github
/
ColossalAI
mirror of https://github.com/hpcaitech/ColossalAI
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[misc] update dockerfile (#5776) 

* [misc] update dockerfile

* [misc] update dockerfile
pull/5780/head
Hongxin Liu 2024-06-04 16:15:41 +08:00 committed by GitHub
parent e22b82755d
commit 32f4187806
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 8 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
docker/Dockerfile
View File

@ -1,9 +1,9 @@
FROM hpcaitech/cuda-conda:11.3
FROM hpcaitech/cuda-conda:12.1
# metainformation
LABEL org.opencontainers.image.source = "https://github.com/hpcaitech/ColossalAI"
LABEL org.opencontainers.image.licenses = "Apache License 2.0"
LABEL org.opencontainers.image.base.name = "docker.io/library/hpcaitech/cuda-conda:11.3"
LABEL org.opencontainers.image.base.name = "docker.io/library/hpcaitech/cuda-conda:12.1"
# enable passwordless ssh
RUN mkdir ~/.ssh && \
@ -18,7 +18,7 @@ RUN apt-get update && \
rm -rf /var/lib/apt/lists/*
# install torch
RUN conda install -y pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.3 -c pytorch
RUN conda install -y python==3.10 && conda install -y pytorch==2.1.2 torchvision==0.16.2 torchaudio==2.1.2 pytorch-cuda=12.1 -c pytorch -c nvidia
# install ninja
RUN apt-get update && \
@ -29,23 +29,18 @@ RUN apt-get update && \
# install apex
RUN git clone https://github.com/NVIDIA/apex && \
cd apex && \
git checkout 91fcaa && \
git checkout a7de60 && \
pip install packaging && \
pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" --global-option="--fast_layer_norm" ./
pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./
# install colossalai
ARG VERSION=main
RUN git clone -b ${VERSION} https://github.com/hpcaitech/ColossalAI.git \
&& cd ./ColossalAI \
&& BUILD_EXT=1 pip install -v --no-cache-dir .
# install titans
RUN pip install --no-cache-dir titans
&& BUILD_EXT=1 pip install -v . \
&& rm -rf colossalai
# install tensornvme
RUN conda install -y cmake && \
git clone https://github.com/hpcaitech/TensorNVMe.git && \
cd TensorNVMe && \
apt update -y && apt install -y libaio-dev && \
pip install -r requirements.txt && \
pip install -v --no-cache-dir .
pip install -v git+https://github.com/hpcaitech/TensorNVMe.git