function
/tests/integration/defs/test_e2e.py @NVIDIA/trt-llm-qa-function
/tests/integration/defs/disaggregated @NVIDIA/trt-llm-qa-serving
/tests/integration/defs/sysinfo @NVIDIA/trt-llm-qa-perf
/tests/integration/defs/perf @NVIDIA/trt-llm-qa-perf
/tests/integration/defs/perf/disagg @NVIDIA/trt-llm-qa-serving

## TensorRT-LLM Infra
### CI
/jenkins @NVIDIA/trt-llm-ci-infra-devs @NVIDIA/trt-llm-infra-devs
### Setup
/docker @NVIDIA/trt-llm-setup-infra-devs @NVIDIA/trt-llm-infra-devs
/.pre-commit-config.yaml @NVIDIA/trt-llm-setup-infra-devs @NVIDIA/trt-llm-infra-devs
### Github workflows
/.github @NVIDIA/trt-llm-gh-workflows-infra-devs @NVIDIA/trt-llm-infra-devs
/.coderabbit.yaml @NVIDIA/trt-llm-gh-workflows-infra-devs @NVIDIA/trt-llm-infra-devs

## TensorRT-LLM - Docs
/docs @NVIDIA/trt-llm-doc-owners
/CODING_GUIDELINES.md @NVIDIA/trt-llm-doc-owners
/CODE_OF_CONDUCT.md @NVIDIA/trt-llm-doc-owners
/CONTAINER_SOURCE.md @NVIDIA/trt-llm-doc-owners
/CONTRIBUTING.md @NVIDIA/trt-llm-doc-owners
/README.md @NVIDIA/trt-llm-doc-owners

## Examples
/examples @NVIDIA/trt-llm-doc-owners

## TensorRT-LLM - Triton backend
/triton_backend @NVIDIA/trt-llm-triton-backend-devs

# TensorRT-LLM Pytorch backend
/tensorrt_llm/_torch @NVIDIA/trt-llm-torch-devs

## TensorRT-LLM Pytorch - Modules
/tensorrt_llm/_torch/modules @NVIDIA/trt-llm-torch-modules

## TensorRT-LLM Pytorch Models
/tensorrt_llm/_torch/models @NVIDIA/trt-llm-torch-models-devs
/examples/models @NVIDIA/trt-llm-torch-models-devs @NVIDIA/trt-llm-doc-owners

## TensorRT-LLM Pytorch backend - runtime
/tensorrt_llm/_torch/pyexecutor @NVIDIA/trt-llm-torch-runtime-devs
## TensorRT-LLM Pytorch backend - AutoDeploy flow
/tensorrt_llm/_torch/auto_deploy @NVIDIA/trt-llm-torch-autodeploy-devs
/examples/auto_deploy @NVIDIA/trt-llm-torch-autodeploy-devs @NVIDIA/trt-llm-doc-owners
/tests/unittest/_torch/auto_deploy @NVIDIA/trt-llm-torch-autodeploy-devs

## TensorRT-LLM Pytorch - Speculative Decoding
/tensorrt_llm/_torch/speculative @NVIDIA/trt-llm-torch-spec-decoding

## TensorRT-LLM Pytorch - Graph Compiler
/tensorrt_llm/_torch/compilation @NVIDIA/trt-llm-torch-graph-compiler
/tensorrt_llm/_torch/custom_ops @NVIDIA/trt-llm-torch-graph-compiler
/tensorrt_llm/_torch/autotuner.py @NVIDIA/trt-llm-torch-graph-compiler
/tests/unittest/_torch/compilation @NVIDIA/trt-llm-torch-graph-compiler
/tests/unittest/_torch/multi_gpu/test_ar_residual_norm.py @NVIDIA/trt-llm-torch-graph-compiler
/tests/unittest/_torch/multi_gpu/test_user_buffers.py @NVIDIA/trt-llm-torch-graph-compiler
/tests/unittest/_torch/thop/test_custom_ops.py @NVIDIA/trt-llm-torch-graph-compiler
/tests/unittest/_torch/misc/test_autotuner.py @NVIDIA/trt-llm-torch-graph-compiler

## TensorRT-LLM Pytorch - Attention
/tensorrt_llm/_torch/attention_backend @NVIDIA/trt-llm-torch-attention-devs
/tensorrt_llm/_torch/modules/attention.py @NVIDIA/trt-llm-torch-attention-devs


### TensorRT-LLM Pytorch - Models - Gemma
/tensorrt_llm/_torch/models/modeling_gemma3.py @NVIDIA/trt-llm-torch-models-gemma-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_gemma3vl.py @NVIDIA/trt-llm-torch-models-gemma-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_gemma3.py @NVIDIA/trt-llm-torch-models-gemma-devs @NVIDIA/trt-llm-torch-models-devs

### TensorRT-LLM Pytorch - Models - Mistral & Mixtral
/tensorrt_llm/_torch/models/modeling_mistral.py @NVIDIA/trt-llm-torch-models-mistral-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_pixtral.py @NVIDIA/trt-llm-torch-models-mistral-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_mistral.py @NVIDIA/trt-llm-torch-models-mistral-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_mixtral.py @NVIDIA/trt-llm-torch-models-mistral-devs @NVIDIA/trt-llm-torch-models-devs

### TensorRT-LLM Pytorch - Models - CLIP
/tensorrt_llm/_torch/models/modeling_clip.py @NVIDIA/trt-llm-torch-models-clip-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_clip.py @NVIDIA/trt-llm-torch-models-clip-devs @NVIDIA/trt-llm-torch-models-devs

### TensorRT-LLM Pytorch - Models - Phi
/tensorrt_llm/_torch/models/modeling_phi3.py @NVIDIA/trt-llm-torch-models-phi-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_phi4mm.py @NVIDIA/trt-llm-torch-models-phi-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_phi3.py @NVIDIA/trt-llm-torch-models-phi-devs @NVIDIA/trt-llm-torch-models-devs
/tests/integration/defs/examples/test_multimodal.py @NVIDIA/trt-llm-torch-models-phi-devs @NVIDIA/trt-llm-torch-models-devs

### TensorRT-LLM Pytorch - Models - Deepseek
/tensorrt_llm/_torch/models/modeling_deepseekv3.py @NVIDIA/trt-llm-torch-models-deepseek-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_deepseek.py @NVIDIA/trt-llm-torch-models-deepseek-devs @NVIDIA/trt-llm-torch-models-devs

### TensorRT-LLM Pytorch - Models - Llama
/tensorrt_llm/_torch/models/modeling_mllama.py @NVIDIA/trt-llm-torch-models-llama-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_llama.py @NVIDIA/trt-llm-torch-models-llama-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_llama_min_latency.py @NVIDIA/trt-llm-torch-models-llama-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_llama.py @NVIDIA/trt-llm-torch-models-llama-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_llama_min_latency.py @NVIDIA/trt-llm-torch-models-llama-devs @NVIDIA/trt-llm-torch-models-devs

### TensorRT-LLM Pytorch - Models - Qwen
/tensorrt_llm/_torch/models/modeling_qwen3_moe.py @NVIDIA/trt-llm-torch-models-qwen-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_qwen3.py @NVIDIA/trt-llm-torch-models-qwen-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_qwen2vl.py @NVIDIA/trt-llm-torch-models-qwen-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_qwen.py @NVIDIA/trt-llm-torch-models-qwen-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_qwen_moe.py @NVIDIA/trt-llm-torch-models-qwen-devs @NVIDIA/trt-llm-torch-models-devs

### TensorRT-LLM Pytorch - Models - VLMs
/tensorrt_llm/_torch/models/modeling_vila.py @NVIDIA/trt-llm-torch-models-vlm-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_vila.py @NVIDIA/trt-llm-torch-models-vlm-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_pixtral.py @NVIDIA/trt-llm-torch-models-vlm-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_pixtral.py @NVIDIA/trt-llm-torch-models-vlm-devs @NVIDIA/trt-llm-torch-models-devs

### TensorRT-LLM Pytorch - Models - Nemotron
/tensorrt_llm/_torch/models/modeling_nanov2vlm.py @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-models-vlm-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_radio.py @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-models-vlm-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_nemotron_nas.py @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_nemotron_h.py @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/modeling_nemotron_nas.py @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/pyexecutor/mamba_cache_manager.py @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/modules/mamba @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-models-devs
/tensorrt_llm/_torch/models/checkpoints/hf/nemotron_h_weight_mapper.py @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_nemotron.py @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_nemotron_h.py @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-models-devs
/tests/unittest/_torch/modeling/test_modeling_nemotron_nas.py @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-models-devs

## TensorRT-LLM - PEFT
/tensorrt_llm/_torch/peft @NVIDIA/trt-llm-torch-peft
/tensorrt_llm/lora_manager.py @NVIDIA/trt-llm-torch-peft
/cpp/tensorrt_llm/batch_manager/peftCacheManager.cpp @NVIDIA/trt-llm-torch-peft
/cpp/include/tensorrt_llm/batch_manager/peftCacheManager.h @NVIDIA/trt-llm-torch-peft
/cpp/tensorrt_llm/runtime/loraCache.cpp @NVIDIA/trt-llm-torch-peft
/cpp/include/tensorrt_llm/runtime/loraCache.h @NVIDIA/trt-llm-torch-peft
/cpp/tensorrt_llm/runtime/loraModule.cpp @NVIDIA/trt-llm-torch-peft
/cpp/include/tensorrt_llm/runtime/loraModule.h @NVIDIA/trt-llm-torch-peft
/cpp/tensorrt_llm/runtime/loraManager.cpp @NVIDIA/trt-llm-torch-peft
/cpp/tensorrt_llm/runtime/loraManager.h @NVIDIA/trt-llm-torch-peft
/cpp/tensorrt_llm/runtime/loraUtils.cpp @NVIDIA/trt-llm-torch-peft
/cpp/tensorrt_llm/runtime/loraUtils.h @NVIDIA/trt-llm-torch-peft


## TensorRT-LLM trtllm-bench Reviewers
/tensorrt_llm/bench @NVIDIA/trtllm-bench-reviewers
/tensorrt_llm/commands/bench.py @NVIDIA/trtllm-bench-reviewers
docs/source/performance/perf-benchmarking.md @NVIDIA/trtllm-bench-reviewers

## TensorRT-LLM LLM API
/tensorrt_llm/llmapi @NVIDIA/trt-llm-llmapi-devs
/tensorrt_llm/executor @NVIDIA/trt-llm-llmapi-devs

## TensorRT-LLM LLM Disaggregated
/examples/disaggregated @NVIDIA/trt-llm-disagg-devs @NVIDIA/trt-llm-doc-owners
/tensorrt_llm/disaggregated_params.py @NVIDIA/trt-llm-disagg-devs
/tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py @NVIDIA/trt-llm-disagg-devs
/cpp/tensorrt_llm/batch_manager/cacheFormatter.cpp @NVIDIA/trt-llm-disagg-devs
/cpp/tensorrt_llm/batch_manager/cacheFormatter.h @NVIDIA/trt-llm-disagg-devs
/cpp/tensorrt_llm/batch_manager/cacheTransBuffer.cpp @NVIDIA/trt-llm-disagg-devs
/cpp/tensorrt_llm/batch_manager/cacheTransBuffer.h @NVIDIA/trt-llm-disagg-devs
/cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp @NVIDIA/trt-llm-disagg-devs
/cpp/tensorrt_llm/batch_manager/dataTransceiver.cpp @NVIDIA/trt-llm-disagg-devs
/cpp/tensorrt_llm/batch_manager/dataTransceiver.h @NVIDIA/trt-llm-disagg-devs
/cpp/tensorrt_llm/batch_manager/dataTransceiverImpl.cpp @NVIDIA/trt-llm-disagg-devs
/cpp/tensorrt_llm/batch_manager/dataTransceiverImpl.h @NVIDIA/trt-llm-disagg-devs
/tensorrt_llm/serve/openai_disagg_server.py @NVIDIA/trt-llm-disagg-devs

## TensorRT-LLM - KV Cache Manager
/cpp/tensorrt_llm/batch_manager/kvCacheManager.cpp @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/tensorrt_llm/batch_manager/kvCacheEventManager.cpp @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/tensorrt_llm/batch_manager/kvCacheTransferManager.cpp @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/tensorrt_llm/batch_manager/evictionPolicy.cpp @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/include/tensorrt_llm/batch_manager/kvCacheManager.h @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/include/tensorrt_llm/batch_manager/kvCacheEventManager.h @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/include/tensorrt_llm/batch_manager/kvCacheTransferManager.h @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/include/tensorrt_llm/batch_manager/evictionPolicy.h @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/tensorrt_llm/batch_manager/allocateKvCache.cpp @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/tests/unit_tests/batch_manager/kvCacheManagerTest.cpp @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/tests/unit_tests/batch_manager/kvCacheUtilsTest.cpp @NVIDIA/trt-llm-kv-cache-manager-devs
/tensorrt_llm/_torch/pyexecutor/resource_manager.py @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/tensorrt_llm/nanobind/batch_manager/kvCacheManager.h @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/tensorrt_llm/nanobind/batch_manager/kvCacheManager.cpp @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/tensorrt_llm/pybind/batch_manager/kvCacheManager.h @NVIDIA/trt-llm-kv-cache-manager-devs
/cpp/tensorrt_llm/pybind/batch_manager/kvCacheManager.cpp @NVIDIA/trt-llm-kv-cache-manager-devs

# The rule below requires that any PR modifying public APIs must be approved by at least one member
# of the NVIDIA/trt-llm-committed-api-review-committee or NVIDIA/trt-llm-noncommitted-api-review-committee team.
# This approval is mandatory regardless of other approvals the PR may have received. Without approval
# from a member of this team, PRs affecting public APIs cannot be merged to main or release branches.
/tests/unittest/api_stability/ @NVIDIA/trt-llm-noncommitted-api-review-committee
/tests/unittest/api_stability/references_committed/ @NVIDIA/trt-llm-committed-api-review-committee

## OSS Compliance & Legal - License/Attribution Protection
## IMPORTANT: Changes to any files below may impact legal compliance, attributions, and third-party licenses.
## These files require review from the TRTLLM OSS compliance team before merging to ensure proper attribution
## and license compliance when adding, removing, or changing versions of dependencies.
### License Files
/LICENSE @NVIDIA/trt-llm-oss-compliance
/ATTRIBUTIONS-*.md @NVIDIA/trt-llm-oss-compliance
/jenkins/license_cpp.json @NVIDIA/trt-llm-ci-infra-devs @NVIDIA/trt-llm-infra-devs @NVIDIA/trt-llm-oss-compliance

### Python Dependency Management
/setup.py @NVIDIA/trt-llm-oss-compliance
/pyproject.toml @NVIDIA/trt-llm-oss-compliance
/requirements.txt @NVIDIA/trt-llm-oss-compliance
/requirements-dev.txt @NVIDIA/trt-llm-oss-compliance

### C++ Build & Dependency Management
/cpp/CMakeLists.txt @NVIDIA/trt-llm-oss-compliance
/cpp/conanfile.py @NVIDIA/trt-llm-oss-compliance
/cpp/cmake/** @NVIDIA/trt-llm-oss-compliance

### Third-Party Dependencies
## Any changes to versions, additions, or removals of third-party libraries
/3rdparty/** @NVIDIA/trt-llm-oss-compliance

### Docker & Installation Scripts
## These scripts install and pin dependency versions
/docker/common/** @NVIDIA/trt-llm-setup-infra-devs @NVIDIA/trt-llm-infra-devs @NVIDIA/trt-llm-oss-compliance

### TAVA Architecture Diagram
/.github/tava_architecture_diagram.md @NVIDIA/trt-llm-TAVA-design-change

### CODEOWNERS file itself
/.github/CODEOWNERS @NVIDIA/trt-llm-gh-workflows-infra-devs @NVIDIA/trt-llm-infra-devs @NVIDIA/trt-llm-oss-compliance

# The following rule should only be uncommented on release branches (e.g., release/0.19).
# The rule below requires that any PR to release/**/* branches must be approved by at least one member
# of the NVIDIA/trt-llm-release-branch-approval team, regardless of who else approves the PR.
# Without approval from a member of this team, PRs cannot be merged to release branches.
# * @NVIDIA/trt-llm-release-branch-approval