智东西China AI News(@Chinazhidx):Nunchux has deployed MiniMax-H3 on AMD MI355X. On 8 GPUs, inference is up to 26.7× faster than SGLang. ⚡️A 5-second clip takes 1.3 seconds. With streaming generation, you can even modify the prompt while the video is playing to guide the next frames.

智东西China AI News

@Chinazhidx

Zhidongxi is China's leading AI industry media outlet, providing news and insights on China's LLMs, robotics, AI agents, AI applications, and AI Hardware.

加入 February 2026

89 正在關注 2.6K 粉絲

智东西China AI News@Chinazhidx

2026.09.24 09:14

Nunchux has deployed MiniMax-H3 on AMD MI355X. On 8 GPUs, inference is up to 26.7× faster than SGLang. ⚡️A 5-second clip takes 1.3 seconds. With streaming generation, you can even modify the prompt while the video is playing to guide the next frames.