Back to appsSubmit
vLLM

vLLM

Official

Docker app from m0ngr31's Repository

Overview

Easy, fast, and cheap LLM serving for everyone

Requirements

Nvidia Driver plugin (nVidia Support)

Runtime arguments

Web UI
http://[IP]:[PORT:8000]/
Shell
sh
Privileged
false
Extra Params
--runtime=nvidia --ipc=host

Template configuration

NVIDIA_VISIBLE_DEVICESVariable
Default
all
Value
all
NVIDIA_DRIVER_CAPABILITIESVariable
Default
all
Value
all
Model StoragePathrw
Target
/root/.cache/huggingface
Default
/mnt/user/appdata/vllm
Value
/mnt/user/appdata/vllm
PortPorttcp
Target
8000
Default
8000
Value
8000
Hugging Face TokenVariable
Target
HUGGING_FACE_HUB_TOKEN

Categories

AI

Download Statistics

20,528,997
Total Downloads
2,939,323
This Month
2,242,947
Avg / Month

Total Downloads Over Time

Loading chart...

Links

TemplateSupportDocker HubProject

Details

Repository
vllm/vllm-openai
Registry
https://hub.docker.com/r/vllm/vllm-openai
Last Updated2026-05-11
First Seen2024-11-15

Run vLLM on Unraid.

vLLM is listed in Community Apps for Unraid OS. Explore Unraid to build a flexible home server, NAS, or homelab.

Explore Unraid OS