yorickr yorickr
  • Joined on 2025-08-12

inference-worker (9fbe6ec)

Published 2026-05-24 20:29:24 +00:00 by yorickr

Installation

docker pull git.yorickrommers.nl/yorickr/inference-worker:9fbe6ec
sha256:b15f049c5f2c39bfdbb5300fd7c3e1aa228b1b00a192db839a22211305d8b2af

Images

Digest OS / Arch Size
fd94b90b5e linux/amd64 2.5 GiB

Image Layers ( linux/amd64)

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"]
ARG BUILD_DATE=2026-05-23T05:30:41Z
ARG APP_VERSION=b9294
ARG APP_REVISION=0f3cb3fc8b4c22a89711457e84d8358a2f480832
ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp
ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp
LABEL org.opencontainers.image.created=2026-05-23T05:30:41Z org.opencontainers.image.version=b9294 org.opencontainers.image.revision=0f3cb3fc8b4c22a89711457e84d8358a2f480832 org.opencontainers.image.title=llama.cpp org.opencontainers.image.description=LLM inference in C/C++ org.opencontainers.image.url=https://github.com/ggml-org/llama.cpp org.opencontainers.image.source=https://github.com/ggml-org/llama.cpp
RUN |5 BUILD_DATE=2026-05-23T05:30:41Z APP_VERSION=b9294 APP_REVISION=0f3cb3fc8b4c22a89711457e84d8358a2f480832 IMAGE_URL=https://github.com/ggml-org/llama.cpp IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp /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 {Test:[CMD curl -f http://localhost:8080/health] Interval:0s Timeout:0s StartPeriod:0s StartInterval:0s Retries:0}
ENTRYPOINT ["/app/llama-server"]
COPY /uv /usr/local/bin/uv # buildkit
ENV PYTHONUNBUFFERED=1
WORKDIR /
RUN /bin/sh -c apt-get update --yes --quiet && DEBIAN_FRONTEND=noninteractive apt-get install --yes --quiet --no-install-recommends software-properties-common gpg-agent build-essential apt-utils && apt-get install --reinstall ca-certificates && add-apt-repository --yes ppa:deadsnakes/ppa && apt update --yes --quiet && DEBIAN_FRONTEND=noninteractive apt-get install --yes --quiet --no-install-recommends python3.11 python3.11-dev python3.11-distutils python3.11-lib2to3 python3.11-gdbm python3.11-tk bash && ln -s /usr/bin/python3.11 /usr/bin/python && apt-get clean && rm -rf /var/lib/apt/lists/* # buildkit
WORKDIR /work
ADD ./src /work # buildkit
RUN /bin/sh -c UV_SYSTEM_PYTHON=1 uv sync --frozen --no-dev && chmod +x /work/start.sh # buildkit
ENTRYPOINT ["/bin/sh" "-c" "/work/start.sh"]

Labels

Key Value
maintainer NVIDIA CORPORATION <cudatools@nvidia.com>
org.opencontainers.image.created 2026-05-23T05:30:41Z
org.opencontainers.image.description LLM inference in C/C++
org.opencontainers.image.ref.name ubuntu
org.opencontainers.image.revision 0f3cb3fc8b4c22a89711457e84d8358a2f480832
org.opencontainers.image.source https://github.com/ggml-org/llama.cpp
org.opencontainers.image.title llama.cpp
org.opencontainers.image.url https://github.com/ggml-org/llama.cpp
org.opencontainers.image.version b9294
Details
Container
2026-05-24 20:29:24 +00:00
6
OCI / Docker
Versions (10) View all
18ca6df 2026-05-25
latest 2026-05-25
b7eb0e1 2026-05-25
2a0d8b1 2026-05-25
206befd 2026-05-25