HyScale: Scaling Long-Context Training for Learned Sparse Attention
arXiv:2610.32057v1 Announce Type: new Abstract: 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...
Read more: https://arxiv.org/abs/2610.32057
Scan with your phone
Scan with your phone