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

ARG SOL_ATTN_COMMIT=930a4d6e432ff8b8ed5e30ff2f72519b92d69bdf

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==0.2.31

RUN python -m pip install --no-cache-dir "fastsafetensors>=0.1.10"

# Official CuTeDSL FlashAttention-4 beta with CUDA 13 Blackwell support.
RUN python -m pip install --no-cache-dir --pre \
    "flash-attn-4[cu13]==4.0.0b27" \
    "nvidia-cutlass-dsl[cu13]==4.6.2" \
    "quack-kernels==0.6.4"

RUN python -m pip uninstall -y pynvml \
    && python -m pip install --no-cache-dir nvidia-ml-py

RUN git clone https://github.com/Saganaki22/ComfyUI-sol-attn.git /opt/ComfyUI-sol-attn \
    && cd /opt/ComfyUI-sol-attn \
    && git checkout ${SOL_ATTN_COMMIT}

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_'); assert hasattr(comfy_kitchen, 'int8_attention'); assert hasattr(comfy_kitchen, 'int8_attention_is_available'); print(torch.__version__, torch.version.cuda)"

ENV H3_MODEL_PATH=/models/minimax_h3_ref2va_pruned_nvfp4.safetensors
ENV PYTHONPATH=/opt/ComfyUI-sol-attn
ENV TORCH_COMPILE_DISABLE=0 TORCHDYNAMO_DISABLE=0
ENTRYPOINT []
CMD ["bash"]