llm-cuda-service (latest)

Published 2025-01-20 10:53:29 +01:00 by nathanlq

Installation

docker pull git.spacesheep.ovh/nathanlq/llm-cuda-service:latest
sha256:5d544f9733f3f5c3e2d2ec9e0c48c63e491c2deeb3bf2ec05d8cfab85928d64c

Image Layers

ARG RELEASE
ARG LAUNCHPAD_BUILD_ARCH
LABEL org.opencontainers.image.ref.name=ubuntu
LABEL org.opencontainers.image.version=22.04
ADD file:21c2e8d95909bec6f4acdaf4aed55b44ee13603681f93b152e423e3e6a4a207b in /
CMD ["/bin/bash"]
ENV NVARCH=x86_64
ENV NVIDIA_REQUIRE_CUDA=cuda>=12.4 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<471 brand=nvidiartx,driver>=470,driver<471 brand=geforce,driver>=470,driver<471 brand=geforcertx,driver>=470,driver<471 brand=quadro,driver>=470,driver<471 brand=quadrortx,driver>=470,driver<471 brand=titan,driver>=470,driver<471 brand=titanrtx,driver>=470,driver<471 brand=tesla,driver>=525,driver<526 brand=unknown,driver>=525,driver<526 brand=nvidia,driver>=525,driver<526 brand=nvidiartx,driver>=525,driver<526 brand=geforce,driver>=525,driver<526 brand=geforcertx,driver>=525,driver<526 brand=quadro,driver>=525,driver<526 brand=quadrortx,driver>=525,driver<526 brand=titan,driver>=525,driver<526 brand=titanrtx,driver>=525,driver<526 brand=tesla,driver>=535,driver<536 brand=unknown,driver>=535,driver<536 brand=nvidia,driver>=535,driver<536 brand=nvidiartx,driver>=535,driver<536 brand=geforce,driver>=535,driver<536 brand=geforcertx,driver>=535,driver<536 brand=quadro,driver>=535,driver<536 brand=quadrortx,driver>=535,driver<536 brand=titan,driver>=535,driver<536 brand=titanrtx,driver>=535,driver<536
ENV NV_CUDA_CUDART_VERSION=12.4.99-1
ENV NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-4
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 -fsSLO https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/${NVARCH}/cuda-keyring_1.1-1_all.deb && dpkg -i cuda-keyring_1.1-1_all.deb && apt-get purge --autoremove -y curl && rm -rf /var/lib/apt/lists/* # buildkit
ENV CUDA_VERSION=12.4.0
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-cudart-12-4=${NV_CUDA_CUDART_VERSION} ${NV_CUDA_COMPAT_PACKAGE} && rm -rf /var/lib/apt/lists/* # buildkit
RUN |1 TARGETARCH=amd64 /bin/sh -c echo "/usr/local/nvidia/lib" >> /etc/ld.so.conf.d/nvidia.conf && echo "/usr/local/nvidia/lib64" >> /etc/ld.so.conf.d/nvidia.conf # buildkit
ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64
COPY NGC-DL-CONTAINER-LICENSE / # buildkit
ENV NVIDIA_VISIBLE_DEVICES=all
ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility
ENV NV_CUDA_LIB_VERSION=12.4.0-1
ENV NV_NVTX_VERSION=12.4.99-1
ENV NV_LIBNPP_VERSION=12.2.5.2-1
ENV NV_LIBNPP_PACKAGE=libnpp-12-4=12.2.5.2-1
ENV NV_LIBCUSPARSE_VERSION=12.3.0.142-1
ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-4
ENV NV_LIBCUBLAS_VERSION=12.4.2.65-1
ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-4=12.4.2.65-1
ENV NV_LIBNCCL_PACKAGE_NAME=libnccl2
ENV NV_LIBNCCL_PACKAGE_VERSION=2.20.5-1
ENV NCCL_VERSION=2.20.5-1
ENV NV_LIBNCCL_PACKAGE=libnccl2=2.20.5-1+cuda12.4
ARG TARGETARCH
LABEL maintainer=NVIDIA CORPORATION <cudatools@nvidia.com>
RUN |1 TARGETARCH=amd64 /bin/sh -c apt-get update && apt-get install -y --no-install-recommends cuda-libraries-12-4=${NV_CUDA_LIB_VERSION} ${NV_LIBNPP_PACKAGE} cuda-nvtx-12-4=${NV_NVTX_VERSION} libcusparse-12-4=${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"]
WORKDIR /app
RUN /bin/sh -c apt-get update && apt-get install -y curl git && apt-get install -y python3.11 python3.11-venv python3.11-dev python3-pip && rm -rf /var/lib/apt/lists/* # buildkit
RUN /bin/sh -c update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.11 1 && update-alternatives --set python3 /usr/bin/python3.11 && curl -sS https://bootstrap.pypa.io/get-pip.py | python3.11 # buildkit
RUN /bin/sh -c python3 --version # buildkit
COPY requirements.txt . # buildkit
RUN /bin/sh -c pip3 install --no-cache-dir --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124 -r requirements.txt # buildkit
COPY . . # buildkit
EXPOSE map[8000/tcp:{}]
HEALTHCHECK &{["CMD-SHELL" "curl --fail http://localhost:8000/health || exit 1"] "0s" "0s" "0s" "0s" '\x00'}
CMD ["uvicorn" "api:app" "--host" "0.0.0.0" "--port" "8000"]

Labels

Key Value
maintainer NVIDIA CORPORATION <cudatools@nvidia.com>
org.opencontainers.image.ref.name ubuntu
org.opencontainers.image.version 22.04
Details
Container
2025-01-20 10:53:29 +01:00
0
OCI / Docker
linux/amd64
1.6 GiB
Versions (1) View all
latest 2025-01-20