Skip to content
Research

TreeWY: Speculative Verification for Gated DeltaNet Hybrids.

arXiv:2608.20961v2 Announce Type: replace Abstract: Modern open models are hybrids: most layers are linear-attention (Gated DeltaNet, GDN) layers carrying a small fixed-size recurrent state instead of a growing key-value (KV) cache. This makes ordinary decodin

arXiv cs.AIResearch source·