h3-blackwell-runtime/Dockerfile.spark

# GB10/Grace Blackwell development image. It does not start inference by default.
FROM ghcr.io/aeon-7/comfyui-aeon-spark:slim

WORKDIR /opt/h3-blackwell-runtime
COPY . .

# Prebuilt against the base image's CUDA 13 / Torch ABI for GB10 (sm_121a).
COPY wheels/sageattn3-*.whl /tmp/wheels/
RUN python -m pip install --no-cache-dir --no-deps /tmp/wheels/sageattn3-*.whl \
    && rm -rf /tmp/wheels

RUN python -m pip install --no-cache-dir --no-deps comfy-kitchen==0.2.28

RUN python -m pip install --no-cache-dir --no-deps -e . \
    && python -c "import comfy_kitchen, torch; from sageattn3 import sageattn3_blackwell; assert hasattr(torch.ops.comfy_kitchen, 'rms_rope_split_half_'); print(torch.__version__, torch.version.cuda)"

ENV H3_MODEL_PATH=/models/minimax_h3_ref2va_pruned_nvfp4.safetensors
ENV TORCH_COMPILE_DISABLE=0 TORCHDYNAMO_DISABLE=0
ENTRYPOINT []
CMD ["bash"]