Nunchux 将 MiniMax 的 MiniMax-H3 部署到 AMD MI355X，在 8 块 GPU 上推理速度最高达 SGLang 的 26.7 倍，5 秒视频仅需 1.3 秒生成。借助流式生成，用户可在视频播放过程中修改提示词来引导后续画面。MiniMax-H3 免费访问即将开放，现已开放 waitlist。
More ways to build with MiniMax-H3. 🐮
Great to see model optimization and AMD inference engineering come together to give creators a faster feedback loop.⚡️
在 X 查看被引用的帖子5s of video, generated in 1.3s!
Nunchux brings @MiniMax’s MiniMax-H3 to @AMD MI355X with up to 26.7× faster inference than SGLang on 8 GPUs @AMDServer
And with streaming generation, you can change the prompt as the video plays, steering what happens next.
One stack, optimized across hardware.Free access to MiniMax-H3 is coming soon! Join the waitlist now at nunchux.ai.
Our blog: nunchux.ai/blog/video-generat…
#AI #VideoGeneration #MiniMaxH3
来源：MiniMax (official) · x.com