[BugFix]add int8 cache dtype when using attention quantization #113
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: 'image' | |
| # This is a docker build check and publish job: | |
| # 1. PR Triggered docker image build check | |
| # - is for image build check | |
| # - Enable on main/*-dev branch | |
| # - push: ${{ github.event_name != 'pull_request' }} ==> false | |
| # 2. branches push trigger image publish | |
| # - is for branch/dev/nightly image | |
| # - commits are merge into main/*-dev ==> vllm-ascend:main / vllm-ascend:*-dev | |
| # 3. tags push trigger image publish | |
| # - is for final release image | |
| # - Publish when tag with v* (pep440 version) ===> vllm-ascend:v1.2.3|latest / vllm-ascend:v1.2.3rc1 | |
| on: | |
| pull_request: | |
| branches: | |
| - 'main' | |
| - '*-dev' | |
| paths: | |
| - '.github/workflows/image.yml' | |
| - 'Dockerfile' | |
| - 'vllm_ascend/**' | |
| push: | |
| # Publish image when tagging, the Dockerfile in tag will be build as tag image | |
| branches: | |
| - 'main' | |
| - '*-dev' | |
| tags: | |
| - 'v*' | |
| paths: | |
| - '.github/workflows/image.yml' | |
| - 'Dockerfile' | |
| - 'vllm_ascend/**' | |
| jobs: | |
| build: | |
| name: vllm-ascend image | |
| runs-on: ubuntu-latest | |
| steps: | |
| - uses: actions/checkout@v4 | |
| - name: Print | |
| run: | | |
| lscpu | |
| - name: Docker meta | |
| id: meta | |
| uses: docker/metadata-action@v5 | |
| with: | |
| # TODO(yikun): add more hub image and a note on release policy for container image | |
| images: | | |
| quay.io/ascend/vllm-ascend | |
| # Note for test case | |
| # https://github.com/marketplace/actions/docker-metadata-action#typeref | |
| # 1. branch job pulish per main/*-dev branch commits | |
| # 2. main and dev pull_request is build only, so the tag pr-N is fine | |
| # 3. only pep440 matched tag will be published: | |
| # - v0.7.1 --> v0.7.1, latest | |
| # - pre/post/dev: v0.7.1rc1/v0.7.1rc1/v0.7.1rc1.dev1/v0.7.1.post1, no latest | |
| # which follow the rule from vLLM with prefix v | |
| # TODO(yikun): the post release might be considered as latest release | |
| tags: | | |
| type=ref,event=branch | |
| type=ref,event=pr | |
| type=pep440,pattern={{raw}} | |
| - name: Free up disk space | |
| uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1 | |
| with: | |
| tool-cache: true | |
| docker-images: false | |
| - name: Build - Set up QEMU | |
| uses: docker/setup-qemu-action@v2 | |
| # TODO(yikun): remove this after https://github.com/docker/setup-qemu-action/issues/198 resolved | |
| with: | |
| image: tonistiigi/binfmt:qemu-v7.0.0-28 | |
| - name: Build - Set up Docker Buildx | |
| uses: docker/setup-buildx-action@v2 | |
| - name: Publish - Login to Quay Container Registry | |
| if: ${{ github.event_name == 'push' }} | |
| uses: docker/login-action@v3 | |
| with: | |
| registry: quay.io | |
| username: ${{ vars.QUAY_USERNAME }} | |
| password: ${{ secrets.QUAY_PASSWORD }} | |
| - name: Build and push | |
| uses: docker/build-push-action@v6 | |
| with: | |
| platforms: linux/amd64,linux/arm64 | |
| cache-from: type=gha | |
| cache-to: type=gha,mode=max | |
| # only trigger when tag, branch/main push | |
| push: ${{ github.event_name != 'pull_request' }} | |
| labels: ${{ steps.meta.outputs.labels }} | |
| tags: ${{ steps.meta.outputs.tags }} | |
| build-args: | | |
| PIP_INDEX_URL=https://pypi.org/simple |