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

[docker] added ssh and rdma support for docker (#4192)

pull/4141/head
Frank Lee 2023-07-07 15:31:51 +08:00 committed by GitHub
parent 190a6ea9c2
commit fee32a3b78
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 12 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
docker/Dockerfile
View File

@ -5,6 +5,18 @@ LABEL org.opencontainers.image.source = "https://github.com/hpcaitech/ColossalAI
LABEL org.opencontainers.image.licenses = "Apache License 2.0" 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:11.3"
# enable passwordless ssh
RUN mkdir ~/.ssh && \
printf "Host * \n ForwardAgent yes\nHost *\n StrictHostKeyChecking no" > ~/.ssh/config && \
ssh-keygen -t rsa -N "" -f ~/.ssh/id_rsa && \
cat ~/.ssh/id_rsa.pub >> ~/.ssh/authorized_keys
# enable RDMA support
RUN apt-get update && \
apt-get install -y infiniband-diags perftest ibverbs-providers libibumad3 libibverbs1 libnl-3-200 libnl-route-3-200 librdmacm1 && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
# install torch # install torch
RUN conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.3 -c pytorch RUN conda install pytorch==1.12.1 torchvision==0.13.1 torchaudio==0.12.1 cudatoolkit=11.3 -c pytorch