llama-swap (latest)

Published 2025-05-22 20:50:45 -04:00 by simcop2387

Installation

docker pull gitea.simcop2387.info/simcop2387/llama-swap:latest
sha256:72c3fe17e9f3e47ccedc54a4a590705c64529f2ab2a287c0dab4c998b5263d1c

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} ${NV_LIBNCCL_PACKAGE_NAME} # buildkit
COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit
COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit
ENV NVIDIA_PRODUCT_NAME=CUDA
ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]
RUN /bin/sh -c apt-get update && apt-get install -y libgomp1 curl && apt autoremove -y && apt clean -y && rm -rf /tmp/* /var/tmp/* && find /var/cache/apt/archives /var/lib/apt/lists -not -name lock -type f -delete && find /var/cache -type f -delete # buildkit
COPY /app/lib/ /app # buildkit
ENV LLAMA_ARG_HOST=0.0.0.0
COPY /app/full/llama-server /app # buildkit
WORKDIR /app
HEALTHCHECK &{["CMD" "curl" "-f" "http://localhost:8080/health"] "0s" "0s" "0s" "0s" '\x00'}
ENTRYPOINT ["/app/llama-server"]
ARG LS_VER=121
WORKDIR /app
RUN |1 LS_VER=121 /bin/sh -c curl -LO https://github.com/mostlygeek/llama-swap/releases/download/v"${LS_VER}"/llama-swap_"${LS_VER}"_linux_amd64.tar.gz && tar -zxf llama-swap_"${LS_VER}"_linux_amd64.tar.gz && rm llama-swap_"${LS_VER}"_linux_amd64.tar.gz # buildkit
COPY config.example.yaml /app/config.yaml # buildkit
HEALTHCHECK &{["CMD-SHELL" "curl -f http://localhost:8080/ || exit 1"] "0s" "0s" "0s" "0s" '\x00'}
ENTRYPOINT ["/app/llama-swap" "-config" "/app/config.yaml"]
RUN /bin/sh -c apt update && apt full-upgrade -y && apt install curl && curl -fsSL https://get.docker.com | sh # buildkit

Labels

Key Value
com.docker.compose.project llama-swap
com.docker.compose.service llama-swap
com.docker.compose.version 2.35.1
maintainer NVIDIA CORPORATION <cudatools@nvidia.com>
org.opencontainers.image.ref.name ubuntu
org.opencontainers.image.version 22.04
Details
Container
2025-05-22 20:50:45 -04:00
1
OCI / Docker
linux/amd64
2.1 GiB
Versions (2) View all
latest 2025-05-22
latesst 2025-05-21