- 谁
- vLLM
- 时间
- 引文
We’re bringing NVIDIA Vera Rubin support H3-image to vLLM-Omni, and native 4K generation in 0.87 seconds!⚡️
发生了什么
vLLM 表示，vLLM-Omni 将支持在 NVIDIA Vera Rubin 上运行 MiniMax H3-Image，并可在 0.87 秒内原生生成 4K 图像。该帖子还祝贺 MiniMax 的 H3-Image 在 Artificial Analysis 的开放权重图像编辑模型中排名第一。
接下来读什么
查看这件事的完整进展vLLM-Omni Adds GPU Support for MiniMax H3-ImageCongrats to @MiniMax_AI on H3-Image taking the #1 spot among open-weight models for image editing by Artificial Analysis! 🎉
We’re bringing NVIDIA Vera Rubin support H3-image to vLLM-Omni, and native 4K generation in 0.87 seconds!⚡️
Check it out!👇
vllm.ai/blog/2026-11-12-minim…
这件事到目前为止
vLLM-Omni supports MiniMax-H3-Image on NVIDIA and AMD GPUs from day one, and vLLM says it is adding NVIDIA Vera Rubin support with native 4K generation in 0.87 seconds. The original release recipe supports multi-reference editing with up to nine images per request. vLLM also described the open-weight model as supporting image generation and editing, native images of about 16 megapixels, 4,096-token prompts, and dense text rendering. Its latest post congratulated MiniMax on H3-Image taking the top spot among open-weight image editing models in Artificial Analysis.