Sign inSign up

aveshasystems/lmcache-vllm-arm:v1.0.0

Manifest digest

sha256:6d3aa1fc53abb1e1bea3c1b7c3f03685f6cbd2752374b2e30ab695c9d6eae102

OS/ARCH

linux/arm64

Compressed size

7.79 GB

Last pushed

9 months by aveshadev

Type

Image

Manifest digest

sha256:6d3aa1fc53abb1e1bea3c1b7c3f03685f6cbd2752374b2e30ab695c9d6eae102

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=22.040 B
5ADD file ... in / 27.08 MB
6CMD ["/bin/bash"]0 B
7ENV NVARCH=sbsa0 B
8ENV NVIDIA_REQUIRE_CUDA=cuda>=12.9 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<5360 B
9ENV NV_CUDA_CUDART_VERSION=12.9.79-10 B
10ARG TARGETARCH0 B
11LABEL maintainer=NVIDIA CORPORATION <[email protected]>0 B
12RUN |1 TARGETARCH=arm64 /bin/sh -c4.38 MB
13ENV CUDA_VERSION=12.9.10 B
14RUN |1 TARGETARCH=arm64 /bin/sh -c93.07 MB
15RUN |1 TARGETARCH=arm64 /bin/sh -c182 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
21ARG CUDA_VERSION0 B
22ARG PYTHON_VERSION0 B
23ARG INSTALL_KV_CONNECTORS=false0 B
24WORKDIR /vllm-workspace104 B
25ENV DEBIAN_FRONTEND=noninteractive0 B
26ARG TARGETPLATFORM0 B
27ARG GDRCOPY_CUDA_VERSION=12.80 B
28ARG GDRCOPY_OS_VERSION=Ubuntu22_040 B
29SHELL [/bin/bash -c]0 B
30ARG DEADSNAKES_MIRROR_URL0 B
31ARG DEADSNAKES_GPGKEY_URL0 B
32ARG GET_PIP_URL0 B
33RUN |9 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true231 B
34RUN |9 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true204.18 MB
35RUN |9 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true1.24 GB
36ARG PIP_INDEX_URL UV_INDEX_URL0 B
37ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL0 B
38ARG PYTORCH_CUDA_INDEX_BASE_URL0 B
39ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER0 B
40RUN |16 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true40.4 MB
41ENV UV_HTTP_TIMEOUT=5000 B
42ENV UV_INDEX_STRATEGY=unsafe-best-match0 B
43ENV UV_LINK_MODE=copy0 B
44RUN |16 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true10.82 KB
45RUN |16 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true4.48 GB
46RUN |16 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true1.19 GB
47COPY examples examples # buildkit189.28 KB
48COPY benchmarks benchmarks # buildkit165.17 KB
49COPY ./vllm/collect_env.py . # buildkit8.2 KB
50RUN |16 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true122 B
51RUN |16 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true7.44 MB
52ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/cuda/lib640 B
53RUN |16 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true89.64 MB
54RUN |16 CUDA_VERSION=12.9.1 PYTHON_VERSION=3.12 INSTALL_KV_CONNECTORS=true521.59 KB
55ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/cuda/lib640 B
56ARG TARGETPLATFORM0 B
57ARG INSTALL_KV_CONNECTORS=false0 B
58ARG PIP_INDEX_URL UV_INDEX_URL0 B
59ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL0 B
60ENV UV_HTTP_TIMEOUT=5000 B
61RUN |6 TARGETPLATFORM=linux/arm64 INSTALL_KV_CONNECTORS=true PIP_INDEX_URL=340.61 MB
62ENV VLLM_USAGE_SOURCE=production-docker-image0 B
63ENTRYPOINT ["vllm" "serve"]0 B
64COPY /build/wheels /tmp/lmcache_wheels # buildkit3.71 MB
65RUN /bin/bash -c pip install90.46 MB
66ENTRYPOINT ["python3" "-m" "vllm.entrypoints.openai.api_server"]0 B

Command

 ARG RELEASE