forked from ztxz16/fastllm
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Dockerfile
22 lines (15 loc) · 796 Bytes
/
Dockerfile
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
# syntax=docker/dockerfile:1-labs
FROM nvidia/cuda:12.1.0-devel-ubuntu22.04
# Update Apt repositories
RUN apt-get update
# Install and configure Python
RUN apt-get -y --no-install-recommends install wget build-essential python3.10 python3-pip
RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.10 1
RUN pip install setuptools streamlit-chat
ENV WORKDIR /fastllm
# Install cmake
RUN wget -c https://cmake.org/files/LatestRelease/cmake-3.28.3-linux-x86_64.sh && bash ./cmake-3.28.3-linux-x86_64.sh --skip-license --prefix=/usr/
WORKDIR $WORKDIR
ADD . $WORKDIR/
RUN mkdir $WORKDIR/build && cd build && cmake .. -DUSE_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES=native && make -j && cd tools && python setup.py install
CMD /fastllm/build/webui -p /models/chatglm2-6b-int8.flm