Sign inSign up

sirensolutions/llamacpp-tunneled-runpod:v9

Index digest

sha256:ee23e9816476395eddfb521c269b87edce609e8d3947dd409ba34ad9e11ebaa0

OS/ARCH

linux/amd64

Compressed size

2.46 GB

Last pushed

7 days by almico

Type

Image

Manifest digest

sha256:42a3ec2ad712b010c84a734d9b0b0455fe7e2acd3bfee8b3614755664b0e812c

Image Layers

Image Layers

1ARG RELEASE0 B
2ARG LAUNCHPAD_BUILD_ARCH0 B
3LABEL org.opencontainers.image.ref.name=ubuntu0 B
4LABEL org.opencontainers.image.version=24.040 B
5ADD file ... in / 28.38 MB
6CMD ["/bin/bash"]0 B
7ENV NVARCH=x86_640 B
8ENV NVIDIA_REQUIRE_CUDA=cuda>=12.8 brand=unknown,driver>=470,driver<471 brand=grid,driver>=470,driver<471 brand=tesla,driver>=470,driver<4710 B
9ENV NV_CUDA_CUDART_VERSION=12.8.90-10 B
10ARG TARGETARCH0 B
11LABEL maintainer=NVIDIA CORPORATION <[email protected]>0 B
12RUN |1 TARGETARCH=amd64 /bin/sh -c6.63 MB
13ENV CUDA_VERSION=12.8.10 B
14RUN |1 TARGETARCH=amd64 /bin/sh -c61.31 MB
15RUN |1 TARGETARCH=amd64 /bin/sh -c183 B
16ENV PATH=/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin0 B
17ENV LD_LIBRARY_PATH=/usr/local/cuda/lib640 B
18COPY NGC-DL-CONTAINER-LICENSE / # buildkit6.72 KB
19ENV NVIDIA_VISIBLE_DEVICES=all0 B
20ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility0 B
21ENV NV_CUDA_LIB_VERSION=12.8.1-10 B
22ENV NV_NVTX_VERSION=12.8.90-10 B
23ENV NV_LIBNPP_VERSION=12.3.3.100-10 B
24ENV NV_LIBNPP_PACKAGE=libnpp-12-8=12.3.3.100-10 B
25ENV NV_LIBCUSPARSE_VERSION=12.5.8.93-10 B
26ENV NV_LIBCUBLAS_PACKAGE_NAME=libcublas-12-80 B
27ENV NV_LIBCUBLAS_VERSION=12.8.4.1-10 B
28ENV NV_LIBCUBLAS_PACKAGE=libcublas-12-8=12.8.4.1-10 B
29ENV NV_LIBNCCL_PACKAGE_NAME=libnccl20 B
30ENV NV_LIBNCCL_PACKAGE_VERSION=2.25.1-10 B
31ENV NCCL_VERSION=2.25.1-10 B
32ENV NV_LIBNCCL_PACKAGE=libnccl2=2.25.1-1+cuda12.80 B
33ARG TARGETARCH0 B
34LABEL maintainer=NVIDIA CORPORATION <[email protected]>0 B
35RUN |1 TARGETARCH=amd64 /bin/sh -c1.92 GB
36RUN |1 TARGETARCH=amd64 /bin/sh -c58.22 KB
37COPY entrypoint.d/ /opt/nvidia/entrypoint.d/ # buildkit1.64 KB
38COPY nvidia_entrypoint.sh /opt/nvidia/ # buildkit1.49 KB
39ENV NVIDIA_PRODUCT_NAME=CUDA0 B
40ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]0 B
41ARG BUILD_DATE=2026-10-16T04:36:01Z0 B
42ARG APP_VERSION=b116810 B
43ARG APP_REVISION=5e03a1ff450cae37a774684de55d14fb48b1f90b0 B
44ARG IMAGE_URL=https://github.com/ggml-org/llama.cpp0 B
45ARG IMAGE_SOURCE=https://github.com/ggml-org/llama.cpp0 B
46LABEL org.opencontainers.image.created=2026-10-16T04:36:01Z org.opencontainers.image.version=b11681 org.opencontainers.image.revision=5e03a1ff450cae37a774684de55d14fb48b1f90b org.opencontainers.image.title=llama.cpp0 B
47RUN |5 BUILD_DATE=2026-10-16T04:36:01Z APP_VERSION=b11681 APP_REVISION=5e03a1ff450cae37a774684de55d14fb48b1f90b249.81 MB
48COPY /app/lib/ /app # buildkit164.34 MB
49ENV LLAMA_ARG_HOST=0.0.0.00 B
50ENV LLAMA_ARG_PORT=80800 B
51COPY /app/full/llama /app/full/llama-server /app/ #24.47 KB
52WORKDIR /app32 B
53HEALTHCHECK {Test:[CMD curl -f http://localhost:8080/health]0 B
54ENTRYPOINT ["/app/llama-server"]0 B
55RUN /bin/sh -c apt-get update12.78 MB
56RUN /bin/sh -c curl -1sLf17.67 MB
57COPY pod_exporter.py /opt/pod_exporter.py # buildkit3.4 KB
58COPY download_models.py /opt/download_models.py # buildkit5.75 KB
59COPY models.ini /opt/models.ini # buildkit246 B
60RUN /bin/sh -c mkdir -p32 B
61COPY Caddyfile /etc/caddy/Caddyfile # buildkit296 B
62RUN /bin/sh -c python3 -m13.51 MB
63COPY start.sh /usr/local/bin/start.sh # buildkit2.54 KB
64RUN /bin/sh -c chmod +x2.54 KB
65ENV PATH=/app:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin0 B
66ENV LD_LIBRARY_PATH=/app:/usr/local/cuda/lib640 B
67WORKDIR /workspace99 B
68ENTRYPOINT ["/usr/local/bin/start.sh"]0 B

Command

 ARG RELEASE