dockerfile

FROM lmsysorg/sglang:v0.5.9-cu130
ARG ARCH=arm64

RUN pip install --no-deps "transformers==5.2.0" "huggingface-hub==1.4.1"

# Build and install flashinfer from source with fp4 quantization fix.
# Keep this aligned with the v0.5.9 base image's flashinfer_python version.
RUN --mount=type=cache,target=/root/.cache/pip \
    --mount=type=cache,target=/sgl-workspace/flashinfer-build \
    bash -c 'if [ ! -d /sgl-workspace/flashinfer-build/flashinfer ]; then git clone https://github.com/flashinfer-ai/flashinfer.git --recursive /sgl-workspace/flashinfer-build/flashinfer; fi' && \
    cd /sgl-workspace/flashinfer-build/flashinfer && \
    git checkout v0.6.3 && \
    git config user.email "build@example.com" && \
    git config user.name "Build" && \
    git remote add nvjullin https://github.com/nvjullin/flashinfer 2>/dev/null || true && \
    git fetch nvjullin fix-fp4-quant-padding && \
    git cherry-pick ce48d4fb 10307340 && \
    cd flashinfer-jit-cache && \
    MAX_JOBS=32 FLASHINFER_NVCC_THREADS=2 FLASHINFER_CUDA_ARCH_LIST="10.0a 10.3a" python -m build --no-isolation --skip-dependency-check --wheel && \
    python -m pip install dist/*.whl