Sign inSign up

peakji92/vllm-openai:v0.6.2

Index digest

sha256:1ed56730b8c6adbc359c922cf86ca6c5a8c5edc08b30e98b185480f0f664211e

OS/ARCH

linux/amd64

Compressed size

4.99 GB

Last pushed

almost 2 years by peakji92

Type

Image

Manifest digest

sha256:0df7d8afe9479be3be9865c6a06cc56c3059308a22d0ed97a29d0f98df54bef7

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=20.040 B
5ADD file ... in / 26.24 MB
6CMD ["/bin/bash"]0 B
7ENV NVARCH=x86_640 B
8ENV NVIDIA_REQUIRE_CUDA=cuda>=12.4 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<4710 B
9ENV NV_CUDA_CUDART_VERSION=12.4.127-10 B
10ENV NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-40 B
11ARG TARGETARCH0 B
12LABEL maintainer=NVIDIA CORPORATION <[email protected]>0 B
13RUN |1 TARGETARCH=amd64 /bin/sh -c7.58 MB
14ENV CUDA_VERSION=12.4.10 B
15RUN |1 TARGETARCH=amd64 /bin/sh -c54.93 MB
16RUN |1 TARGETARCH=amd64 /bin/sh -c185 B
17ENV PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin0 B
18ENV LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib640 B
19COPY NGC-DL-CONTAINER-LICENSE / # buildkit6.72 KB
20ENV NVIDIA_VISIBLE_DEVICES=all0 B
21ENV NVIDIA_DRIVER_CAPABILITIES=compute,utility0 B
22ARG CUDA_VERSION=12.4.10 B
23ARG PYTHON_VERSION=3.120 B
24WORKDIR /vllm-workspace104 B
25ENV DEBIAN_FRONTEND=noninteractive0 B
26RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.12 /bin/sh229 B
27RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.12 /bin/sh344.95 MB
28RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.12 /bin/sh12.33 KB
29RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.12 /bin/sh3.19 GB
30RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.12 /bin/sh1.25 GB
31RUN /bin/sh -c pip install138.27 MB
32ENV VLLM_USAGE_SOURCE=production-docker-image0 B
33ENTRYPOINT ["python3" "-m" "vllm.entrypoints.openai.api_server"]0 B
34COPY docker-entrypoint.sh docker-entrypoint.sh # buildkit1.47 KB
35RUN /bin/sh -c chmod u+x1.47 KB
36EXPOSE map[80/tcp:{}]0 B
37ENV VLLM_NO_USAGE_STATS=10 B
38ENV VLLM_DO_NOT_TRACK=10 B
39ENV VLLM_LOGGING_LEVEL=WARNING0 B
40ENV VLLM_NO_DEPRECATION_WARNING=10 B
41ENV HOST=0.0.0.00 B
42ENV PORT=800 B
43ENV UVICORN_LOG_LEVEL=warning0 B
44ENV MODEL=Qwen/Qwen2-1.5B-Instruct0 B
45ENV REVISION=0 B
46ENV TRUST_REMOTE_CODE=0 B
47ENV DTYPE=0 B
48ENV KV_CACHE_DTYPE=0 B
49ENV MAX_MODEL_LEN=0 B
50ENV PIPELINE_PARALLEL_SIZE=0 B
51ENV TENSOR_PARALLEL_SIZE=0 B
52ENV MAX_PARALLEL_LOADING_WORKERS=0 B
53ENV BLOCK_SIZE=0 B
54ENV ENABLE_PREFIX_CACHING=0 B
55ENV DISABLE_SLIDING_WINDOW=0 B
56ENV USE_V2_BLOCK_MANAGER=0 B
57ENV SEED=0 B
58ENV SWAP_SPACE=0 B
59ENV CPU_OFFLOAD_GB=0 B
60ENV GPU_MEMORY_UTILIZATION=0 B
61ENV MAX_NUM_BATCHED_TOKENS=0 B
62ENV MAX_NUM_SEQS=0 B
63ENV MAX_LOGPROBS=0 B
64ENV DISABLE_LOG_STATS=true0 B
65ENV QUANTIZATION=0 B
66ENV MAX_SEQ_LEN_TO_CAPTURE=0 B
67ENV NUM_SCHEDULER_STEPS=0 B
68ENV SCHEDULER_DELAY_FACTOR=0 B
69ENV ENABLE_CHUNKED_PREFILL=0 B
70ENV SPECULATIVE_MODEL=0 B
71ENV SPECULATIVE_MODEL_QUANTIZATION=0 B
72ENV NUM_SPECULATIVE_TOKENS=0 B
73ENV SPECULATIVE_DRAFT_TENSOR_PARALLEL_SIZE=0 B
74ENV SPECULATIVE_MAX_MODEL_LEN=0 B
75ENV SPECULATIVE_DISABLE_BY_BATCH_SIZE=0 B
76ENV NGRAM_PROMPT_LOOKUP_MAX=0 B
77ENV NGRAM_PROMPT_LOOKUP_MIN=0 B
78ENV SPEC_DECODING_ACCEPTANCE_METHOD=0 B
79ENV TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_THRESHOLD=0 B
80ENV TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_ALPHA=0 B
81ENV SERVED_MODEL_NAME=0 B
82ENV DISABLE_LOG_REQUESTS=true0 B
83ENTRYPOINT ["./docker-entrypoint.sh"]0 B

Command

 ARG RELEASE