RH-RunningHub / MiniMax-H3-MultiGPU-LightningView on GitHub
MiniMax-H3 multi-GPU inference acceleration: ~12x on 8x RTX 6000D (step distillation + SageAttention2 + Cache-DiT + torch.compile, TP2+Ulysses4 on sglang)
80Sep 10, 2026Updated this week

Alternatives and similar repositories for MiniMax-H3-MultiGPU-Lightning

Users that are interested in MiniMax-H3-MultiGPU-Lightning are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?