Add new workflow to push Docker images (#179)

.github/workflows/autodocs.yml

@@ -1,24 +0,0 @@
-name: Automatic Documentation for Launcher
-
-on:
-  pull_request:
-
-jobs:
-  update_docs:
-    runs-on: ubuntu-latest
-
-    steps:
-    - name: Checkout code
-      uses: actions/checkout@v2
-
-    - name: Install Launcher
-      id: install-launcher
-      env:
-        REF: ${{ github.head_ref }}
-        REPO: ${{ github.repository }}
-      run: cargo install --git "https://github.com/$REPO" --branch "$REF" text-generation-launcher
-
-    - name: Check launcher Docs are up-to-date
-      run: |
-        echo text-generation-launcher --help
-        python update_doc.py --check

.github/workflows/build.yaml

@@ -1,394 +0,0 @@
-name: Build and push docker image to internal registry
-
-on:
-  workflow_dispatch:
-  push:
-    branches:
-      - 'main'
-    tags:
-      - 'v*'
-  pull_request:
-    paths:
-      - ".github/workflows/build.yaml"
-      - "integration-tests/**"
-      - "server/**"
-      - "proto/**"
-      - "router/**"
-      - "launcher/**"
-      - "Cargo.lock"
-      - "rust-toolchain.toml"
-      - "Dockerfile"
-    branches:
-      - 'main'
-
-jobs:
-  start-runner:
-    name: Start self-hosted EC2 runner
-    runs-on: ubuntu-latest
-    env:
-      AWS_REGION: us-east-1
-      EC2_AMI_ID: ami-03cfed9ea28f4b002
-      EC2_INSTANCE_TYPE: g5.12xlarge
-      EC2_SUBNET_ID: subnet-931b34f5,subnet-ecb993cd,subnet-943dc2d8,subnet-45371f1a,subnet-ee93e0df,subnet-fddc3dfc
-      EC2_SECURITY_GROUP: sg-030175c435ac141d6
-    outputs:
-      label: ${{ steps.start-ec2-runner.outputs.label }}
-      ec2-instance-id: ${{ steps.start-ec2-runner.outputs.ec2-instance-id }}
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ env.AWS_REGION }}
-      - name: Start EC2 runner
-        id: start-ec2-runner
-        uses: philschmid/philschmid-ec2-github-runner@main
-        with:
-          mode: start
-          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
-          ec2-image-id: ${{ env.EC2_AMI_ID }}
-          ec2-instance-type: ${{ env.EC2_INSTANCE_TYPE }}
-          subnet-id: ${{ env.EC2_SUBNET_ID }}
-          security-group-id: ${{ env.EC2_SECURITY_GROUP }}
-          aws-resource-tags: > # optional, requires additional permissions
-            [
-              {"Key": "Name", "Value": "ec2-tgi-github-runner"},
-              {"Key": "GitHubRepository", "Value": "${{ github.repository }}"}
-            ]
-
-  build-and-push-image:
-    concurrency:
-      group: ${{ github.workflow }}-build-and-push-image-${{ github.head_ref || github.run_id }}
-      cancel-in-progress: true
-    needs: start-runner # required to start the main job when the runner is ready
-    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
-    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: 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/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 }}
-      # If main, release or tag
-      - name: Extract metadata (tags, labels) for Docker
-        if: ${{ github.event_name != 'pull_request' }}
-        id: meta
-        uses: docker/metadata-action@v4.3.0
-        with:
-          flavor: |
-            latest=auto
-          images: |
-            registry.internal.huggingface.tech/api-inference/community/text-generation-inference
-            ghcr.io/huggingface/text-generation-inference
-            db4c2190dd824d1f950f5d1555fbadf0.azurecr.io/text-generation-inference
-          tags: |
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=raw,value=latest,enable=${{ github.ref == format('refs/heads/{0}', github.event.repository.default_branch) }}
-            type=raw,value=sha-${{ env.GITHUB_SHA_SHORT }}
-      - name: Build and push Docker image
-        id: build-and-push
-        uses: docker/build-push-action@v4
-        with:
-          context: .
-          file: Dockerfile
-          push: true
-          platforms: 'linux/amd64'
-          build-args: |
-            GIT_SHA=${{ env.GITHUB_SHA }}
-            DOCKER_LABEL=sha-${{ env.GITHUB_SHA_SHORT }}
-          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-to: type=registry,ref=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:cache,mode=min
-
-  integration-tests:
-    concurrency:
-      group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
-      cancel-in-progress: true
-    needs:
-      - start-runner
-      - build-and-push-image # Wait for the docker image to be built
-    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
-    env:
-      DOCKER_VOLUME: /cache
-    steps:
-      - uses: actions/checkout@v2
-      - name: Inject slug/short variables
-        uses: rlespinasse/github-slug-action@v4.4.1
-      - name: Set up Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: 3.9
-      - name: Tailscale
-        uses: tailscale/github-action@7bd8039bf25c23c4ab1b8d6e2cc2da2280601966
-        with:
-          authkey: ${{ secrets.TAILSCALE_AUTHKEY }}
-      - name: Prepare disks
-        run: |
-          sudo mkfs -t ext4 /dev/nvme1n1
-          sudo mkdir ${{ env.DOCKER_VOLUME }}
-          sudo mount /dev/nvme1n1 ${{ env.DOCKER_VOLUME }}
-      - name: Install
-        run: |
-          make install-integration-tests
-      - name: Run tests
-        run: |
-          export DOCKER_IMAGE=registry.internal.huggingface.tech/api-inference/community/text-generation-inference:sha-${{ 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:
-      - start-runner
-      - build-and-push-image # Wait for the main docker image to be built
-      - integration-tests # Wait for the main integration-tests
-    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
-    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: 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/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:
-      - start-runner
-      - build-and-push-image # Wait for the main docker image to be built
-      - integration-tests # Wait for the main integration-tests
-    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
-    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: 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/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
-
-  stop-runner:
-    name: Stop self-hosted EC2 runner
-    needs:
-      - start-runner
-      - build-and-push-image
-      - build-and-push-image-rocm
-      - build-and-push-image-intel
-      - integration-tests
-    runs-on: ubuntu-latest
-    env:
-      AWS_REGION: us-east-1
-    if: ${{ always() }} # required to stop the runner even if the error happened in the previous jobs
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ env.AWS_REGION }}
-      - name: Stop EC2 runner
-        uses: philschmid/philschmid-ec2-github-runner@main
-        with:
-          mode: stop
-          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
-          label: ${{ needs.start-runner.outputs.label }}
-          ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }}

.github/workflows/build_documentation.yml

@@ -1,20 +0,0 @@
-name: Build documentation
-
-on:
-  push:
-    paths:
-      - "docs/source/**"
-    branches:
-      - main
-      - doc-builder*
-      - v*-release
-
-jobs:
-   build:
-    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@main
-    with:
-      commit_sha: ${{ github.sha }}
-      package: text-generation-inference
-      additional_args: --not_python_module
-    secrets:
-      hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}

.github/workflows/build_pr_documentation.yml

@@ -1,19 +0,0 @@
-name: Build PR Documentation
-
-on:
-  pull_request:
-    paths:
-      - "docs/source/**"
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  build:
-    uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@main
-    with:
-      commit_sha: ${{ github.event.pull_request.head.sha }}
-      pr_number: ${{ github.event.number }}
-      package: text-generation-inference
-      additional_args: --not_python_module

.github/workflows/client-tests.yaml

@@ -1,25 +0,0 @@
-name: Python Client Tests
-
-on:
-  pull_request:
-    paths:
-      - ".github/workflows/client-tests.yaml"
-      - "clients/python/**"
-
-jobs:
-  run_tests:
-    runs-on: ubuntu-latest
-
-    steps:
-      - uses: actions/checkout@v2
-      - name: Set up Python
-        uses: actions/setup-python@v1
-        with:
-          python-version: 3.9
-      - name: Install
-        run: |
-          cd clients/python && pip install .
-      - name: Run tests
-        run: |
-          pip install pytest pytest-asyncio
-          make python-client-tests

.github/workflows/load_test.yaml

@@ -1,108 +0,0 @@
-name: Nightly load test
-
-on:
-  schedule:
-    - cron: '0 0 * * 1-5'
-
-  pull_request:
-    paths:
-      - ".github/workflows/load_test.yaml"
-    branches:
-      - 'main'
-
-jobs:
-  start-runner:
-    name: Start self-hosted EC2 runner
-    runs-on: ubuntu-latest
-    env:
-      AWS_REGION: eu-central-1
-      EC2_AMI_ID: ami-0ab09c07cfd194259
-      EC2_INSTANCE_TYPE: g5.12xlarge
-      EC2_SUBNET_ID: subnet-988fd9f2,subnet-6f56db13,subnet-6a039326
-      EC2_SECURITY_GROUP: sg-072f92ae3082936c6
-    outputs:
-      label: ${{ steps.start-ec2-runner.outputs.label }}
-      ec2-instance-id: ${{ steps.start-ec2-runner.outputs.ec2-instance-id }}
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ env.AWS_REGION }}
-      - name: Start EC2 runner
-        id: start-ec2-runner
-        uses: philschmid/philschmid-ec2-github-runner@main
-        with:
-          mode: start
-          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
-          ec2-image-id: ${{ env.EC2_AMI_ID }}
-          ec2-instance-type: ${{ env.EC2_INSTANCE_TYPE }}
-          subnet-id: ${{ env.EC2_SUBNET_ID }}
-          security-group-id: ${{ env.EC2_SECURITY_GROUP }}
-          aws-resource-tags: > # optional, requires additional permissions
-            [
-              {"Key": "Name", "Value": "ec2-tgi-github-runner"},
-              {"Key": "GitHubRepository", "Value": "${{ github.repository }}"}
-            ]
-
-  load-tests:
-    concurrency:
-      group: ${{ github.workflow }}-${{ github.job }}-${{ github.head_ref || github.run_id }}
-      cancel-in-progress: true
-    needs: start-runner # required to start the main job when the runner is ready
-    runs-on: ${{ needs.start-runner.outputs.label }} # run the job on the newly created runner
-    env:
-      DOCKER_VOLUME: /cache
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v3
-
-      - name: Prepare disks
-        run: |
-          sudo mkfs -t ext4 /dev/nvme1n1
-          sudo mkdir ${{ env.DOCKER_VOLUME }}
-          sudo mount /dev/nvme1n1 ${{ env.DOCKER_VOLUME }}
-
-      - name: Install k6
-        run: |
-          curl https://github.com/grafana/k6/releases/download/v0.44.0/k6-v0.44.0-linux-amd64.tar.gz -L | tar xvz --strip-components 1
-
-      - name: Start starcoder
-        run: |
-          docker run --name tgi-starcoder --rm --gpus all -p 3000:80 -v ${{ env.DOCKER_VOLUME }}:/data -e HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }} --pull always -d ghcr.io/huggingface/text-generation-inference:latest --model-id bigcode/starcoder --num-shard 2 --max-batch-total-tokens 32768
-          sleep 10
-          wget --timeout 10 --retry-on-http-error --waitretry=1 --tries=240 http://localhost:3000/health
-
-      - name: Run k6
-        run: |
-          ./k6 run load_tests/starcoder_load.js
-
-      - name: Stop starcoder
-        if: ${{ always() }}
-        run: |
-          docker stop tgi-starcoder || true
-
-  stop-runner:
-    name: Stop self-hosted EC2 runner
-    needs:
-      - start-runner
-      - load-tests
-    runs-on: ubuntu-latest
-    env:
-      AWS_REGION: eu-central-1
-    if: ${{ always() }} # required to stop the runner even if the error happened in the previous jobs
-    steps:
-      - name: Configure AWS credentials
-        uses: aws-actions/configure-aws-credentials@v1
-        with:
-          aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
-          aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
-          aws-region: ${{ env.AWS_REGION }}
-      - name: Stop EC2 runner
-        uses: philschmid/philschmid-ec2-github-runner@main
-        with:
-          mode: stop
-          github-token: ${{ secrets.GH_PERSONAL_ACCESS_TOKEN }}
-          label: ${{ needs.start-runner.outputs.label }}
-          ec2-instance-id: ${{ needs.start-runner.outputs.ec2-instance-id }}

.github/workflows/push_docker_image.yml

@@ -0,0 +1,56 @@
+name: Build and push docker image to Github registry
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Tag for the Docker image:'
+        required: true
+
+jobs:
+  build-and-push:
+    concurrency:
+      group: ${{ github.workflow }}
+      cancel-in-progress: true
+    runs-on: ubuntu-latest
+    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@v4
+      - name: Initialize Docker Buildx
+        uses: docker/setup-buildx-action@v3
+        with:
+          install: true
+          config-inline: |
+            [registry."docker.io"]
+      - name: Login to GitHub Container Registry
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v4.3.0
+        with:
+          flavor: |
+            latest=true
+          images: ghcr.io/huggingface/tgi-gaudi
+          tags: |
+            type=raw,value=${{ github.event.inputs.tag }}
+      - name: Build and push Docker image
+        id: build-and-push
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          file: ../../Dockerfile
+          push: true
+          platforms: 'linux/amd64'
+          tags: ${{ steps.meta.outputs.tags }}

.github/workflows/stale.yml

@@ -1,14 +0,0 @@
-name: 'Close stale issues and PRs'
-on:
-  schedule:
-    - cron: '30 1 * * *'
-
-jobs:
-  stale:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/stale@v8
-        with:
-          stale-issue-message: 'This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.'
-          days-before-stale: 30
-          days-before-close: 5

.github/workflows/tests.yaml

@@ -1,88 +0,0 @@
-name: Server Tests
-
-on:
-  pull_request:
-    paths:
-      - ".github/workflows/tests.yaml"
-      - "server/**"
-      - "proto/**"
-      - "router/**"
-      - "launcher/**"
-      - "Cargo.lock"
-      - "rust-toolchain.toml"
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  run_tests:
-    runs-on: ubuntu-latest
-
-    env:
-      SCCACHE_GHA_ENABLED: "on"
-      RUSTC_WRAPPER: /usr/local/bin/sccache
-      SCCACHE: 0.3.3
-
-    steps:
-      - uses: actions/checkout@v2
-      - name: Set up Python
-        uses: actions/setup-python@v1
-        with:
-          python-version: 3.9
-      - name: Install Rust
-        uses: actions-rs/toolchain@v1
-        with:
-          # Released on: 28 December, 2023
-          # Branched from master on: 10 November, 2023
-          # https://releases.rs/docs/1.75.0/
-          toolchain: 1.75.0
-          override: true
-          components: rustfmt, clippy
-      - name: Install Protoc
-        uses: arduino/setup-protoc@v1
-      - name: Clean unused files
-        run: |
-          sudo rm -rf /usr/local/lib/android # will release about 10 GB if you don't need Android
-          sudo rm -rf /usr/share/dotnet # will release about 20GB if you don't need .NET
-      - name: Install sccache
-        run: |
-          curl -fsSL https://github.com/mozilla/sccache/releases/download/v$SCCACHE/sccache-v$SCCACHE-x86_64-unknown-linux-musl.tar.gz | tar -xzv --strip-components=1 -C /usr/local/bin sccache-v$SCCACHE-x86_64-unknown-linux-musl/sccache
-          chmod +x /usr/local/bin/sccache
-      - name: configure sccache
-        uses: actions/github-script@v6
-        with:
-          script: |
-            core.exportVariable('ACTIONS_CACHE_URL', process.env.ACTIONS_CACHE_URL || '');
-            core.exportVariable('ACTIONS_RUNTIME_TOKEN', process.env.ACTIONS_RUNTIME_TOKEN || '');
-            core.exportVariable('SCCACHE_GHA_CACHE_TO', 'sccache-${{runner.os}}-${{github.ref_name}}');
-            core.exportVariable('SCCACHE_GHA_CACHE_FROM', 'sccache-${{runner.os}}-main,sccache-${{runner.os}}-');
-      - name: cargo registry cache
-        uses: actions/cache@v3
-        with:
-          key: cargo-${{ runner.os }}-${{ hashFiles('**/Cargo.toml') }}-${{ github.sha }}
-          restore-keys: |
-            cargo-${{ runner.os }}-${{ hashFiles('**/Cargo.toml') }}-
-            cargo-${{ runner.os }}-
-          path: |
-            ~/.cargo/registry
-            ~/.cargo/git
-      - name: Install
-        run: |
-          make install
-      - name: Run server tests
-        run: |
-          pip install pytest
-          export HUGGING_FACE_HUB_TOKEN=${{ secrets.HUGGING_FACE_HUB_TOKEN }}
-          pytest -s -vv server/tests
-      - name: Pre-commit checks
-        run: |
-          pip install pre-commit
-          pre-commit install
-          pre-commit run --all-files
-      - name: Run Rust tests
-        run: |
-          cargo test
-      - name: sccache stats
-        run: |
-          /usr/local/bin/sccache --show-stats

.github/workflows/upload_pr_documentation.yml

@@ -1,16 +0,0 @@
-name: Upload PR Documentation
-
-on:
-  workflow_run:
-    workflows: ["Build PR Documentation"]
-    types:
-      - completed
-
-jobs:
-  build:
-    uses: huggingface/doc-builder/.github/workflows/upload_pr_documentation.yml@main
-    with:
-      package_name: text-generation-inference
-    secrets:
-      hf_token: ${{ secrets.HF_DOC_BUILD_PUSH }}
-      comment_bot_token: ${{ secrets.COMMENT_BOT_TOKEN }}