cloud image w/o tmux (#1628)

This commit is contained in:
Wing Lian
2024-05-15 22:27:40 -04:00
committed by GitHub
parent 419b2a6a98
commit 60113437e4
2 changed files with 68 additions and 0 deletions

View File

@@ -125,3 +125,45 @@ jobs:
${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }}
labels: ${{ steps.metadata.outputs.labels }}
build-axolotl-cloud-no-tmux:
needs: build-axolotl
if: ${{ ! contains(github.event.commits[0].message, '[skip docker]]') && github.repository_owner == 'OpenAccess-AI-Collective' }}
# this job needs to be run on self-hosted GPU runners...
strategy:
matrix:
include:
- cuda: 121
cuda_version: 12.1.0
python_version: "3.11"
pytorch: 2.3.0
axolotl_extras:
runs-on: axolotl-gpu-runner
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Docker metadata
id: metadata
uses: docker/metadata-action@v5
with:
images: winglian/axolotl-cloud-term
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v2
- name: Build
uses: docker/build-push-action@v5
with:
context: .
build-args: |
BASE_TAG=${{ github.ref_name }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
CUDA=${{ matrix.cuda }}
file: ./docker/Dockerfile-cloud-no-tmux
push: ${{ github.event_name != 'pull_request' }}
tags: |
${{ steps.metadata.outputs.tags }}-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
${{ (matrix.is_latest) && format('{0}-latest', steps.metadata.outputs.tags) || '' }}
labels: ${{ steps.metadata.outputs.labels }}

View File

@@ -0,0 +1,26 @@
ARG BASE_TAG=main
FROM winglian/axolotl:$BASE_TAG
ENV HF_DATASETS_CACHE="/workspace/data/huggingface-cache/datasets"
ENV HUGGINGFACE_HUB_CACHE="/workspace/data/huggingface-cache/hub"
ENV TRANSFORMERS_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 && \
mkdir -p ~/.ssh && \
chmod 700 ~/.ssh && \
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
ENTRYPOINT ["/root/cloud-entrypoint.sh"]
CMD ["sleep", "infinity"]