chengzeyi/ParaAttention

https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching

1 best points · 1 comments · 1 Hacker News post · 436 GitHub stars · View on GitHub

Hacker News discussions

• ParaAttention: Speed Up Flux and Mochi Inference with Multiple GPUs (1 points, 1 comments, by chengzeyi, 2024-11-13)