Multi-stage Dockerfile for decord CUDA build

Use devel image for compilation, runtime for final image.
Keeps image smaller while enabling NVDEC decode.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Dockerfile.gpu

@@ -1,6 +1,32 @@
 # GPU-enabled worker image
-# Based on NVIDIA CUDA with Python for CuPy support
+# Multi-stage build: use devel image for compiling, runtime for final image
 
+# Stage 1: Build decord with CUDA
+FROM nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04 AS builder
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    python3.11 \
+    python3.11-venv \
+    python3.11-dev \
+    python3-pip \
+    git \
+    cmake \
+    build-essential \
+    pkg-config \
+    && rm -rf /var/lib/apt/lists/* \
+    && ln -sf /usr/bin/python3.11 /usr/bin/python3 \
+    && ln -sf /usr/bin/python3 /usr/bin/python
+
+# Build decord with CUDA support
+RUN git clone --recursive https://github.com/dmlc/decord /tmp/decord && \
+    cd /tmp/decord && \
+    mkdir build && cd build && \
+    cmake .. -DUSE_CUDA=ON -DCMAKE_BUILD_TYPE=Release \
+             -DCMAKE_CUDA_ARCHITECTURES="70;75;80;86;89;90" && \
+    make -j$(nproc) && \
+    cd ../python && pip install --target=/decord-install .
+
+# Stage 2: Runtime image
 FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04
 
 WORKDIR /app
@@ -26,18 +52,10 @@ RUN pip install --no-cache-dir -r requirements.txt
 # Install GPU-specific dependencies (CuPy for CUDA 12.x)
 RUN pip install --no-cache-dir cupy-cuda12x
 
-# Build decord from source with CUDA support for GPU-native video decoding
+# Copy decord from builder stage
-RUN apt-get update && apt-get install -y --no-install-recommends \
+COPY --from=builder /decord-install /usr/local/lib/python3.11/dist-packages/
-    cmake build-essential \
+COPY --from=builder /tmp/decord/build/libdecord.so /usr/local/lib/
-    && rm -rf /var/lib/apt/lists/*
+RUN ldconfig
-
-RUN git clone --recursive https://github.com/dmlc/decord /tmp/decord && \
-    cd /tmp/decord && \
-    mkdir build && cd build && \
-    cmake .. -DUSE_CUDA=ON -DCMAKE_BUILD_TYPE=Release && \
-    make -j$(nproc) && \
-    cd ../python && pip install . && \
-    rm -rf /tmp/decord
 
 # Copy application
 COPY . .