Add decord for GPU-native video decode

- Install decord in GPU Dockerfile for hardware video decode
- Update GPUVideoSource to use decord with GPU context
- Decord decodes on GPU via NVDEC, avoiding CPU memory copies
- Falls back to FFmpeg pipe if decord unavailable
- Enable STREAMING_GPU_PERSIST=1 for full GPU pipeline

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

Dockerfile.gpu

@@ -26,6 +26,10 @@ 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
 
+# Install decord for GPU-accelerated video decoding (keeps frames on GPU)
+# This avoids CPU<->GPU memory transfers during video decode
+RUN pip install --no-cache-dir decord
+
 # Copy application
 COPY . .
 
@@ -39,8 +43,8 @@ ENV PYTHONUNBUFFERED=1
 ENV PYTHONDONTWRITEBYTECODE=1
 ENV EFFECTS_PATH=/app/artdag-effects
 ENV PYTHONPATH=/app
-# GPU persistence disabled until all primitives support GPU frames
-ENV STREAMING_GPU_PERSIST=0
+# GPU persistence enabled - frames stay on GPU throughout pipeline
+ENV STREAMING_GPU_PERSIST=1
 # Use cluster's public IPFS gateway for HLS segment URLs
 ENV IPFS_GATEWAY_URL=https://celery-artdag.rose-ash.com/ipfs