mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
159 lines
10 KiB
Plaintext
159 lines
10 KiB
Plaintext
# This file defines code ownership rules for the repository.
|
|
|
|
|
|
# TensorRT-LLM Pytorch backend
|
|
/tensorrt_llm/_torch @NVIDIA/trt-llm-torch-devs
|
|
## 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
|
|
/tensorrt_llm/examples/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/test_custom_ops.py @NVIDIA/trt-llm-torch-graph-compiler
|
|
/tests/unittest/_torch/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 - Modules
|
|
/tensorrt_llm/_torch/modules @NVIDIA/trt-llm-torch-modules
|
|
|
|
|
|
## TensorRT-LLM Pytorch Models
|
|
/tensorrt_llm/_torch/models @NVIDIA/trt-llm-torch-models-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_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/resource_manager.py @NVIDIA/trt-llm-torch-models-nemotron-devs @NVIDIA/trt-llm-torch-runtime-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 - Triton backend
|
|
/triton_backend @NVIDIA/trt-llm-triton-backend-devs
|
|
|
|
## 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
|
|
/tensorrt_llm/disaggregated_params.py @NVIDIA/trt-llm-disagg-devs
|
|
/tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py @NVIDIA/trt-llm-disagg-devs
|
|
/tensorrt_llm/_torch/pyexecutor/py_executor.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 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
|
|
### Github workflows
|
|
/tensorrt_llm/.github @NVIDIA/trt-llm-gh-workflows-infra-devs @NVIDIA/trt-llm-infra-devs
|
|
/tensorrt_llm/.coderabbit.yaml @NVIDIA/trt-llm-gh-workflows-infra-devs @NVIDIA/trt-llm-infra-devs
|
|
|
|
## TensorRT-LLM - Docs
|
|
/docs @NVIDIA/trt-llm-doc-owners
|
|
/examples @NVIDIA/trt-llm-doc-owners
|
|
|
|
# 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
|
|
|
|
# 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
|