dhi.io/vllm-openai

vLLM OpenAI 0.32.x (dev)

CIS

linux/amd64

debian 13

Tags:

0-debian-dev, 0-debian13-dev, 0-dev, 0.32-debian-dev, 0.32-debian13-dev, 0.32-dev, 0.32.0-debian-dev, 0.32.0-debian13-dev, 0.32.0-dev

Index digest:

sha256:0844100476312c6f1c508820c5e829faf7c0474b87b0decb9ddac0e1aaeb00b9

Manifest digest:

sha256:8dc4c2abd356bcfd9e2a32baf6125c532f4ba3f0144ded213f28e6a8565c3ce8

ARCH

Size

4.45 GB

Last pushed

1 day ago

Vulnerabilities

192

Support

Active

Packages (1093)Specifications Vulnerabilities (275)Attestations

Source & Build Information

Dockerfile link

https://github.com/docker-hardened-images/definitions/blob/ccab9f35c03e8f5dfb8ad1c3482be397f7f0ac61/.build/image/vllm-openai/debian-13/0.32-dev.yaml

Git commit

https://github.com/docker-hardened-images/definitions/commit/ccab9f35c03e8f5dfb8ad1c3482be397f7f0ac61

Dockerfile

# syntax=dhi/build:2-debian13

# DO NOT EDIT THIS FILE MANUALLY
# generated with 'dhi def merge image/vllm-openai/debian-13/0.32-dev.yaml'

name: vLLM OpenAI 0.32.x (dev)
image: dhi/vllm-openai
variant: dev
tags:
    - 0-dev
    - 0.32-dev
    - 0.32.0-dev
    - 0-debian-dev
    - 0-debian13-dev
    - 0.32-debian-dev

Build parameters

Entrypoint

/usr/bin/vllm

serve

CMD

User

Working directory

/home/nonroot

Environment variables

CUDA_VERSION=13.0.3
DEBIAN_FRONTEND=noninteractive
HF_HOME=/home/nonroot/.cache/huggingface
LD_LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
LIBRARY_PATH=/usr/local/nvidia/lib:/usr/local/nvidia/lib64:/usr/local/cuda/lib64
NUMBA_CACHE_DIR=/home/nonroot/.cache/numba
NVIDIA_DRIVER_CAPABILITIES=compute,utility
NVIDIA_PRODUCT_NAME=CUDA
NVIDIA_REQUIRE_CUDA=cuda>=13.0
NVIDIA_VISIBLE_DEVICES=all
PATH=/usr/local/nvidia/bin:/usr/local/cuda/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
REQUESTS_CA_BUNDLE=/etc/ssl/certs/ca-certificates.crt
SSL_CERT_FILE=/etc/ssl/certs/ca-certificates.crt
TMPDIR=/tmp
TORCH_CUDA_ARCH_LIST=7.5 8.0 8.6 8.9 9.0 10.0 11.0 12.0
TRITON_CACHE_DIR=/home/nonroot/.cache/triton
VLLM_CACHE_ROOT=/home/nonroot/.cache/vllm
VLLM_ENABLE_CUDA_COMPATIBILITY=0
VLLM_TARGET_DEVICE=cuda
VLLM_USAGE_SOURCE=production-docker-image
XDG_CACHE_HOME=/home/nonroot/.cache

Ports

8000/tcp

Labels

com.docker.dhi.chain-id

sha256:1f386e23c57d9273fbc4aea8f1acc9b9298a68e8b82f351d419069678eda0c7d

com.docker.dhi.compliance

cis

com.docker.dhi.created

2026-10-31T04:27:50Z

com.docker.dhi.date.release

2026-10-18

com.docker.dhi.definition

image/vllm-openai/debian-13/0.32-dev

com.docker.dhi.distro

debian-13

com.docker.dhi.entitlement

public

com.docker.dhi.flavor

com.docker.dhi.name

dhi/vllm-openai

com.docker.dhi.package-manager

apt

com.docker.dhi.shell

bash

com.docker.dhi.title

vLLM OpenAI 0.32.x (dev)

com.docker.dhi.url

https://dhi.io/catalog/vllm-openai

com.docker.dhi.variant

dev

com.docker.dhi.version

0.32.0-debian13-dev