Upgrade to v1.2

.github/workflows/build_75.yaml

@@ -7,18 +7,6 @@
        - 'main'
      tags:
        - 'v*'
-   pull_request:
-     paths:
-       - ".github/workflows/build_75.yaml"
-#       - "integration-tests/**"
-       - "backends/**"
-       - "core/**"
-       - "router/**"
-       - "Cargo.lock"
-       - "rust-toolchain.toml"
-       - "Dockerfile"
-     branches:
-       - 'main'
 
  jobs:
    build-and-push-image:

.github/workflows/build_86.yaml

@@ -7,18 +7,6 @@
        - '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:

.github/workflows/build_89.yaml

@@ -7,18 +7,6 @@
        - '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:

.github/workflows/build_90.yaml

@@ -7,18 +7,6 @@
        - '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:

.github/workflows/build_all.yaml

@@ -0,0 +1,105 @@
+ name: Build and push Cuda docker image to registry
+
+ on:
+   workflow_dispatch:
+   push:
+     tags:
+       - 'v*'
+
+ jobs:
+   build-and-push-image:
+     concurrency:
+       group: ${{ github.workflow }}-${{ github.job }}-all-${{ 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: 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: ${{ secrets.TAILSCALE_DOCKER_PASSWORD }}
+           registry: registry.internal.huggingface.tech
+       - name: Extract metadata (tags, labels) for Docker
+         id: meta
+         uses: docker/[email protected]
+         with:
+           images: |
+             registry.internal.huggingface.tech/api-inference/text-embeddings-inference
+             ghcr.io/huggingface/text-embeddings-inference
+           flavor: |
+             latest=false
+           tags: |
+             type=semver,pattern=cuda-{{version}}
+             type=semver,pattern=cuda-{{major}}.{{minor}}
+             type=raw,value=cuda-latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
+             type=raw,value=cuda-sha-${{ env.GITHUB_SHA_SHORT }}
+       - name: Build and push Docker image
+         id: build-and-push
+         uses: docker/build-push-action@v4
+         with:
+           context: .
+           file: Dockerfile-cuda-all
+           push: ${{ github.event_name != 'pull_request' }}
+           platforms: 'linux/amd64'
+           build-args: |
+             GIT_SHA=${{ env.GITHUB_SHA }}
+             DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}
+           tags: ${{ steps.meta.outputs.tags }}
+           labels: ${{ steps.meta.outputs.labels }}
+           cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/text-embeddings-inference:cache-all,mode=max
+           cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/text-embeddings-inference:cache-all,mode=max
+       - name: Extract metadata (tags, labels) for Docker
+         id: meta-sagemaker
+         uses: docker/[email protected]
+         with:
+           images: |
+             registry.internal.huggingface.tech/api-inference/text-embeddings-inference/sagemaker
+           flavor: |
+             latest=false
+           tags: |
+             type=semver,pattern=cuda-{{version}}
+             type=semver,pattern=cuda-{{major}}.{{minor}}
+             type=raw,value=cuda-latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
+             type=raw,value=cuda-sha-${{ env.GITHUB_SHA_SHORT }}
+       - name: Build and push Docker image
+         id: build-and-push-sagemaker
+         uses: docker/build-push-action@v4
+         with:
+           context: .
+           file: Dockerfile-cuda-all
+           push: ${{ github.event_name != 'pull_request' }}
+           platforms: 'linux/amd64'
+           target: sagemaker
+           build-args: |
+             GIT_SHA=${{ env.GITHUB_SHA }}
+             DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}
+           tags: ${{ steps.meta-sagemaker.outputs.tags }}
+           labels: ${{ steps.meta-sagemaker.outputs.labels }}
+           cache-from: type=registry,ref=registry.internal.huggingface.tech/api-inference/text-embeddings-inference:cache-all,mode=max
+           cache-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/text-embeddings-inference:cache-all,mode=max