Fusing and parallelizing builds.

.github/workflows/build.yaml

@@ -18,15 +18,23 @@ on:
       - "Cargo.lock"
       - "rust-toolchain.toml"
       - "Dockerfile"
+      - "Dockerfile_amd"
+      - "Dockerfile_intel"
     branches:
       - 'main'
 
 jobs:
   build-and-push-image:
     concurrency:
-      group: ${{ github.workflow }}-build-and-push-image-${{ github.head_ref || github.run_id }}
+      group: ${{ github.workflow }}-build-and-push-image-${{ matrix.name }}-${{ github.head_ref || github.run_id }}
       cancel-in-progress: true
     runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, ci]
+    strategy:
+      matrix: [
+        {name: "cuda", label: "", dockerfile: "Dockerfile"},
+        {name: "amd", label: "-rocm", dockerfile: "Dockerfile_amd"},
+        {name: "intel", label: "-intel", dockerfile: "Dockerfile_intel"}
+      ]
     permissions:
       contents: write
       packages: write
@@ -76,7 +84,7 @@ jobs:
           images: |
             registry.internal.huggingface.tech/api-inference/community/text-generation-inference
           tags: |
-            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
+            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ matrix.label }}
       # If main, release or tag
       - name: Extract metadata (tags, labels) for Docker
         if: ${{ github.event_name != 'pull_request' }}
@@ -90,237 +98,38 @@ jobs:
             ghcr.io/huggingface/text-generation-inference
             db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
           tags: |
-            type=semver,pattern={{version}}
+            type=semver,pattern={{version}}${{ matrix.label }}
-            type=semver,pattern={{major}}.{{minor}}
+            type=semver,pattern={{major}}.{{minor}}${{ matrix.label }}
-            type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
+            type=raw,value=latest${{ matrix.label }},enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
-            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
+            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}${{ matrix.label }}
       - name: Build and push Docker image
         id: build-and-push
         uses: docker/build-push-action@v4
         with:
           context: .
-          file: Dockerfile
+          file: ${{ matrix.dockerfile }}
           push: true
           platforms: 'linux/amd64'
           build-args: |
             GIT_SHA=${{ env.GITHUB_SHA }}
-            DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}
+            DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}${{ matrix.label }}
           tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
           labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
-          cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=min
+          cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache${{ matrix.label }},mode=min
-          cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=min
+          cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache${{ matrix.label }},mode=min
-
-  integration-tests:
-    concurrency:
-      group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
-      cancel-in-progress: true
-    needs:
-      - build-and-push-image # Wait for the docker image to be built
-    runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, ci]
-    env:
-      DOCKER_VOLUME: /mnt/cache
-    steps:
-      - uses: actions/checkout@v2
-      - name: Inject slug/short variables
-        uses: rlespinasse/github-slug-action@v4.4.1
       - name: Set up Python
+        if: ${{ matrix.name }} == "cuda"
         uses: actions/setup-python@v4
         with:
           python-version: 3.9
-      - name: Tailscale
-        uses: huggingface/tailscale-action@main
-        with:
-          authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
       - name: Install
+        if: ${{ matrix.name }} == "cuda"
         run: |
           make install-integration-tests
       - name: Run tests
+        if: ${{ matrix.name }} == "cuda"
         run: |
+          export DOCKER_VOLUME=/mnt/cache
           export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ env.GITHUB_SHA_SHORT }}
           export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
           pytest -s -vv integration-tests
-
-  build-and-push-image-rocm:
-    concurrency:
-      group: ${{ github.workflow }}-build-and-push-image-rocm-${{ github.head_ref || github.run_id }}
-      cancel-in-progress: true
-    needs:
-      - build-and-push-image # Wait for the main docker image to be built
-      - integration-tests # Wait for the main integration-tests
-    runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, 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/setup-buildx-action@v2.0.0
-        with:
-          install: true
-      - name: Inject slug/short variables
-        uses: rlespinasse/github-slug-action@v4.4.1
-      - name: Tailscale
-        uses: huggingface/tailscale-action@main
-        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/login-action@v2.1.0
-        with:
-          username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }}
-          password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
-          registry: registry.internal.huggingface.tech
-      - name: Login to Azure Container Registry
-        if: github.event_name != 'pull_request'
-        uses: docker/login-action@v2.1.0
-        with:
-          username: ${{ secrets.AZURE_DOCKER_USERNAME }}
-          password: ${{ secrets.AZURE_DOCKER_PASSWORD }}
-          registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io
-      # If pull request
-      - name: Extract metadata (tags, labels) for Docker
-        if: ${{ github.event_name == 'pull_request' }}
-        id: meta-pr
-        uses: docker/metadata-action@v4.3.0
-        with:
-          images: |
-            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
-          tags: |
-            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
-      # If main, release or tag
-      - name: Extract metadata (tags, labels) for Docker
-        if: ${{ github.event_name != 'pull_request' }}
-        id: meta
-        uses: docker/metadata-action@v4.3.0
-        with:
-          flavor: |
-            latest=false
-          images: |
-            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
-            ghcr.io/huggingface/text-generation-inference
-            db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
-          tags: |
-            type=semver,pattern={{version}}-rocm
-            type=semver,pattern={{major}}.{{minor}}-rocm
-            type=raw,value=latest-rocm,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
-            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
-      - name: Build and push Docker image
-        id: build-and-push
-        uses: docker/build-push-action@v4
-        with:
-          context: .
-          file: Dockerfile_amd
-          push: true
-          platforms: 'linux/amd64'
-          build-args: |
-            GIT_SHA=${{ env.GITHUB_SHA }}
-            DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}-rocm
-          tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
-          cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-rocm,mode=min
-          cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-rocm,mode=min
-
-  build-and-push-image-intel:
-    concurrency:
-      group: ${{ github.workflow }}-build-and-push-image-intel-${{ github.head_ref || github.run_id }}
-      cancel-in-progress: true
-    needs:
-      - build-and-push-image # Wait for the main docker image to be built
-      - integration-tests # Wait for the main integration-tests
-    runs-on: [self-hosted, nvidia-gpu , multi-gpu, 4-a10, 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
-    outputs:
-      # env is not available in the later `container:`, but previous job outputs are.
-      short_sha: ${{ env.GITHUB_SHA_SHORT }}
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v3
-      - name: Initialize Docker Buildx
-        uses: docker/setup-buildx-action@v2.0.0
-        with:
-          install: true
-      - name: Inject slug/short variables
-        uses: rlespinasse/github-slug-action@v4.4.1
-      - name: Tailscale
-        uses: huggingface/tailscale-action@main
-        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/login-action@v2.1.0
-        with:
-          username: ${{ secrets.TAILSCALE_DOCKER_USERNAME }}
-          password: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
-          registry: registry.internal.huggingface.tech
-      - name: Login to Azure Container Registry
-        if: github.event_name != 'pull_request'
-        uses: docker/login-action@v2.1.0
-        with:
-          username: ${{ secrets.AZURE_DOCKER_USERNAME }}
-          password: ${{ secrets.AZURE_DOCKER_PASSWORD }}
-          registry: db4c2190dd824d1f950f5d1555fbadf0.azurecr.io
-      # If pull request
-      - name: Extract metadata (tags, labels) for Docker
-        if: ${{ github.event_name == 'pull_request' }}
-        id: meta-pr
-        uses: docker/metadata-action@v4.3.0
-        with:
-          images: |
-            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
-          tags: |
-            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-intel
-      # If main, release or tag
-      - name: Extract metadata (tags, labels) for Docker
-        if: ${{ github.event_name != 'pull_request' }}
-        id: meta
-        uses: docker/metadata-action@v4.3.0
-        with:
-          flavor: |
-            latest=false
-          images: |
-            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
-            ghcr.io/huggingface/text-generation-inference
-            db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
-          tags: |
-            type=semver,pattern={{version}}-intel
-            type=semver,pattern={{major}}.{{minor}}-intel
-            type=raw,value=latest-intel,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
-            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}-intel
-      - name: Build and push Docker image
-        id: build-and-push
-        uses: docker/build-push-action@v4
-        with:
-          context: .
-          file: Dockerfile_intel
-          push: true
-          platforms: 'linux/amd64'
-          build-args: |
-            GIT_SHA=${{ env.GITHUB_SHA }}
-            DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}-intel
-          tags: ${{ steps.meta.outputs.tags || steps.meta-pr.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels || steps.meta-pr.outputs.labels }}
-          cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min
-          cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache-intel,mode=min