feat(load-balancer): implement Live Load Balancer runtime Docker infrastructure

.github/workflows/ci.yml

@@ -128,10 +128,103 @@ jobs:
           echo "Testing CPU handler in Docker environment..."
           docker run --rm tetra-rp-cpu:test ./test-handler.sh
 
+  docker-test-lb:
+    runs-on: ubuntu-latest
+    needs: [test, lint]
+    steps:
+      - name: Clear Space
+        if: github.event_name == 'pull_request'
+        run: |
+          rm -rf /usr/share/dotnet
+          rm -rf /opt/ghc
+          rm -rf "/usr/local/share/boost"
+          rm -rf "$AGENT_TOOLSDIRECTORY"
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: recursive
+          fetch-depth: 0
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Setup dependencies
+        run: |
+          uv sync
+          git submodule update
+          cp tetra-rp/src/tetra_rp/protos/remote_execution.py src/
+
+      - name: Build Load Balancer Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile-lb
+          platforms: linux/amd64
+          push: false
+          tags: tetra-rp-lb:test
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          load: true
+
+  docker-test-lb-cpu:
+    runs-on: ubuntu-latest
+    needs: [test, lint]
+    steps:
+      - name: Clear Space
+        if: github.event_name == 'pull_request'
+        run: |
+          rm -rf /usr/share/dotnet
+          rm -rf /opt/ghc
+          rm -rf "/usr/local/share/boost"
+          rm -rf "$AGENT_TOOLSDIRECTORY"
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: recursive
+          fetch-depth: 0
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Setup dependencies
+        run: |
+          uv sync
+          git submodule update
+          cp tetra-rp/src/tetra_rp/protos/remote_execution.py src/
+
+      - name: Build CPU Load Balancer Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile-lb-cpu
+          platforms: linux/amd64
+          push: false
+          tags: tetra-rp-lb-cpu:test
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+          load: true
 
   release:
     runs-on: ubuntu-latest
-    needs: [test, lint, docker-test]
+    needs: [test, lint, docker-test, docker-test-lb, docker-test-lb-cpu]
     if: github.ref == 'refs/heads/main'
     outputs:
       release_created: ${{ steps.release.outputs.release_created }}
@@ -255,6 +348,111 @@ jobs:
           cache-from: type=gha
           cache-to: type=gha,mode=max
 
+  docker-main-lb:
+    runs-on: ubuntu-latest
+    needs: [test, lint, docker-test, docker-test-lb, release]
+    if: github.ref == 'refs/heads/main' && github.event_name == 'push' && !needs.release.outputs.release_created
+    steps:
+      - name: Clear Space
+        run: |
+          rm -rf /usr/share/dotnet
+          rm -rf /opt/ghc
+          rm -rf "/usr/local/share/boost"
+          rm -rf "$AGENT_TOOLSDIRECTORY"
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: recursive
+          fetch-depth: 0
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Setup dependencies
+        run: |
+          uv sync
+          git submodule update
+          cp tetra-rp/src/tetra_rp/protos/remote_execution.py src/
+
+      - name: Build and push Load Balancer Docker image (main)
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile-lb
+          platforms: linux/amd64
+          push: true
+          tags: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-lb:main
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  docker-main-lb-cpu:
+    runs-on: ubuntu-latest
+    needs: [test, lint, docker-test, docker-test-lb-cpu, release]
+    if: github.ref == 'refs/heads/main' && github.event_name == 'push' && !needs.release.outputs.release_created
+    steps:
+      - name: Clear Space
+        run: |
+          rm -rf /usr/share/dotnet
+          rm -rf /opt/ghc
+          rm -rf "/usr/local/share/boost"
+          rm -rf "$AGENT_TOOLSDIRECTORY"
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: recursive
+          fetch-depth: 0
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Setup dependencies
+        run: |
+          uv sync
+          git submodule update
+          cp tetra-rp/src/tetra_rp/protos/remote_execution.py src/
+
+      - name: Build and push CPU Load Balancer Docker image (main)
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile-lb-cpu
+          platforms: linux/amd64
+          push: true
+          tags: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-lb-cpu:main
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
 
   docker-prod-gpu:
     runs-on: ubuntu-latest
@@ -380,4 +578,130 @@ jobs:
           tags: ${{ steps.meta-cpu.outputs.tags }}
           labels: ${{ steps.meta-cpu.outputs.labels }}
           cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  docker-prod-lb:
+    runs-on: ubuntu-latest
+    needs: [release]
+    if: needs.release.outputs.release_created
+    steps:
+      - name: Clear Space
+        run: |
+          rm -rf /usr/share/dotnet
+          rm -rf /opt/ghc
+          rm -rf "/usr/local/share/boost"
+          rm -rf "$AGENT_TOOLSDIRECTORY"
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: recursive
+          fetch-depth: 0
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Extract Load Balancer metadata
+        id: meta-lb
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-lb
+          tags: |
+            type=semver,pattern={{version}}
+            type=raw,value=latest,enable={{is_default_branch}}
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Setup dependencies
+        run: |
+          uv sync
+          git submodule update
+          cp tetra-rp/src/tetra_rp/protos/remote_execution.py src/
+
+      - name: Build and push Load Balancer Docker image (prod)
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile-lb
+          platforms: linux/amd64
+          push: true
+          tags: ${{ steps.meta-lb.outputs.tags }}
+          labels: ${{ steps.meta-lb.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+  docker-prod-lb-cpu:
+    runs-on: ubuntu-latest
+    needs: [release]
+    if: needs.release.outputs.release_created
+    steps:
+      - name: Clear Space
+        run: |
+          rm -rf /usr/share/dotnet
+          rm -rf /opt/ghc
+          rm -rf "/usr/local/share/boost"
+          rm -rf "$AGENT_TOOLSDIRECTORY"
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          submodules: recursive
+          fetch-depth: 0
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Extract CPU Load Balancer metadata
+        id: meta-lb-cpu
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-lb-cpu
+          tags: |
+            type=semver,pattern={{version}}
+            type=raw,value=latest,enable={{is_default_branch}}
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@v4
+        with:
+          enable-cache: true
+
+      - name: Setup dependencies
+        run: |
+          uv sync
+          git submodule update
+          cp tetra-rp/src/tetra_rp/protos/remote_execution.py src/
+
+      - name: Build and push CPU Load Balancer Docker image (prod)
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile-lb-cpu
+          platforms: linux/amd64
+          push: true
+          tags: ${{ steps.meta-lb-cpu.outputs.tags }}
+          labels: ${{ steps.meta-lb-cpu.outputs.labels }}
+          cache-from: type=gha
           cache-to: type=gha,mode=max

Dockerfile-lb

@@ -0,0 +1,39 @@
+FROM pytorch/pytorch:2.8.0-cuda12.8-cudnn9-runtime
+
+WORKDIR /app
+
+# Prevent interactive prompts during package installation
+ENV DEBIAN_FRONTEND=noninteractive
+# Set timezone to avoid tzdata prompts
+ENV TZ=Etc/UTC
+
+# Enable HuggingFace transfer acceleration
+ENV HF_HUB_ENABLE_HF_TRANSFER=1
+# Relocate HuggingFace cache outside /root/.cache to exclude from volume sync
+ENV HF_HOME=/hf-cache
+
+# Configure APT cache to persist under /root/.cache for volume sync
+RUN mkdir -p /root/.cache/apt/archives/partial \
+ && echo 'Dir::Cache "/root/.cache/apt";' > /etc/apt/apt.conf.d/01cache
+
+# Install system dependencies and uv
+RUN DEBIAN_FRONTEND=noninteractive apt-get update && apt-get install -y --no-install-recommends \
+    build-essential curl ca-certificates nala git \
+ && curl -LsSf https://astral.sh/uv/install.sh | sh \
+ && cp ~/.local/bin/uv /usr/local/bin/uv \
+ && chmod +x /usr/local/bin/uv \
+ && apt-get clean \
+ && rm -rf /var/lib/apt/lists/*
+
+# Copy app code and install dependencies
+COPY README.md pyproject.toml uv.lock ./
+COPY src/ ./
+RUN uv export --format requirements-txt --no-dev --no-hashes > requirements.txt \
+ && uv pip install --system -r requirements.txt
+
+EXPOSE 80
+
+# CMD will be overridden by RunPod at runtime to run the specific generated handler
+# The handler factory generates handler_{resource_name}.py files
+# RunPod will invoke: uvicorn handler_{resource_name}:app --host 0.0.0.0 --port 80
+CMD ["uvicorn", "lb_handler:app", "--host", "0.0.0.0", "--port", "80", "--timeout-keep-alive", "600"]