llama-server

Pull the image from the command line:

docker pull git.unme.me/night/llama-server@sha256:02bd7e7bf6e1ff9707cf9f8826b86399288c3801ad6d50db9c6d7e7a72ed4493

Digest

sha256:02bd7e7bf6e1ff9707cf9f8826b86399288c3801ad6d50db9c6d7e7a72ed4493

For more information on the Container registry, see the documentation.

ARG RELEASE

ARG LAUNCHPAD_BUILD_ARCH

LABEL org.opencontainers.image.ref.name=ubuntu

LABEL org.opencontainers.image.version=24.04

ADD file:bcebbf0fddcba5b864d5d267b68dd23bcfb01275e6ec7bcab69bf8b56af14804 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=12.8.57-1

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=12.8.0

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/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=12.8.0-1

ENV NV_NVTX_VERSION=12.8.55-1

ENV NV_LIBNPP_VERSION=12.3.3.65-1

ENV NV_LIBNPP_PACKAGE=libnpp-12-8=12.3.3.65-1

ENV NV_LIBCUSPARSE_VERSION=12.5.7.53-1

ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-8

ENV NV_LIBCUBLAS_VERSION=12.8.3.14-1

ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-8=12.8.3.14-1

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"]

RUN /bin/sh -c apt-get update && apt-get install -y --no-install-recommends libcurl4 libgomp1 && rm -rf /var/lib/apt/lists/* # buildkit

COPY /src/llama.cpp/build/bin/llama-server /usr/local/bin/ # buildkit

COPY /src/llama.cpp/build/bin/*.so /usr/local/lib/ # buildkit

ENV LD_LIBRARY_PATH=/usr/local/lib

EXPOSE [8080/tcp]

ENTRYPOINT ["/usr/local/bin/llama-server"]

Key	Value
maintainer	NVIDIA CORPORATION <cudatools@nvidia.com>
org.opencontainers.image.ref.name	ubuntu
org.opencontainers.image.version	24.04

llama-server (sha256:02bd7e7bf6e1ff9707cf9f8826b86399288c3801ad6d50db9c6d7e7a72ed4493)

Installation

Image layers

Labels