Files
axolotl/docker/Dockerfile-cloud
Wing Lian 31a15a49b6 add additional packages via apt for better multi-node support (#2949)
* cleanup in Dockerfile and add infiniband packages

* fixes for ci

* fix nightly too
2025-07-20 21:19:23 -04:00

29 lines
1.1 KiB
Plaintext

ARG BASE_TAG=main
FROM axolotlai/axolotl:$BASE_TAG
ENV HF_DATASETS_CACHE="/workspace/data/huggingface-cache/datasets"
ENV HF_HUB_CACHE="/workspace/data/huggingface-cache/hub"
ENV HF_HOME="/workspace/data/huggingface-cache/hub"
ENV HF_HUB_ENABLE_HF_TRANSFER="1"
EXPOSE 8888
EXPOSE 22
COPY scripts/cloud-entrypoint.sh /root/cloud-entrypoint.sh
COPY scripts/motd /etc/motd
RUN pip install jupyterlab notebook ipywidgets && \
jupyter lab clean
RUN apt install --yes --no-install-recommends openssh-server tmux iproute2 nvtop ibverbs-providers ibverbs-utils infiniband-diags librdmacm-dev librdmacm1 rdmacm-utils slurm-wlm && \
rm -rf /var/lib/apt/lists/* && \
mkdir -p ~/.ssh && \
chmod 700 ~/.ssh && \
printf "\n[[ -z \"\$TMUX\" ]] && { tmux attach-session -t ssh_tmux || tmux new-session -s ssh_tmux; exit; }\n" >> ~/.bashrc && \
printf "[ ! -z \"\$TERM\" -a -r /etc/motd ] && cat /etc/motd\n" >> ~/.bashrc && \
chmod +x /workspace/axolotl/scripts/cloud-entrypoint.sh && \
chmod +x /root/cloud-entrypoint.sh && \
echo 'set-option -g history-limit 5000' >> ~/.tmux.conf
ENTRYPOINT ["/root/cloud-entrypoint.sh"]
CMD ["sleep", "infinity"]