winglian's picture
fix for accelerate env var for auto bf16, add new base image and expand torch_cuda_arch_list support (#1413)
da265dd unverified
raw
history blame
2.26 kB
name: ci-cd-base
on:
workflow_dispatch:
jobs:
build-base:
if: github.repository_owner == 'OpenAccess-AI-Collective'
# this job needs to be run on self-hosted GPU runners...
runs-on: axolotl-gpu-runner
strategy:
fail-fast: false
matrix:
include:
- cuda: "118"
cuda_version: 11.8.0
python_version: "3.10"
pytorch: 2.1.2
torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
- cuda: "121"
cuda_version: 12.1.0
python_version: "3.10"
pytorch: 2.1.2
torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
- cuda: "121"
cuda_version: 12.1.0
python_version: "3.11"
pytorch: 2.1.2
torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
- cuda: "121"
cuda_version: 12.1.0
python_version: "3.11"
pytorch: 2.2.1
torch_cuda_arch_list: "7.0 7.5 8.0 8.6 8.7 8.9 9.0+PTX"
steps:
- name: Checkout
uses: actions/checkout@v3
- name: Docker metadata
id: metadata
uses: docker/metadata-action@v3
with:
images: winglian/axolotl-base
- name: Login to Docker Hub
uses: docker/login-action@v2
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@v4
with:
context: .
file: ./docker/Dockerfile-base
push: ${{ github.event_name != 'pull_request' }}
tags: ${{ steps.metadata.outputs.tags }}-base-py${{ matrix.python_version }}-cu${{ matrix.cuda }}-${{ matrix.pytorch }}${{ matrix.axolotl_extras != '' && '-' || '' }}${{ matrix.axolotl_extras }}
labels: ${{ steps.metadata.outputs.labels }}
build-args: |
CUDA_VERSION=${{ matrix.cuda_version }}
CUDA=${{ matrix.cuda }}
PYTHON_VERSION=${{ matrix.python_version }}
PYTORCH_VERSION=${{ matrix.pytorch }}
TORCH_CUDA_ARCH_LIST=${{ matrix.torch_cuda_arch_list }}