Sign inSign up

lmcache/vllm-openai:nightly-2026-08-22-cu129

Manifest digest

sha256:3775d88814efe2878da9d003cc6d0748b884f44f9d6f8350abdd2281bc46d53d

OS/ARCH

linux/amd64

Compressed size

11.36 GB

Last pushed

26 days by lmcache

Type

Image

Manifest digest

sha256:3775d88814efe2878da9d003cc6d0748b884f44f9d6f8350abdd2281bc46d53d

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 / 28.34 MB
6CMD ["/bin/bash"]0 B
7ARG JETPACK_HOST_MOUNTS=0 B
8ENV NVIDIA_REQUIRE_JETPACK_HOST_MOUNTS=0 B
9RUN |1 JETPACK_HOST_MOUNTS= /bin/sh -c32 B
10RUN |1 JETPACK_HOST_MOUNTS= /bin/sh -c3.65 MB
11ARG GDRCOPY_VERSION=2.4.40 B
12ARG HPCX_VERSION=2.230 B
13ARG RDMACORE_VERSION=50.00 B
14ARG MOFED_VERSION=5.4-rdmacore50.00 B
15ARG OPENUCX_VERSION=1.19.00 B
16ARG OPENMPI_VERSION=4.1.70 B
17ARG EFA_VERSION=1.38.10 B
18ARG AWS_OFI_NCCL_VERSION=1.14.00 B
19ENV GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.23 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.19.00 B
20ARG TARGETARCH=amd640 B
21RUN |10 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.2385.71 MB
22ENV OPAL_PREFIX=/opt/hpcx/ompi PATH=/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin0 B
23ENV OMPI_MCA_coll_hcoll_enable=00 B
24ARG CUDA_VERSION=12.9.0.0430 B
25ARG CUDA_DRIVER_VERSION=575.51.030 B
26ENV CUDA_VERSION=12.9.0.043 CUDA_DRIVER_VERSION=575.51.030 B
27RUN |12 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.2384.38 MB
28RUN |12 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.2316.5 KB
29ENV _CUDA_COMPAT_PATH=/usr/local/cuda/compat ENV=/etc/shinit_v2 BASH_ENV=/etc/bash.bashrc SHELL=/bin/bash0 B
30LABEL com.nvidia.volumes.needed=nvidia_driver com.nvidia.cuda.version=9.00 B
31ARG NCCL_VERSION=2.26.5 CUBLAS_VERSION=12.9.0.13 CUFFT_VERSION=11.4.0.6 CURAND_VERSION=10.3.10.190 B
32ENV NCCL_VERSION=2.26.5 CUBLAS_VERSION=12.9.0.13 CUFFT_VERSION=11.4.0.6 CURAND_VERSION=10.3.10.190 B
33ADD docs.tgz / # buildkit11.26 KB
34RUN |39 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.23179 B
35ARG _LIBPATH_SUFFIX=0 B
36ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin LD_LIBRARY_PATH=/usr/local/cuda/compat/lib:/usr/local/nvidia/lib:/usr/local/nvidia/lib64 NVIDIA_VISIBLE_DEVICES=all NVIDIA_DRIVER_CAPABILITIES=compute,utility,video0 B
37COPY /opt/amazon/aws-ofi-nccl /opt/amazon/aws-ofi-nccl # buildkit1.65 MB
38RUN |40 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.235.3 KB
39COPY entrypoint/ /opt/nvidia/ # buildkit6.22 KB
40ENV NVIDIA_PRODUCT_NAME=CUDA0 B
41ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]0 B
42RUN |40 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.4 HPCX_VERSION=2.23406 B
43RUN /bin/sh -c export DEBIAN_FRONTEND=noninteractive101.45 MB
44RUN /bin/sh -c /nvidia/build-scripts/installCUDA.sh #206.23 MB
45RUN /bin/sh -c /nvidia/build-scripts/installLIBS.sh 4.91 GB
46LABEL com.nvidia.nccl.version=2.26.5 com.nvidia.cublas.version=12.9.0.13 com.nvidia.cufft.version=11.4.0.6 com.nvidia.curand.version=10.3.10.190 B
47RUN /bin/sh -c export DEBIAN_FRONTEND=noninteractive34.3 MB
48COPY cuda-*.patch /tmp # buildkit502 B
49RUN /bin/sh -c export DEVEL=1338.36 MB
50ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs:0 B
51ARG CUDA_VERSION=12.90 B
52ARG PYTHON_VERSION=3.120 B
53ARG UBUNTU_VERSION=24.040 B
54ENV DEBIAN_FRONTEND=noninteractive0 B
55ENV PATH=/opt/venv/bin:/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/mpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/ucx/bin:/opt/amazon/efa/bin0 B
56RUN |3 CUDA_VERSION=12.9 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.04133.39 MB
57WORKDIR /workspace32 B
58ARG torch_cuda_arch_list=7.5 8.0 8.6 8.90 B
59ENV TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.90 B
60COPY ./requirements/build.txt build.txt # buildkit370 B
61ARG max_jobs=20 B
62ENV MAX_JOBS=20 B
63ARG nvcc_threads=80 B
64ENV NVCC_THREADS=80 B
65ARG CUDA_VERSION=12.90 B
66ARG VLLM_VERSION=nightly0 B
67RUN |7 CUDA_VERSION=12.9 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.041.57 MB
68ARG LMCACHE_COMMIT_ID=10 B
69COPY . /workspace/LMCache # buildkit74.72 MB
70WORKDIR /workspace/LMCache32 B
71RUN |8 CUDA_VERSION=12.9 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.045.38 GB
72WORKDIR /workspace32 B
73ENTRYPOINT ["/opt/venv/bin/vllm" "serve"]0 B

Command

 ARG RELEASE