mirror of
https://github.com/comfyanonymous/ComfyUI.git
synced 2026-04-15 13:02:35 +08:00
c55980a268
This commit significantly simplifies the Docker image architecture by removing the complex multi-stage build process that was causing build failures and compatibility issues across different GPU generations. Key changes: - Replace multi-stage builder pattern with runtime-based Sage Attention installation via enhanced entrypoint.sh - Downgrade from CUDA 12.9 to CUDA 12.8 for broader GPU compatibility (RTX 30+ series) - Remove pre-built wheel installation in favor of dynamic source compilation during container startup - Add comprehensive multi-GPU detection and mixed-generation support in entrypoint script - Integrate intelligent build caching with rebuild detection when GPU configuration changes - Remove --use-sage-attention from default CMD to allow flexible runtime configuration Architecture improvements: - Single FROM nvidia/cuda:12.8.0-devel-ubuntu24.04 (was multi-stage with runtime + devel) - Simplified package installation without build/runtime separation - Enhanced Python 3.12 setup with proper symlinks - Removed complex git SHA resolution and cache-busting mechanisms Performance optimizations: - Dynamic CUDA architecture targeting (TORCH_CUDA_ARCH_LIST) based on detected GPUs - Intelligent Triton version selection (3.2 for RTX 20, latest for RTX 30+) - Parallel compilation settings moved to environment variables - Reduced Docker layer count for faster builds and smaller image size The previous multi-stage approach was abandoned due to: - Frequent build failures across different CUDA environments - Complex dependency management between builder and runtime stages - Inability to handle mixed GPU generations at build time - Excessive build times and debugging complexity This runtime-based approach provides better flexibility, reliability, and user experience while maintaining optimal performance through intelligent GPU detection and version selection.
69 lines
1.9 KiB
Docker
69 lines
1.9 KiB
Docker
# Use NVIDIA CUDA 12.8 devel image for compilation support
|
|
FROM nvidia/cuda:12.8.0-devel-ubuntu24.04
|
|
|
|
# Environment
|
|
ENV DEBIAN_FRONTEND=noninteractive \
|
|
PYTHONUNBUFFERED=1 \
|
|
COMFY_AUTO_INSTALL=1 \
|
|
PIP_DISABLE_PIP_VERSION_CHECK=1 \
|
|
PIP_NO_CACHE_DIR=1 \
|
|
EXT_PARALLEL=4 \
|
|
NVCC_APPEND_FLAGS="--threads 8" \
|
|
MAX_JOBS=32 \
|
|
SAGE_ATTENTION_AVAILABLE=0
|
|
|
|
# System deps including Python 3.12
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
python3.12 \
|
|
python3.12-dev \
|
|
python3.12-venv \
|
|
python3-pip \
|
|
git \
|
|
build-essential \
|
|
cmake \
|
|
libgl1 \
|
|
libglx-mesa0 \
|
|
libglib2.0-0 \
|
|
fonts-dejavu-core \
|
|
fontconfig \
|
|
util-linux \
|
|
wget \
|
|
curl \
|
|
&& ln -sf /usr/bin/python3.12 /usr/bin/python \
|
|
&& ln -sf /usr/bin/python3.12 /usr/bin/python3 \
|
|
&& rm -rf /var/lib/apt/lists/*
|
|
|
|
# Create runtime user/group
|
|
RUN groupadd --gid 1000 appuser \
|
|
&& useradd --uid 1000 --gid 1000 --create-home --shell /bin/bash appuser
|
|
|
|
# Workdir
|
|
WORKDIR /app/ComfyUI
|
|
|
|
# Leverage layer caching: install deps before copying full tree
|
|
COPY requirements.txt ./
|
|
|
|
# Core Python deps (torch CUDA 12.8, ComfyUI reqs), media/NVML libs
|
|
RUN python -m pip install --upgrade pip setuptools wheel \
|
|
&& python -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu128 \
|
|
&& python -m pip install triton \
|
|
&& python -m pip install -r requirements.txt \
|
|
&& python -m pip install imageio-ffmpeg "av>=14.2" nvidia-ml-py
|
|
|
|
# Copy the application
|
|
COPY . .
|
|
|
|
# Entrypoint
|
|
COPY entrypoint.sh /entrypoint.sh
|
|
RUN chmod +x /entrypoint.sh \
|
|
&& chown -R appuser:appuser /app /home/appuser /entrypoint.sh
|
|
|
|
EXPOSE 8188
|
|
|
|
# Start as root so entrypoint can adjust ownership and drop privileges
|
|
USER root
|
|
ENTRYPOINT ["/entrypoint.sh"]
|
|
|
|
# Default command - entrypoint will add --use-sage-attention if available
|
|
CMD ["python", "main.py", "--listen", "0.0.0.0"]
|