NOTE: We've renamed the APIs from Start()/StartV2() to Schedule() and from WaitForComplete()/WaitForCompleteV2() to Wait() while adding support for generic unique ...
💪 FP8 compatibility ! 🚀 Speed Up all Process 🚀 less VRAM consumption (Stay high, batch_size=1 for RTX4090 max, I'm trying to fix that) 🛠️ Better benchmark coming soon ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results