starlight-apk/Qwen
1
0
Fork 0
mirror of https://github.com/QwenLM/Qwen.git synced 2026-05-20 16:35:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

add trt docker file && add warning for ascend

Browse Source
This commit is contained in:
贺弘
2024-01-31 10:14:37 +08:00
committed by Ren Xuancheng
parent ee01f36ed9
commit 99b13b4fd2
2 changed files with 16 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
recipes/inference/tensorrt/docker/Dockerfile Normal file
View File

@@ -0,0 +1,14 @@
FROM nvidia/cuda:12.1.0-devel-ubuntu22.04
RUN apt-get update && \
apt-get -y install python3.10 python3-pip openmpi-bin libopenmpi-dev git && \
rm -rf /var/lib/apt/lists/*
RUN pip install tensorrt_llm==0.8.0.dev2024011601 -U --no-cache-dir --pre --extra-index-url https://pypi.nvidia.com
RUN pip install --no-cache-dir modelscope==1.11.1
RUN git clone https://github.com/NVIDIA/TensorRT-LLM.git && \
cd TensorRT-LLM && \
git checkout c89653021e66ca78c55f02b366f404455bc12e8d && \
pip install --no-cache-dir -r examples/qwen/requirements.txt