Sign inSign up

peakji92/vllm-openai:v0.5.4

Index digest

sha256:6f476e5baf2f609fc346aad099f24c81b9faf12d05ada61bd73c19d8bb80c33e

OS/ARCH

linux/amd64

Compressed size

5.1 GB

Last pushed

about 2 years by peakji92

Type

Image

Manifest digest

sha256:43fc0f3cf00847d5bf2dc8a839b0c6c0eac50dc1db558560387ca420cf1b2be8

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=3.100 B
24WORKDIR /vllm-workspace104 B
25RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.10 /bin/sh107 MB
26RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.10 /bin/sh108.46 MB
27RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.10 /bin/sh4.81 MB
28RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.10 /bin/sh32 B
29RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.10 /bin/sh6.74 KB
30RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.10 /bin/sh3.15 GB
31RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.10 /bin/sh413.71 MB
32RUN |2 CUDA_VERSION=12.4.1 PYTHON_VERSION=3.10 /bin/sh1.23 GB
33RUN /bin/sh -c pip install14.4 MB
34ENV VLLM_USAGE_SOURCE=production-docker-image0 B
35ENTRYPOINT ["python3" "-m" "vllm.entrypoints.openai.api_server"]0 B
36COPY docker-entrypoint.sh docker-entrypoint.sh # buildkit1.41 KB
37RUN /bin/sh -c chmod u+x1.41 KB
38EXPOSE map[80/tcp:{}]0 B
39ENV VLLM_NO_USAGE_STATS=10 B
40ENV VLLM_DO_NOT_TRACK=10 B
41ENV VLLM_LOGGING_LEVEL=WARNING0 B
42ENV VLLM_NO_DEPRECATION_WARNING=10 B
43ENV HOST=0.0.0.00 B
44ENV PORT=800 B
45ENV UVICORN_LOG_LEVEL=warning0 B
46ENV MODEL=Qwen/Qwen2-1.5B-Instruct0 B
47ENV REVISION=0 B
48ENV TRUST_REMOTE_CODE=0 B
49ENV DTYPE=0 B
50ENV KV_CACHE_DTYPE=0 B
51ENV MAX_MODEL_LEN=0 B
52ENV PIPELINE_PARALLEL_SIZE=0 B
53ENV TENSOR_PARALLEL_SIZE=0 B
54ENV MAX_PARALLEL_LOADING_WORKERS=0 B
55ENV BLOCK_SIZE=0 B
56ENV ENABLE_PREFIX_CACHING=0 B
57ENV DISABLE_SLIDING_WINDOW=0 B
58ENV USE_V2_BLOCK_MANAGER=0 B
59ENV SEED=0 B
60ENV SWAP_SPACE=0 B
61ENV CPU_OFFLOAD_GB=0 B
62ENV GPU_MEMORY_UTILIZATION=0 B
63ENV MAX_NUM_BATCHED_TOKENS=0 B
64ENV MAX_NUM_SEQS=0 B
65ENV MAX_LOGPROBS=0 B
66ENV DISABLE_LOG_STATS=true0 B
67ENV QUANTIZATION=0 B
68ENV MAX_SEQ_LEN_TO_CAPTURE=0 B
69ENV ENABLE_CHUNKED_PREFILL=0 B
70ENV SPECULATIVE_MODEL=0 B
71ENV NUM_SPECULATIVE_TOKENS=0 B
72ENV SPECULATIVE_DRAFT_TENSOR_PARALLEL_SIZE=0 B
73ENV SPECULATIVE_MAX_MODEL_LEN=0 B
74ENV SPECULATIVE_DISABLE_BY_BATCH_SIZE=0 B
75ENV NGRAM_PROMPT_LOOKUP_MAX=0 B
76ENV NGRAM_PROMPT_LOOKUP_MIN=0 B
77ENV SPEC_DECODING_ACCEPTANCE_METHOD=0 B
78ENV TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_THRESHOLD=0 B
79ENV TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_ALPHA=0 B
80ENV SERVED_MODEL_NAME=0 B
81ENV DISABLE_LOG_REQUESTS=true0 B
82ENTRYPOINT ["./docker-entrypoint.sh"]0 B

Command

 ARG RELEASE