feat(ci): add github actions workflow and service handling options

.github/workflows/dev.yml

@@ -0,0 +1,73 @@
+name: Build and Push Docker Images
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - "**"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+env:
+  DOCKER_IMAGE: runpod/pod-template
+  DOCKER_PLATFORM: linux/amd64
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Clean up runner disk space
+        run: |
+          echo "Cleaning up unnecessary folders to free disk space..."
+          rm -rf /usr/share/dotnet
+          rm -rf /opt/ghc
+          rm -rf /opt/hostedtoolcache/CodeQL
+          rm -rf "$AGENT_TOOLSDIRECTORY"
+          docker system prune -af || true
+          df -h
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Build and push pip-based image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ./Dockerfile
+          platforms: ${{ env.DOCKER_PLATFORM }}
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ env.DOCKER_IMAGE }}:latest,${{ env.DOCKER_IMAGE }}:pip-latest
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Clean up Docker and disk space between builds
+        run: |
+          echo "Cleaning up Docker and disk space..."
+          docker system prune -af
+          docker builder prune -af
+          rm -rf /tmp/*
+          df -h
+
+      - name: Build and push uv-based image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ./Dockerfile.uv
+          platforms: ${{ env.DOCKER_PLATFORM }}
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ env.DOCKER_IMAGE }}:uv-latest
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

Dockerfile

@@ -1,29 +1,65 @@
-# Use Runpod PyTorch base image
-FROM runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404
-
-# Set environment variables
-ENV PYTHONUNBUFFERED=1
-
-# Set the working directory
-WORKDIR /app
-
-# Install system dependencies if needed
-RUN apt-get update --yes && \
-    DEBIAN_FRONTEND=noninteractive apt-get install --yes --no-install-recommends \
-    wget \
-    && rm -rf /var/lib/apt/lists/*
-
-# Copy requirements file
-COPY requirements.txt /app/
-
-# Install Python dependencies with pip
-# For uv alternative, see Dockerfile.uv
-RUN pip install --no-cache-dir --upgrade pip && \
-    pip install --no-cache-dir -r requirements.txt
-
-# Copy application files
-COPY . /app
-
-# Set the default command
-CMD ["python", "main.py"]
-
+# Use Runpod PyTorch base image
+FROM runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+
+# Set the working directory
+WORKDIR /app
+
+# Install system dependencies if needed
+RUN apt-get update --yes && \
+    DEBIAN_FRONTEND=noninteractive apt-get install --yes --no-install-recommends \
+    wget \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements file
+COPY requirements.txt /app/
+
+# Install Python dependencies with pip
+# For uv alternative, see Dockerfile.uv
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
+
+# Copy application files
+COPY . /app
+
+# ============================================================================
+# OPTION 1: Keep everything from base image (Jupyter, SSH, entrypoint) - DEFAULT
+# ============================================================================
+# The base image already provides everything:
+# - Entrypoint: /opt/nvidia/nvidia_entrypoint.sh (handles CUDA setup)
+# - Default CMD: /start.sh (starts Jupyter/SSH automatically based on template settings)
+# - Jupyter Notebook (starts if startJupyter=true in template)
+# - SSH access (starts if startSsh=true in template)
+#
+# Just don't override CMD - the base image handles everything!
+# CMD is not set, so base image default (/start.sh) is used
+
+# ============================================================================
+# OPTION 2: Override CMD but keep entrypoint and services
+# ============================================================================
+# If you want to run your own command but still have Jupyter/SSH start:
+# - Keep the entrypoint (CUDA setup still happens automatically)
+# - Use the provided run.sh script which starts /start.sh in background,
+#   then runs your application commands
+#
+# Edit run.sh to customize what runs after services start, then uncomment:
+# COPY run.sh /app/run.sh
+# RUN chmod +x /app/run.sh
+# CMD ["/app/run.sh"]
+#
+# The run.sh script:
+# 1. Starts /start.sh in background (starts Jupyter/SSH)
+# 2. Waits for services to initialize
+# 3. Runs your application commands
+# 4. Waits for background processes
+
+# ============================================================================
+# OPTION 3: Override everything - no Jupyter, no SSH, just your app
+# ============================================================================
+# If you don't want any base image services, override both entrypoint and CMD:
+#
+# ENTRYPOINT []  # Clear entrypoint
+# CMD ["python", "/app/main.py"]
+

Dockerfile.uv

@@ -1,30 +1,66 @@
-# Use Runpod PyTorch base image
-FROM runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404
-
-# Set environment variables
-ENV PYTHONUNBUFFERED=1
-
-# Set the working directory
-WORKDIR /app
-
-# Install system dependencies if needed
-RUN apt-get update --yes && \
-    DEBIAN_FRONTEND=noninteractive apt-get install --yes --no-install-recommends \
-    wget \
-    && rm -rf /var/lib/apt/lists/*
-
-# Install uv
-RUN pip install --no-cache-dir uv
-
-# Copy requirements file
-COPY requirements.txt /app/
-
-# Install Python dependencies with uv
-RUN uv pip install --system --break-system-packages -r requirements.txt
-
-# Copy application files
-COPY . /app
-
-# Set the default command
-CMD ["python", "main.py"]
-
+# Use Runpod PyTorch base image
+FROM runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+
+# Set the working directory
+WORKDIR /app
+
+# Install system dependencies if needed
+RUN apt-get update --yes && \
+    DEBIAN_FRONTEND=noninteractive apt-get install --yes --no-install-recommends \
+    wget \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install uv
+RUN pip install --no-cache-dir uv
+
+# Copy requirements file
+COPY requirements.txt /app/
+
+# Install Python dependencies with uv
+RUN uv pip install --system --break-system-packages -r requirements.txt
+
+# Copy application files
+COPY . /app
+
+# ============================================================================
+# OPTION 1: Keep everything from base image (Jupyter, SSH, entrypoint) - DEFAULT
+# ============================================================================
+# The base image already provides everything:
+# - Entrypoint: /opt/nvidia/nvidia_entrypoint.sh (handles CUDA setup)
+# - Default CMD: /start.sh (starts Jupyter/SSH automatically based on template settings)
+# - Jupyter Notebook (starts if startJupyter=true in template)
+# - SSH access (starts if startSsh=true in template)
+#
+# Just don't override CMD - the base image handles everything!
+# CMD is not set, so base image default (/start.sh) is used
+
+# ============================================================================
+# OPTION 2: Override CMD but keep entrypoint and services
+# ============================================================================
+# If you want to run your own command but still have Jupyter/SSH start:
+# - Keep the entrypoint (CUDA setup still happens automatically)
+# - Use the provided run.sh script which starts /start.sh in background,
+#   then runs your application commands
+#
+# Edit run.sh to customize what runs after services start, then uncomment:
+# COPY run.sh /app/run.sh
+# RUN chmod +x /app/run.sh
+# CMD ["/app/run.sh"]
+#
+# The run.sh script:
+# 1. Starts /start.sh in background (starts Jupyter/SSH)
+# 2. Waits for services to initialize
+# 3. Runs your application commands
+# 4. Waits for background processes
+
+# ============================================================================
+# OPTION 3: Override everything - no Jupyter, no SSH, just your app
+# ============================================================================
+# If you don't want any base image services, override both entrypoint and CMD:
+#
+# ENTRYPOINT []  # Clear entrypoint
+# CMD ["python", "/app/main.py"]
+