Sign inSign up

peakji92/vllm-openai:v0.6.5

Index digest

sha256:47ff6d976098f1a6de17a0ee4bbd9f814c805f2858e81e67b016e0d604b167c5

OS/ARCH

linux/amd64

Compressed size

5.09 GB

Last pushed

almost 2 years by peakji92

Type

Image

Manifest digest

sha256:6fbbae59dd74de84654d59a082b6bf3f15b0aea898893d0b4953e8cb9306926e

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 / 28.17 MB
6CMD ["/bin/bash"]0 B
7ENV NVARCH=x86_640 B
8ENV NVIDIA_REQUIRE_CUDA=cuda>=12.1 brand=tesla,driver>=470,driver<471 brand=unknown,driver>=470,driver<471 brand=nvidia,driver>=470,driver<4710 B
9ENV NV_CUDA_CUDART_VERSION=12.1.55-10 B
10ENV NV_CUDA_COMPAT_PACKAGE=cuda-compat-12-10 B
11ARG TARGETARCH0 B
12LABEL maintainer=NVIDIA CORPORATION <[email protected]>0 B
13RUN |1 TARGETARCH=amd64 /bin/sh -c4.41 MB
14ENV CUDA_VERSION=12.1.00 B
15RUN |1 TARGETARCH=amd64 /bin/sh -c53.15 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
26ARG TARGETPLATFORM0 B
27COPY requirements-cuda-arm64.txt requirements-cuda-arm64.txt # buildkit271 B
28RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64229 B
29RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd64406.96 MB
30RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd6411.11 KB
31RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd643.27 GB
32RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd6432 B
33RUN |3 CUDA_VERSION=12.1.0 PYTHON_VERSION=3.12 TARGETPLATFORM=linux/amd641.25 GB
34COPY examples examples # buildkit73.1 KB
35RUN /bin/sh -c if [87.56 MB
36ENV VLLM_USAGE_SOURCE=production-docker-image0 B
37ENTRYPOINT ["python3" "-m" "vllm.entrypoints.openai.api_server"]0 B
38COPY docker-entrypoint.sh docker-entrypoint.sh # buildkit1.52 KB
39RUN /bin/sh -c chmod u+x1.52 KB
40EXPOSE map[80/tcp:{}]0 B
41ENV VLLM_NO_USAGE_STATS=10 B
42ENV VLLM_DO_NOT_TRACK=10 B
43ENV VLLM_LOGGING_LEVEL=WARNING0 B
44ENV VLLM_NO_DEPRECATION_WARNING=10 B
45ENV HOST=0.0.0.00 B
46ENV PORT=800 B
47ENV UVICORN_LOG_LEVEL=warning0 B
48ENV MODEL=peakji/qwen2.5-1.5b-instruct-trim0 B
49ENV TASK=0 B
50ENV REVISION=0 B
51ENV TRUST_REMOTE_CODE=0 B
52ENV LOAD_FORMAT=0 B
53ENV DTYPE=0 B
54ENV DOWNLOAD_DIR=0 B
55ENV KV_CACHE_DTYPE=0 B
56ENV MAX_MODEL_LEN=0 B
57ENV PIPELINE_PARALLEL_SIZE=0 B
58ENV TENSOR_PARALLEL_SIZE=0 B
59ENV MAX_PARALLEL_LOADING_WORKERS=0 B
60ENV BLOCK_SIZE=0 B
61ENV ENABLE_PREFIX_CACHING=0 B
62ENV DISABLE_SLIDING_WINDOW=0 B
63ENV SEED=0 B
64ENV SWAP_SPACE=0 B
65ENV CPU_OFFLOAD_GB=0 B
66ENV GPU_MEMORY_UTILIZATION=0 B
67ENV MAX_NUM_BATCHED_TOKENS=0 B
68ENV MAX_NUM_SEQS=0 B
69ENV MAX_LOGPROBS=0 B
70ENV DISABLE_LOG_STATS=true0 B
71ENV QUANTIZATION=0 B
72ENV MAX_SEQ_LEN_TO_CAPTURE=0 B
73ENV LIMIT_MM_PER_PROMPT=0 B
74ENV NUM_SCHEDULER_STEPS=0 B
75ENV SCHEDULER_DELAY_FACTOR=0 B
76ENV ENABLE_CHUNKED_PREFILL=0 B
77ENV SPECULATIVE_MODEL=0 B
78ENV SPECULATIVE_MODEL_QUANTIZATION=0 B
79ENV NUM_SPECULATIVE_TOKENS=0 B
80ENV SPECULATIVE_DRAFT_TENSOR_PARALLEL_SIZE=0 B
81ENV SPECULATIVE_MAX_MODEL_LEN=0 B
82ENV SPECULATIVE_DISABLE_BY_BATCH_SIZE=0 B
83ENV NGRAM_PROMPT_LOOKUP_MAX=0 B
84ENV NGRAM_PROMPT_LOOKUP_MIN=0 B
85ENV SPEC_DECODING_ACCEPTANCE_METHOD=0 B
86ENV TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_THRESHOLD=0 B
87ENV TYPICAL_ACCEPTANCE_SAMPLER_POSTERIOR_ALPHA=0 B
88ENV SERVED_MODEL_NAME=0 B
89ENV DISABLE_LOG_REQUESTS=true0 B
90ENTRYPOINT ["./docker-entrypoint.sh"]0 B

Command

 ARG RELEASE