vLLM-Omni and MiniMax-H3-Image speed up image generation

vLLM-Omni generates 2048² images in 0.63s on 4×B300, while the open-sourced MiniMax-H3-Image now ships an official vLLM Docker image and hits 0.88s on 4×H200.

2026-11-10 ~ 2026-11-10 · 2 related posts