TensorRT-LLM icon indicating copy to clipboard operation
TensorRT-LLM copied to clipboard

error when build TensorRT_LLM engine

Open zxy1119 opened this issue 1 year ago • 11 comments

System Info

image CUDA 11.8 Please tell me what causes this error.

Who can help?

No response

Information

  • [ ] The official example scripts
  • [ ] My own modified scripts

Tasks

  • [ ] An officially supported task in the examples folder (such as GLUE/SQuAD, ...)
  • [ ] My own task or dataset (give details below)

Reproduction

python scripts/build_wheel.py --clean --trt_root /data0/baolili/TensorRT-10.1.0.27 --python_bindings --benchmarks

Expected behavior

Successfully built tensor_llm

actual behavior

Failed to build

additional notes

Failed to build

zxy1119 avatar Aug 18 '24 09:08 zxy1119

Hi, @zxy1119 Which GPU are you using?

Kefeng-Duan avatar Aug 21 '24 09:08 Kefeng-Duan

@Kefeng-Duan nvidia A800 i upgraded CUDA version 11.8 -> 12.2 but still build tensorrt_llm error image

zxy1119 avatar Aug 21 '24 09:08 zxy1119

@zxy1119 have you clean the workspace?

Kefeng-Duan avatar Aug 21 '24 09:08 Kefeng-Duan

i use python3 scripts/build_wheel.py --clean --trt_root /usr/local/TensorRT-10.1.0.27,but image and it is no *.whl file generated in the directory cpp/build. how to clean the workspace?

zxy1119 avatar Aug 21 '24 13:08 zxy1119

@zxy1119 could you update to the latest version, delete the build folder and rerun the build wheel command?

Kefeng-Duan avatar Aug 23 '24 07:08 Kefeng-Duan

it is the latest version , and i think the problem is cutlass_kernels image

this is my version 93546f25e777541f6b2d571dd1a9a6d9906094d2 082e3c8ef4a1ea6d619ef2e373a8b6308f36b12f b203a707c6c7477c21bb9e77eeb4f2cdadd18a60

zxy1119 avatar Aug 23 '24 08:08 zxy1119

@zxy1119 could you show more screenshot about the cutlass error?

Kefeng-Duan avatar Aug 23 '24 08:08 Kefeng-Duan

sure, this is my build log cmake_log.log

zxy1119 avatar Aug 23 '24 08:08 zxy1119

This part of the code seems to be the issue. image image

zxy1119 avatar Aug 23 '24 08:08 zxy1119

@zxy1119 GCC 8 seems too old, please try with a newer GCC. I tested and failed with 8.3, succeeded with 12.2, FYI.

yuhengxnv avatar Aug 25 '24 18:08 yuhengxnv

This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 15 days."

github-actions[bot] avatar Oct 05 '24 02:10 github-actions[bot]

@zxy1119 any updates after trying https://github.com/NVIDIA/TensorRT-LLM/issues/2124#issuecomment-2308950182?

poweiw avatar May 21 '25 22:05 poweiw

Issue has not received an update in over 14 days. Adding stale label.

github-actions[bot] avatar Oct 07 '25 03:10 github-actions[bot]

This issue was closed because it has been 14 days without activity since it has been marked as stale.

github-actions[bot] avatar Oct 21 '25 03:10 github-actions[bot]