TensorRT-LLM/.gitignore at main · NVIDIA/TensorRT-LLM · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
__pycache__/
.mypy_cache/
.vscode
.zed
.cursor
*.engine
*.engine.config
*.cache
*.nsys-rep
*.npy
*.so
*.whl
.VSCodeCounter
cpp/build*
cpp/Release
build
!tensorrt_llm/bench/build
!builders/
*.egg-info/
.coverage
*.onnx
tmp/
venv/
.venv/
.venv-*/
.python-version
.local/
.hypothesis/
.idea/
dump*/
.trt-internal
*.dot
*.prof
*.log
*.pkl
*.hdf5
config.json
/*.svg
cpp/cmake-build-*
cpp/.ccache
cpp/.conan
tensorrt_llm/bin
tensorrt_llm/include
tensorrt_llm/libs
tensorrt_llm/bindings.*.so
tensorrt_llm/bindings.pyi
tensorrt_llm/bindings/**/*.pyi
tensorrt_llm/tensorrt_llm_transfer_agent_binding.*.so
tensorrt_llm/tensorrt_llm_transfer_agent_binding.pyi
tensorrt_llm/deep_ep
tensorrt_llm/deep_ep_cpp_tllm.*.so
tensorrt_llm/deep_ep_cpp_tllm.pyi
tensorrt_llm/deep_gemm
tensorrt_llm/deep_gemm_cpp_tllm.*.so
tensorrt_llm/deep_gemm_cpp_tllm.pyi
tensorrt_llm/pg_utils_bindings.*.so
tensorrt_llm/flash_mla
tensorrt_llm/flash_mla_cpp_tllm.*.so
tensorrt_llm/flash_mla_cpp_tllm.pyi
/3rdparty/fmha_sm100/
tensorrt_llm/runtime/kv_cache_manager_v2/**/*.so
**/*__mypyc*.so
tensorrt_llm/scripts
*docs/cpp_docs*
*docs/source/_cpp_gen*
docs/source/**/*.rst
!docs/source/examples/index.rst
!docs/source/_includes/note_sections.rst
!docs/source/features/auto_deploy/transforms.rst
!docs/source/features/auto_deploy/transforms/
!docs/source/features/auto_deploy/transforms/*.rst
*.swp
.nfs*

# Testing
.coverage.*
results_trt/
llm-test-workspace/
ad-test-workspace/

# FetchContent reference cache
3rdparty/.cache_3rdparty/

# build/debug
*.safetensors
*/tllm_debug/**
*.patch
!cpp/tensorrt_llm/deep_ep/*.patch
examples/disaggregated/slurm/benchmark/logs/
scripts/attribution/data/checksum_to_paths.yml

# Generated files
/ATTRIBUTIONS.md
cpp/include/tensorrt_llm/executor/version.h
cpp/tensorrt_llm/kernels/contextFusedMultiHeadAttention/fmha_v2_cu/
cpp/tensorrt_llm/kernels/contextFusedMultiHeadAttention/cubin/fmha_cubin.h
cpp/tensorrt_llm/kernels/contextFusedMultiHeadAttention/cubin/fmha_cubin.cpp
.devcontainer/.env
/examples/layer_wise_benchmarks/autotuner_cache/
/examples/layer_wise_benchmarks/profiles/

# User config files
CLAUDE.local.md
CMakeUserPresets.json
compile_commands.json
*.bin
.dir-locals.el
.devcontainer/devcontainer.env.user
.devcontainer/docker-compose.override.yml

# Enroot sqsh files
enroot/sw-tensorrt-docker+*.sqsh
enroot/tensorrt_llm.devel.sqsh

# MacOSX Files
.DS_Store

# stress test aiperf output artifacts
tests/integration/defs/stress_test/artifacts/

# Agent related files
.claude/agent-memory/
.claude/agent-tests/perf-test-sync/report.html
.claude/agent-tests/perf-test-sync/results.json
.claude/settings.json

.plans/

# Kimi K3 eval harness per-job runtime configs
# (run_eval_kimi_k3.sbatch --parallel tep and --dflash rewrites)
examples/kimi_k3/.eval_tep_runtime.*.yaml
examples/kimi_k3/.eval_dflash_runtime.*.yaml