MiMo-V2.5-Pro-UltraSpeed: Pushing 1T-Parameter Model Generation Speed to 1000 Tokens/s
MiMo, in collaboration with TileRT, releases the UltraSpeed mode of Xiaomi MiMo-V2.5-Pro — breaking 1000 tokens/s generation speed on a 1T-parameter model for the first time on commodity GPUs through extreme model-system codesign.