Back to Tools Directory

vllm-omni

Python

A framework for efficient model inference with omni-modality models

Categories & Topics

audio-generationdiffusionimage-generationinferencemodel-servingmultimodalpytorchtransformervideo-generationworld-model
Visit WebsiteView on GitHub

Repository Stats

5.9k
GitHub Stars
1.4k
Forks
5.9k
Watchers
1430
Open Issues
License
Apache License 2.0
Repository
vllm-project/vllm-omni
Last Updated
Today
August 7, 2026
Latest Release
v0.26.0
4 days ago
Top Contributors
tzhouam
113
yenuo26
102
hsliuustc0106
99
david6666666
94
linyueqian
89
gcanlin
82
princepride
66
amy-why-3459
60
View all contributors →

Related Tools

ATOM

151

AiTer Optimized Model

colibri

23k

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

Comfyui-zhenzhen

702

https://ai.t8star.org/register?aff=dP7j Comfyui的各种平价API调用节点,支持seedance2.0(满血版,支持真人,不排队)

dflash

5.6k

DFlash: Block Diffusion for Flash Speculative Decoding

gpt_image_playground

3.3k

基于 OpenAI gpt-image-2 API 的图片生成与编辑工具

guizang-ppt-skill

23k

AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts, social covers, and a WebGL/low-power presentation runtime.