Sign inSign up

velaraptor1/qwen3-32b-awg-vllm-worker:public-ep

Index digest

sha256:70f897def7e9e3ce9b59093034514b25caac8e7003d0c7172cd37eb6ced4c494

OS/ARCH

linux/amd64

Compressed size

41.76 GB

Last pushed

about 1 year by velaraptor1

Type

Image

Manifest digest

sha256:cc44fe83867965603b18ea59d23b6e8eca0aa75d0cc9d3229cc9af8af7efcc15

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
22RUN /bin/sh -c apt-get update166.22 MB
23RUN /bin/sh -c ldconfig /usr/local/cuda-12.1/compat/4.4 KB
24COPY builder/requirements.txt /requirements.txt # buildkit223 B
25RUN /bin/sh -c python3 -m3.11 GB
26RUN /bin/sh -c python3 -m6.51 GB
27ARG MODEL_NAME=0 B
28ARG TOKENIZER_NAME=0 B
29ARG BASE_PATH=/runpod-volume0 B
30ARG QUANTIZATION=0 B
31ARG MODEL_REVISION=0 B
32ARG TOKENIZER_REVISION=0 B
33ENV MODEL_NAME= MODEL_REVISION= TOKENIZER_NAME= TOKENIZER_REVISION=0 B
34ENV PYTHONPATH=/:/vllm-workspace0 B
35COPY src /src # buildkit9.18 KB
36RUN |6 MODEL_NAME= TOKENIZER_NAME= BASE_PATH=/runpod-volume32 B
37CMD ["python3" "/src/handler.py"]0 B
38ARG MODEL_NAME=Qwen/Qwen3-32B-AWQ0 B
39ARG TOKENIZER_NAME=0 B
40ARG BASE_PATH=/models0 B
41ARG QUANTIZATION=0 B
42ARG MODEL_REVISION=0 B
43ARG TOKENIZER_REVISION=0 B
44ENV MODEL_NAME=Qwen/Qwen3-32B-AWQ MODEL_REVISION= TOKENIZER_NAME= TOKENIZER_REVISION=0 B
45COPY requirements.txt /src/requirements_2.txt # buildkit160 B
46RUN |6 MODEL_NAME=Qwen/Qwen3-32B-AWQ TOKENIZER_NAME= BASE_PATH=/models37.2 KB
47COPY utils.py /src/utils.py # buildkit3.11 KB
48COPY models/ /models/huggingface-cache/hub/ # buildkit31.89 GB
49RUN |6 MODEL_NAME=Qwen/Qwen3-32B-AWQ TOKENIZER_NAME= BASE_PATH=/models32 B
50COPY handler.py /src/handler.py # buildkit645 B
51CMD ["python3" "/src/handler.py"]0 B

Command

 ARG RELEASE