feat: support nomic models #145
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: Build and push Cuda A10 docker image to registry | |
| on: | |
| workflow_dispatch: | |
| push: | |
| branches: | |
| - 'main' | |
| tags: | |
| - 'v*' | |
| pull_request: | |
| paths: | |
| - ".github/workflows/build.yaml" | |
| # - "integration-tests/**" | |
| - "backends/**" | |
| - "core/**" | |
| - "router/**" | |
| - "Cargo.lock" | |
| - "rust-toolchain.toml" | |
| - "Dockerfile" | |
| branches: | |
| - 'main' | |
| jobs: | |
| build-and-push-image: | |
| concurrency: | |
| group: ${{ github.workflow }}-${{ github.job }}-86-${{ github.head_ref || github.run_id }} | |
| cancel-in-progress: true | |
| runs-on: [self-hosted, intel-cpu, 32-cpu, tgi-ci] | |
| permissions: | |
| contents: write | |
| packages: write | |
| # This is used to complete the identity challenge | |
| # with sigstore/fulcio when running outside of PRs. | |
| id-token: write | |
| security-events: write | |
| steps: | |
| - name: Checkout repository | |
| uses: actions/checkout@v3 | |
| - name: Initialize Docker Buildx | |
| uses: docker/[email protected] | |
| with: | |
| install: true | |
| - name: Configure sccache | |
| uses: actions/github-script@v6 | |
| with: | |
| script: | | |
| core.exportVariable('ACTIONS_CACHE_URL', process.env.ACTIONS_CACHE_URL || ''); | |
| core.exportVariable('ACTIONS_RUNTIME_TOKEN', process.env.ACTIONS_RUNTIME_TOKEN || ''); | |
| - name: Inject slug/short variables | |
| uses: rlespinasse/[email protected] | |
| - name: Tailscale | |
| uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966 | |
| with: | |
| authkey: ${{ secrets.TAILSCALE_AUTHKEY }} | |
| - name: Login to GitHub Container Registry | |
| if: github.event_name != 'pull_request' | |
| uses: docker/login-action@v2 | |
| with: | |
| registry: ghcr.io | |
| username: ${{ github.actor }} | |
| password: ${{ secrets.GITHUB_TOKEN }} | |
| - name: Login to internal Container Registry | |
| uses: docker/[email protected] | |
| with: | |
| username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }} | |
| password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }} | |
| registry: registry.internal.huggingface.tech | |
| - name: Extract metadata (tags, labels) for Docker | |
| id: meta-86 | |
| uses: docker/[email protected] | |
| with: | |
| images: | | |
| registry.internal.huggingface.tech/api-inference/text-embeddings-inference | |
| ghcr.io/huggingface/text-embeddings-inference | |
| flavor: | | |
| latest=false | |
| tags: | | |
| type=semver,pattern=86-{{version}} | |
| type=semver,pattern=86-{{major}}.{{minor}} | |
| type=raw,value=86-latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }} | |
| type=raw,value=86-sha-${{ env.GITHUB_SHA_SHORT }} | |
| - name: Build and push Docker image | |
| id: build-and-push-86 | |
| uses: docker/build-push-action@v4 | |
| with: | |
| context: . | |
| file: Dockerfile-cuda | |
| push: ${{ github.event_name != 'pull_request' }} | |
| platforms: 'linux/amd64' | |
| build-args: | | |
| SCCACHE_GHA_ENABLED=on | |
| ACTIONS_CACHE_URL=${{ env.ACTIONS_CACHE_URL }} | |
| ACTIONS_RUNTIME_TOKEN=${{ env.ACTIONS_RUNTIME_TOKEN }} | |
| CUDA_COMPUTE_CAP=86 | |
| GIT_SHA=${{ env.GITHUB_SHA }} | |
| DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }} | |
| tags: ${{ steps.meta-86.outputs.tags }} | |
| labels: ${{ steps.meta-86.outputs.labels }} | |
| cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/text-embeddings-inference:cache-86,mode=max | |
| cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/text-embeddings-inference:cache-86,mode=max | |
| - name: Extract metadata (tags, labels) for Docker | |
| id: meta-86-grpc | |
| uses: docker/[email protected] | |
| with: | |
| images: | | |
| registry.internal.huggingface.tech/api-inference/text-embeddings-inference | |
| ghcr.io/huggingface/text-embeddings-inference | |
| flavor: | | |
| latest=false | |
| tags: | | |
| type=semver,pattern=86-{{version}}-grpc | |
| type=semver,pattern=86-{{major}}.{{minor}}-grpc | |
| type=raw,value=86-latest-grpc | |
| type=raw,value=86-sha-${{ env.GITHUB_SHA_SHORT }}-grpc | |
| - name: Build and push Docker image | |
| id: build-and-push-86-grpc | |
| uses: docker/build-push-action@v4 | |
| with: | |
| context: . | |
| target: grpc | |
| file: Dockerfile-cuda | |
| push: ${{ github.event_name != 'pull_request' }} | |
| platforms: 'linux/amd64' | |
| build-args: | | |
| SCCACHE_GHA_ENABLED=on | |
| ACTIONS_CACHE_URL=${{ env.ACTIONS_CACHE_URL }} | |
| ACTIONS_RUNTIME_TOKEN=${{ env.ACTIONS_RUNTIME_TOKEN }} | |
| CUDA_COMPUTE_CAP=86 | |
| GIT_SHA=${{ env.GITHUB_SHA }} | |
| DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }} | |
| tags: ${{ steps.meta-86-grpc.outputs.tags }} | |
| labels: ${{ steps.meta-86-grpc.outputs.labels }} | |
| cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/text-embeddings-inference:cache-86,mode=max |