search

NVIDIA / TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.
https://nvidia.github.io/TensorRT-LLM
Apache License 2.0
8.5k stars 964 forks source link

unknown flag: --trt_root #2348

Open Gu0725 opened 1 week ago

Gu0725 commented 1 week ago

kou@SERVER04:/data/ghj/TensorRT-LLM$ make -C docker build make: 进入目录“/data/ghj/TensorRT-LLM/docker” Building docker image: tensorrt_llm/devel:latest DOCKER_BUILDKIT=1 docker build --pull \ --progress auto \ --build-arg BASE_IMAGE=nvcr.io/nvidia/pytorch \ --build-arg BASE_TAG=24.07-py3 \ --build-arg BUILD_WHEEL_ARGS="--clean --trt_root /usr/local/tensorrt --python_bindings --benchmarks" \ --build-arg TORCH_INSTALL_TYPE="skip" \ \ \ \ \ \ --build-arg TRT_LLM_VER="0.15.0.dev2024101500" \ \ --build-arg GIT_COMMIT="75057cd036af25e288c004d8ac9e52fd2d6224aa" \ --target devel \ --file Dockerfile.multi \ --tag tensorrt_llm/devel:latest \ .. unknown flag: --trt_root See 'docker buildx build --help'. make: *** [Makefile:64：devel_build] 错误 125 make: 离开目录“/data/ghj/TensorRT-LLM/docker”

Superjomn commented 1 week ago

You can follow the build from source instructions.

Gu0725 commented 1 week ago

You can follow the build from source instructions.

I have tried building from source multiple times, but the issue still persists. It works fine on other devices, but not on my own server. Do you have any alternative suggestions?

Superjomn commented 2 days ago

Maybe you can try a clean build by re-clone the source code, and re-try the make.