vllm-project /
vllm-omni
A framework for efficient model inference with omni-modality models
Updated 50 min ago
Why now
Version v0.32.0 came out on October 28.
+120 stars gained this week
Stars gained each day, last 30 days
Usual pace · 15 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
vLLM-Omni is a framework for serving omni-modality models that generate text, audio, image, and video. It is aimed at teams who need efficient, scalable inference for these models.
Summary written by AI from the repository’s description and README.
vllm-project / vllm-omni
View on GitHub(opens in new tab)