base-template-inferenz (sha256:28f2ab1a00172f0f521cb296833668df8a738d784930ea8bcd572f7fc0489cdf)
Published 2026-08-19 23:52:53 +02:00 by stefan
Installation
docker pull forgejo.zahl1.de/stefan/base-template-inferenz@sha256:28f2ab1a00172f0f521cb296833668df8a738d784930ea8bcd572f7fc0489cdfsha256:28f2ab1a00172f0f521cb296833668df8a738d784930ea8bcd572f7fc0489cdfAbout this package
LLM inference in C/C++
Image layers
| ARG RELEASE |
| ARG LAUNCHPAD_BUILD_ARCH |
| LABEL org.opencontainers.image.version=24.04 |
| ADD file:cb9335ce6f27399c2b17787739d6675502767c53e0335ded2a5f0d003d996650 in / |
| CMD ["/bin/bash"] |
| ARG BUILD_DATE=2026-08-19T04:53:31Z |
| ARG APP_VERSION=b10499 |
| ARG APP_REVISION=6d05498314db1b57f81c271080018aa2d0b89be9 |
| 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=2026-08-19T04:53:31Z org.opencontainers.image.version=b10499 org.opencontainers.image.revision=6d05498314db1b57f81c271080018aa2d0b89be9 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=2026-08-19T04:53:31Z APP_VERSION=b10499 APP_REVISION=6d05498314db1b57f81c271080018aa2d0b89be9 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 ffmpeg && 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 /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 --chown=10001:10001 /modelle /modelle # buildkit |
| RUN /bin/sh -c useradd --system --uid 10001 --create-home --home-dir /home/dienst dienst && mkdir -p /modelle-extra /etc/llama-swap && chown -R dienst:dienst /modelle-extra /etc/llama-swap # buildkit |
| COPY /usr/local/bin/llama-swap /usr/local/bin/llama-swap # buildkit |
| COPY --chown=10001:10001 config.yaml /etc/llama-swap/config.yaml # buildkit |
| USER dienst |
| EXPOSE [8000/tcp] |
| ENTRYPOINT ["/usr/local/bin/llama-swap" "--config" "/etc/llama-swap/config.yaml" "--listen" ":8000"] |
Labels
| Key | Value |
|---|---|
| org.opencontainers.image.created | 2026-08-19T04:53:31Z |
| org.opencontainers.image.description | LLM inference in C/C++ |
| org.opencontainers.image.revision | 6d05498314db1b57f81c271080018aa2d0b89be9 |
| 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 | b10499 |
Details
2026-08-19 23:52:53 +02:00
Versions (62)
View all
Container
1
OCI / Docker
linux/amd64
9.1 GiB