HyScale2 min read
HyScale: Scaling Long-Context Training for Learned Sparse Attention
We present HyScale, a long-context training system for learned sparse attention. Learned sparse attention is a promising architecture for million-token contexts, widely adopted in production since DeepSeek-V3.2. Selection, however, grows into the training bottleneck.
By Yangshen Deng, Xinjing Huang, Yulong Wang, Yunzhuo Liu, Jun Hu, Shuyong Tan, Chun-Chih Tseng, Mingji Han, Ray Ying, Key Zhang, Luo MaiarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Oct 27, 2026.
Comments
Sign in to join the discussion.