TensorRT-LLMs/.gitignore
Chang Liu e47c787dd7
[TRTLLM-8535][feat] Support DeepSeek V3.2 with FP8 + BF16 KV cache/NVFP4 + BF16 KV cache (#8405)
Signed-off-by: Fanrong Li <23290157+lfr-0531@users.noreply.github.com>
Signed-off-by: Chang Liu <9713593+chang-l@users.noreply.github.com>
Signed-off-by: Tracin <10434017+Tracin@users.noreply.github.com>
2025-10-24 13:40:41 -04:00

86 lines
1.5 KiB
Plaintext

__pycache__/
.vscode
*.engine
*.engine.config
*.cache
*.nsys-rep
*.npy
.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/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
*docs/cpp_docs*
*docs/source/_cpp_gen*
docs/source/**/*.rst
!docs/source/examples/index.rst
*.swp
# Testing
.coverage.*
results_trt/
llm-test-workspace/
# build/debug
*.safetensors
*/tllm_debug/**
*.patch
!cpp/tensorrt_llm/deep_ep/*.patch
# Generated files
cpp/include/tensorrt_llm/executor/version.h
cpp/tensorrt_llm/kernels/contextFusedMultiHeadAttention/fmha_v2_cu/
cpp/tensorrt_llm/kernels/contextFusedMultiHeadAttention/cubin/fmha_cubin.h
.devcontainer/.env
# User config files
CMakeUserPresets.json
compile_commands.json
*.bin
.dir-locals.el
.devcontainer/devcontainer.env.user
.devcontainer/docker-compose.override.yml
# Enroot sqsh files
enroot/tensorrt_llm.devel.sqsh