Sign inSign up

matamagu/lmcache-vllm-openai:0.3.2-patched

Index digest

sha256:19c014533ed180ae1de68b2045c421c6ca3cbc9cf756dfb9a23a40e8944bf44f

OS/ARCH

linux/amd64

Compressed size

24.64 GB

Last pushed

11 months by matamagu

Type

Image

Manifest digest

sha256:a635b123c4a541796162b462ae2040902dcc57bd12102317def1e3dc2f7bd2e8

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 / 76.91 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 -c0 B
10RUN |1 JETPACK_HOST_MOUNTS= /bin/sh -c330.26 MB
11ARG GDRCOPY_VERSION=2.4.10 B
12ARG HPCX_VERSION=2.22.10 B
13ARG RDMACORE_VERSION=50.00 B
14ARG MOFED_VERSION=5.4-rdmacore50.00 B
15ARG OPENUCX_VERSION=1.18.00 B
16ARG OPENMPI_VERSION=4.1.70 B
17ARG EFA_VERSION=1.34.00 B
18ARG AWS_OFI_NCCL_VERSION=1.12.10 B
19ENV GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.1 MOFED_VERSION=5.4-rdmacore50.0 OPENUCX_VERSION=1.18.00 B
20ARG TARGETARCH=amd640 B
21RUN |10 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.1221.56 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=12.8.1.0120 B
25ARG CUDA_DRIVER_VERSION=570.124.060 B
26ENV CUDA_VERSION=12.8.1.012 CUDA_DRIVER_VERSION=570.124.06 CUDA_CACHE_DISABLE=10 B
27RUN |12 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.1773.43 MB
28RUN |12 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.170.5 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=2.25.10 B
32ARG CUBLAS_VERSION=12.8.4.10 B
33ARG CUFFT_VERSION=11.3.3.830 B
34ARG CURAND_VERSION=10.3.9.900 B
35ARG CUSPARSE_VERSION=12.5.8.930 B
36ARG CUSOLVER_VERSION=11.7.3.900 B
37ARG NPP_VERSION=12.3.3.1000 B
38ARG NVJPEG_VERSION=12.3.5.920 B
39ARG CUFILE_VERSION=1.13.1.30 B
40ARG NVJITLINK_VERSION=12.8.930 B
41ARG CUBLASMP_VERSION=0.4.0.7890 B
42ARG CAL_VERSION=0.4.4.500 B
43ARG NVSHMEM_VERSION=3.2.50 B
44ARG CUDNN_VERSION=9.8.0.870 B
45ARG CUDNN_FRONTEND_VERSION=1.10.00 B
46ARG TRT_VERSION=10.9.0.340 B
47ARG TRTOSS_VERSION=0 B
48ARG NSIGHT_SYSTEMS_VERSION=2025.1.1.1100 B
49ARG NSIGHT_COMPUTE_VERSION=2025.1.1.20 B
50ARG CUSPARSELT_VERSION=0.7.1.00 B
51ENV NCCL_VERSION=2.25.1 CUBLAS_VERSION=12.8.4.1 CUFFT_VERSION=11.3.3.83 CURAND_VERSION=10.3.9.900 B
52RUN |32 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.16.68 GB
53LABEL com.nvidia.nccl.version=2.25.1 com.nvidia.cublas.version=12.8.4.1 com.nvidia.cufft.version=11.3.3.83 com.nvidia.curand.version=10.3.9.900 B
54ARG DALI_VERSION=1.47.00 B
55ARG DALI_BUILD=0 B
56ARG DALI_URL_SUFFIX=1200 B
57ARG POLYGRAPHY_VERSION=0.49.180 B
58ARG TRANSFORMER_ENGINE_VERSION=2.10 B
59ARG MODEL_OPT_VERSION=0.25.00 B
60ENV DALI_VERSION=1.47.0 DALI_BUILD= DALI_URL_SUFFIX=120 POLYGRAPHY_VERSION=0.49.180 B
61ADD docs.tgz / # buildkit17 KB
62RUN |38 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.13 KB
63ARG _LIBPATH_SUFFIX=0 B
64ENV 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
65COPY entrypoint/ /opt/nvidia/ # buildkit26.5 KB
66ENV NVIDIA_PRODUCT_NAME=CUDA0 B
67ENTRYPOINT ["/opt/nvidia/nvidia_entrypoint.sh"]0 B
68RUN |39 JETPACK_HOST_MOUNTS= GDRCOPY_VERSION=2.4.1 HPCX_VERSION=2.22.12.5 KB
69RUN /bin/sh -c export DEBIAN_FRONTEND=noninteractive97.32 MB
70COPY cuda-*.patch /tmp # buildkit3.5 KB
71RUN /bin/sh -c export DEVEL=1939.56 MB
72ENV LIBRARY_PATH=/usr/local/cuda/lib64/stubs:0 B
73COPY /opt/amazon/aws-ofi-nccl /opt/amazon/aws-ofi-nccl # buildkit924 KB
74RUN /bin/sh -c if [45 KB
75ARG CUDA_VERSION=12.80 B
76ARG PYTHON_VERSION=3.120 B
77ARG UBUNTU_VERSION=24.040 B
78ENV DEBIAN_FRONTEND=noninteractive0 B
79RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.04301.65 MB
80WORKDIR /workspace0 B
81RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.0459.44 MB
82RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.040 B
83RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.040 B
84RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.040 B
85RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.0416.64 MB
86RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.040 B
87RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.040 B
88RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.044.21 MB
89RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.045.36 GB
90RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.043 KB
91RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.043 KB
92RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.0450 KB
93RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.044.99 GB
94COPY ./requirements/common.txt common.txt # buildkit2.5 KB
95COPY ./requirements/cuda.txt cuda.txt # buildkit2.5 KB
96RUN |3 CUDA_VERSION=12.8 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.042.63 GB
97ARG torch_cuda_arch_list=7.0 7.5 8.0 8.60 B
98ENV TORCH_CUDA_ARCH_LIST=7.0 7.5 8.0 8.60 B
99ARG vllm_fa_cmake_gpu_arches=80-real;90-real0 B
100ENV VLLM_FA_CMAKE_GPU_ARCHES=80-real;90-real0 B
101RUN |5 CUDA_VERSION=12.8.1.012 PYTHON_VERSION=3.12 UBUNTU_VERSION=24.041.97 GB
102WORKDIR /workspace0 B
103ENTRYPOINT ["/opt/venv/bin/vllm" "serve"]0 B
104mount / from exec sh265.08 MB

Command

 ARG RELEASE