Files
celery/Dockerfile.gpu
giles 41adf058bd
Some checks are pending
GPU Worker CI/CD / test (push) Waiting to run
GPU Worker CI/CD / deploy (push) Blocked by required conditions
Build decord from source with CUDA for GPU video decode
- Build decord with -DUSE_CUDA=ON for true NVDEC hardware decode
- Use DLPack for zero-copy transfer from decord to CuPy
- Frames stay on GPU throughout: decode -> process -> encode

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-04 01:50:14 +00:00

62 lines
1.8 KiB
Docker

# GPU-enabled worker image
# Based on NVIDIA CUDA with Python for CuPy support
FROM nvidia/cuda:12.1.1-cudnn8-runtime-ubuntu22.04
WORKDIR /app
# Install Python 3.11 and system dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
python3.11 \
python3.11-venv \
python3-pip \
git \
ffmpeg \
&& rm -rf /var/lib/apt/lists/* \
&& ln -sf /usr/bin/python3.11 /usr/bin/python3 \
&& ln -sf /usr/bin/python3 /usr/bin/python
# Upgrade pip
RUN python3 -m pip install --upgrade pip
# Install CPU dependencies first
COPY requirements.txt .
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
RUN apt-get update && apt-get install -y --no-install-recommends \
cmake build-essential \
&& rm -rf /var/lib/apt/lists/*
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 . .
# Clone effects repo
RUN git clone https://git.rose-ash.com/art-dag/effects.git /app/artdag-effects
# Create cache directory
RUN mkdir -p /data/cache
ENV PYTHONUNBUFFERED=1
ENV PYTHONDONTWRITEBYTECODE=1
ENV EFFECTS_PATH=/app/artdag-effects
ENV PYTHONPATH=/app
# 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
# Default command runs celery worker
CMD ["celery", "-A", "celery_app", "worker", "--loglevel=info", "-E", "-Q", "gpu,celery"]