| ARG RELEASE |
| ARG LAUNCHPAD_BUILD_ARCH |
| LABEL org.opencontainers.image.ref.name=ubuntu |
| LABEL org.opencontainers.image.version=24.04 |
| ADD file:6df775300d76441aa33f31b22c1afce8dfe35c8ffbc14ef27c27009235b12a95 in / |
| CMD ["/bin/bash"] |
| ENV NVARCH=x86_64 |
| ENV NVIDIA_REQUIRE_CUDA=cuda>=12.8 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=vapps,driver>=470,driver<471 brand=vpc,driver>=470,driver<471 brand=vcs,driver>=470,driver<471 brand=vws,driver>=470,driver<471 brand=cloudgaming,driver>=470,driver<471 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=vapps,driver>=535,driver<536 brand=vpc,driver>=535,driver<536 brand=vcs,driver>=535,driver<536 brand=vws,driver>=535,driver<536 brand=cloudgaming,driver>=535,driver<536 brand=unknown,driver>=550,driver<551 brand=grid,driver>=550,driver<551 brand=tesla,driver>=550,driver<551 brand=nvidia,driver>=550,driver<551 brand=quadro,driver>=550,driver<551 brand=quadrortx,driver>=550,driver<551 brand=nvidiartx,driver>=550,driver<551 brand=vapps,driver>=550,driver<551 brand=vpc,driver>=550,driver<551 brand=vcs,driver>=550,driver<551 brand=vws,driver>=550,driver<551 brand=cloudgaming,driver>=550,driver<551 brand=unknown,driver>=560,driver<561 brand=grid,driver>=560,driver<561 brand=tesla,driver>=560,driver<561 brand=nvidia,driver>=560,driver<561 brand=quadro,driver>=560,driver<561 brand=quadrortx,driver>=560,driver<561 brand=nvidiartx,driver>=560,driver<561 brand=vapps,driver>=560,driver<561 brand=vpc,driver>=560,driver<561 brand=vcs,driver>=560,driver<561 brand=vws,driver>=560,driver<561 brand=cloudgaming,driver>=560,driver<561 brand=unknown,driver>=565,driver<566 brand=grid,driver>=565,driver<566 brand=tesla,driver>=565,driver<566 brand=nvidia,driver>=565,driver<566 brand=quadro,driver>=565,driver<566 brand=quadrortx,driver>=565,driver<566 brand=nvidiartx,driver>=565,driver<566 brand=vapps,driver>=565,driver<566 brand=vpc,driver>=565,driver<566 brand=vcs,driver>=565,driver<566 brand=vws,driver>=565,driver<566 brand=cloudgaming,driver>=565,driver<566 |
| ENV NV_CUDA_CUDART_VERSION=12.8.90-1 |
| ARG TARGETARCH |
| LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com> |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends gnupg2 curl ca-certificates && curl -fsSL https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH}/3bf863cc.pub | apt-key add - && echo "deb https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2404/${NVARCH} /" > /etc/apt/sources.list.d/cuda.list && apt-get purge --autoremove -y curl && rm -rf /var/lib/apt/lists/* # buildkit |
| ENV CUDA_VERSION=12.8.1 |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-12-8=${NV_CUDA_CUDART_VERSION} cuda-compat-12-8 && rm -rf /var/lib/apt/lists/* # buildkit |
| RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit |
| ENV PATH=/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin |
| ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64 |
| COPY NGC-DL-CONTAINER-LICENSE / # buildkit |
| ENV NVIDIA_VISIBLE_DEVICES=all |
| ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility |
| ENV NV_CUDA_LIB_VERSION=12.8.1-1 |
| ENV NV_NVTX_VERSION=12.8.90-1 |
| ENV NV_LIBNPP_VERSION=12.3.3.100-1 |
| ENV NV_LIBNPP_PACKAGE=libnpp-12-8=12.3.3.100-1 |
| ENV NV_LIBCUSPARSE_VERSION=12.5.8.93-1 |
| ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-8 |
| ENV NV_LIBCUBLAS_VERSION=12.8.4.1-1 |
| ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-8=12.8.4.1-1 |
| ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2 |
| ENV NV_LIBNCCL_PACKAGE_VERSION=2.25.1-1 |
| ENV NCCL_VERSION=2.25.1-1 |
| ENV NV_LIBNCCL_PACKAGE=libnccl2=2.25.1-1+cuda12.8 |
| ARG TARGETARCH |
| LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com> |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-libraries-12-8=${NV_CUDA_LIB_VERSION} ${NV_LIBNPP_PACKAGE} cuda-nvtx-12-8=${NV_NVTX_VERSION} libcusparse-12-8=${NV_LIBCUSPARSE_VERSION} ${NV_LIBCUBLAS_PACKAGE} ${NV_LIBNCCL_PACKAGE} && rm -rf /var/lib/apt/lists/* # buildkit |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-mark hold ${NV_LIBCUBLAS_PACKAGE_NAME} ${NV_LIBNCCL_PACKAGE_NAME} # buildkit |
| COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit |
| COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit |
| ENV NVIDIA_PRODUCT_NAME=CUDA |
| ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"] |
| ENV NV_CUDNN_VERSION=9.8.0.87-1 |
| ENV NV_CUDNN_PACKAGE_NAME=libcudnn9-cuda-12 |
| ENV NV_CUDNN_PACKAGE=libcudnn9-cuda-12=9.8.0.87-1 |
| ARG TARGETARCH |
| LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com> |
| LABEL com.nvidia.cudnn.version=9.8.0.87-1 |
| RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends ${NV_CUDNN_PACKAGE} && apt-mark hold ${NV_CUDNN_PACKAGE_NAME} && rm -rf /var/lib/apt/lists/* # buildkit |
| ENV DEBIAN_FRONTEND=noninteractive |
| ENV TORCH_DEVICE=cuda |
| ENV HF_HOME=/data/huggingface |
| ENV PYTHONUNBUFFERED=1 |
| RUN /bin/sh -c apt-get update && apt-get install -y --no-install-recommends python3 python3-venv curl && rm -rf /var/lib/apt/lists/* # buildkit |
| RUN /bin/sh -c python3 -m venv /opt/venv # buildkit |
| ENV PATH=/opt/venv/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin |
| RUN /bin/sh -c pip install --upgrade pip # buildkit |
| RUN /bin/sh -c pip install "numpy>=2.0.0,<2.5" "scikit-learn>=1.5.0" # buildkit |
| RUN /bin/sh -c pip install torch torchvision --index-url https://download.pytorch.org/whl/cu128 # buildkit |
| RUN /bin/sh -c pip install "marker-pdf[full]" uvicorn fastapi python-multipart # buildkit |
| RUN /bin/sh -c python3 -c "import marker.services.openai as m; print(m.__file__)" > /tmp/marker_openai_path && MARKER_OPENAI_PATH=$(cat /tmp/marker_openai_path) && sed -i 's/response_text = response\.choices\[0\]\.message\.content/response_text = response.choices[0].message.content or getattr(response.choices[0].message, "reasoning_content", "") or ""/' "$MARKER_OPENAI_PATH" && grep -q 'reasoning_content' "$MARKER_OPENAI_PATH" && rm /tmp/marker_openai_path # buildkit |
| RUN /bin/sh -c python3 -c "import marker.processors.llm.llm_page_correction as m; print(m.__file__)" > /tmp/marker_pagecorrection_path && MARKER_PAGECORRECTION_PATH=$(cat /tmp/marker_pagecorrection_path) && sed -i 's|page_id, _, _ = block_data\["id"\]\.split("/")|_, page_id, _, _ = block_data["id"].strip().lstrip("/").split("/")|' "$MARKER_PAGECORRECTION_PATH" && sed -i 's|page_id, block_type, block_id = block_data\["id"\]\.split("/")|_, page_id, block_type, block_id = block_data["id"].strip().lstrip("/").split("/")|' "$MARKER_PAGECORRECTION_PATH" && grep -q 'lstrip("/").split("/")' "$MARKER_PAGECORRECTION_PATH" && python3 -c "import ast; ast.parse(open('$MARKER_PAGECORRECTION_PATH').read())" && rm /tmp/marker_pagecorrection_path # buildkit |
| RUN /bin/sh -c apt-get update && apt-get install -y --no-install-recommends git cmake build-essential cuda-nvcc-12-8 cuda-cudart-dev-12-8=12.8.90-1 libcublas-dev-12-8=12.8.4.1-1 && rm -rf /var/lib/apt/lists/* && git clone --depth 1 https://github.com/ggml-org/llama.cpp.git /tmp/llama.cpp && ln -sf /usr/local/cuda-12.8/lib64/stubs/libcuda.so /usr/local/cuda-12.8/lib64/libcuda.so && ln -sf /usr/local/cuda-12.8/lib64/stubs/libcuda.so /usr/local/cuda-12.8/lib64/libcuda.so.1 && cmake -B /tmp/llama.cpp/build -S /tmp/llama.cpp -DGGML_CUDA=ON -DCMAKE_CUDA_ARCHITECTURES="86;89" -DCMAKE_CUDA_COMPILER=/usr/local/cuda-12.8/bin/nvcc -DLLAMA_CURL=OFF -DCMAKE_BUILD_TYPE=Release && cmake --build /tmp/llama.cpp/build --target llama-server -j"$(nproc)" # buildkit |
| RUN /bin/sh -c apt-get update && apt-get install -y --no-install-recommends libgomp1 && rm -rf /var/lib/apt/lists/* && mkdir -p /usr/local/lib/llama.cpp && cp /tmp/llama.cpp/build/bin/llama-server /usr/local/bin/llama-server && cp /tmp/llama.cpp/build/bin/*.so /usr/local/lib/llama.cpp/ && echo "/usr/local/lib/llama.cpp" > /etc/ld.so.conf.d/llama-cpp.conf && ldconfig && rm -rf /tmp/llama.cpp && apt-get purge -y git cmake build-essential cuda-nvcc-12-8 cuda-cudart-dev-12-8 libcublas-dev-12-8 && apt-get autoremove -y && rm -rf /var/lib/apt/lists/* # buildkit |
| ENV SURYA_INFERENCE_BACKEND=llamacpp |
| ENV LLAMA_CPP_BINARY=/usr/local/bin/llama-server |
| WORKDIR /app |
| COPY server.py /app/server.py # buildkit |
| VOLUME [/data/huggingface] |
| EXPOSE [8001/tcp] |
| HEALTHCHECK {Test:[CMD-SHELL curl -f http://localhost:8001/health || exit 1] Interval:30s Timeout:10s StartPeriod:3m0s StartInterval:0s Retries:5} |
| CMD ["uvicorn" "server:app" "--host" "0.0.0.0" "--port" "8001" "--workers" "1"] |
