Sign inSign up

cledge/vllm-openai:fastapi-instrumentation

Manifest digest

sha256:dc837d91bc17ec7350d89241f6599e77de4990a2a5524d334cbca7b734c1ad6b

OS/ARCH

linux/amd64

Compressed size

8.08 GB

Last pushed

2 months by cledge

Type

Image

Manifest digest

sha256:dc837d91bc17ec7350d89241f6599e77de4990a2a5524d334cbca7b734c1ad6b

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 / 29.04 MB
6CMD ["/bin/bash"]0 B
7ENV NVARCH=x86_640 B
8ENV NVIDIA_REQUIRE_CUDA=cuda>=13.0 brand=unknown,driver>=535,driver<536 brand=grid,driver>=535,driver<536 brand=tesla,driver>=535,driver<5360 B
9ENV NV_CUDA_CUDART_VERSION=13.0.96-10 B
10ARG TARGETARCH0 B
11LABEL maintainer=NVIDIA CORPORATION <[email protected]>0 B
12RUN |1 TARGETARCH=amd64 /bin/sh -c4.43 MB
13ENV CUDA_VERSION=13.0.20 B
14RUN |1 TARGETARCH=amd64 /bin/sh -c100.3 MB
15RUN |1 TARGETARCH=amd64 /bin/sh -c185 B
16ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin0 B
17ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/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 DEADSNAKES_MIRROR_URL0 B
24ARG DEADSNAKES_GPGKEY_URL0 B
25ARG GET_PIP_URL0 B
26ENV DEBIAN_FRONTEND=noninteractive0 B
27WORKDIR /vllm-workspace104 B
28RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=230 B
29RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=214.04 MB
30RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=1.61 GB
31RUN |5 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=47.63 MB
32ENV UV_HTTP_TIMEOUT=5000 B
33ENV UV_INDEX_STRATEGY=unsafe-best-match0 B
34ENV UV_LINK_MODE=copy0 B
35ENV VLLM_ENABLE_CUDA_COMPATIBILITY=00 B
36ARG PYTORCH_CUDA_INDEX_BASE_URL0 B
37COPY requirements/common.txt /tmp/common.txt # buildkit1.52 KB
38COPY requirements/cuda.txt /tmp/requirements-cuda.txt # buildkit659 B
39RUN |6 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=3.31 GB
40ARG FLASHINFER_VERSION=0.6.8.post10 B
41RUN |7 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=1.94 GB
42ARG GDRCOPY_CUDA_VERSION=12.80 B
43ARG GDRCOPY_OS_VERSION=Ubuntu22_040 B
44ARG TARGETPLATFORM0 B
45COPY tools/install_gdrcopy.sh /tmp/install_gdrcopy.sh # buildkit896 B
46RUN |10 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=524.71 KB
47ARG BITSANDBYTES_VERSION_X86=0.46.10 B
48ARG BITSANDBYTES_VERSION_ARM64=0.42.00 B
49ARG TIMM_VERSION=>=1.0.170 B
50ARG RUNAI_MODEL_STREAMER_VERSION=>=0.15.70 B
51RUN |14 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=115.47 MB
52ARG PIP_INDEX_URL UV_INDEX_URL0 B
53ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL0 B
54ARG PYTORCH_CUDA_INDEX_BASE_URL0 B
55ARG PIP_KEYRING_PROVIDER UV_KEYRING_PROVIDER0 B
56ARG PYTORCH_NIGHTLY0 B
57COPY /workspace/torch_lib_versions.txt torch_lib_versions.txt # buildkit198 B
58RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=232.09 MB
59RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=122 B
60ENV LD_LIBRARY_PATH=/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib640 B
61RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=11.04 MB
62RUN |22 CUDA_VERSION=13.0.2 PYTHON_VERSION=3.12 DEADSNAKES_MIRROR_URL=286.26 MB
63ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib64:/usr/local/cuda/lib64:/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib640 B
64COPY examples examples # buildkit248.95 KB
65COPY benchmarks benchmarks # buildkit226.17 KB
66COPY ./vllm/collect_env.py . # buildkit9.62 KB
67ARG TARGETPLATFORM0 B
68ARG INSTALL_KV_CONNECTORS=false0 B
69ARG CUDA_VERSION0 B
70ARG VLLM_BUILD_COMMIT0 B
71ARG VLLM_BUILD_PIPELINE0 B
72ARG VLLM_BUILD_URL0 B
73ARG VLLM_IMAGE_TAG0 B
74ARG PIP_INDEX_URL UV_INDEX_URL0 B
75ARG PIP_EXTRA_INDEX_URL UV_EXTRA_INDEX_URL0 B
76ENV UV_HTTP_TIMEOUT=5000 B
77ARG torch_cuda_arch_list=7.5 8.0 8.6 8.90 B
78ENV TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.90 B
79RUN |12 TARGETPLATFORM=linux/amd64 INSTALL_KV_CONNECTORS=true CUDA_VERSION=13.0.2208.69 MB
80ENV VLLM_USAGE_SOURCE=production-docker-image0 B
81ENV VLLM_BUILD_COMMIT=ad7125a431e176d4161099480a66f0169609a690 VLLM_BUILD_PIPELINE=019d130e-464e-4ff7-b84b-492992c0c06b VLLM_BUILD_URL=https://buildkite.com/vllm/release-v2/builds/1649 VLLM_IMAGE_TAG=vllm/vllm-openai:v0.21.00 B
82LABEL org.opencontainers.image.source=https://github.com/vllm-project/vllm org.opencontainers.image.revision=ad7125a431e176d4161099480a66f0169609a690 org.opencontainers.image.version=vllm/vllm-openai:v0.21.0 org.opencontainers.image.url=https://buildkite.com/vllm/release-v2/builds/16490 B
83ENTRYPOINT ["vllm" "serve"]0 B
84RUN /bin/sh -c pip install1.98 MB

Command

 ARG RELEASE