# 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 . .

# Build the upstream GB10 Blackwell SageAttention3 package; the base image supplies CUDA 13 and Torch.
RUN git clone --depth 1 https://github.com/thu-ml/SageAttention.git /tmp/SageAttention \
    && cd /tmp/SageAttention/sageattention3_blackwell \
    && sed -i 's/cc_major, cc_minor = torch.cuda.get_device_capability()/cc_major, cc_minor = (12, 1)/' setup.py \
    && TORCH_CUDA_ARCH_LIST=12.1a NVCC_APPEND_FLAGS='-gencode=arch=compute_121a,code=sm_121a' python -m pip install --no-cache-dir --no-build-isolation . \
    && rm -rf /tmp/SageAttention

RUN python -m pip install --no-cache-dir --no-deps -e . \
    && python -c "import comfy_kitchen, torch; from sageattn3 import sageattn3_blackwell; 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"]