mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
17 lines
1.1 KiB
Plaintext
17 lines
1.1 KiB
Plaintext
*.a filter=lfs diff=lfs merge=lfs -text
|
|
*.dll filter=lfs diff=lfs merge=lfs -text
|
|
*.lib filter=lfs diff=lfs merge=lfs -text
|
|
*.so filter=lfs diff=lfs merge=lfs -text
|
|
*.txz filter=lfs diff=lfs merge=lfs -text
|
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
|
triton_backend/tools/gpt/input_data.json filter=lfs diff=lfs merge=lfs -text
|
|
*cubin.cpp filter=lfs diff=lfs merge=lfs -text
|
|
docs/source/blogs/media/tech_blog3_mla_absorb.png filter=lfs diff=lfs merge=lfs -text
|
|
tests/integration/test_input_files/*.png filter=lfs diff=lfs merge=lfs -text
|
|
tests/integration/test_input_files/*.jpg filter=lfs diff=lfs merge=lfs -text
|
|
docs/source/blogs/media/tech_blog10_baseline_performance_detail.png filter=lfs diff=lfs merge=lfs -text
|
|
docs/source/blogs/media/tech_blog10_full_strategy_performance.png filter=lfs diff=lfs merge=lfs -text
|
|
docs/source/blogs/media/tech_blog10_context_wait_performance.png filter=lfs diff=lfs merge=lfs -text
|
|
cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/kernelMetaInfo_cubin.cpp filter=lfs diff=lfs merge=lfs -text
|
|
cpp/tensorrt_llm/kernels/decoderMaskedMultiheadAttention/cubin/xqa_kernel_cubin.cpp filter=lfs diff=lfs merge=lfs -text
|