SOURCE-LINKED INTELLIGENCE

GDN Tree-Scan: Served Tree Verification for Recurrent-Hybrid Language Models

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Tree speculative decoding verifies multiple candidate continuations in one target forward pass. For attention-only transformers, the verifier mainly needs an ancestry mask. Recurrent-hybrid language models break this assumption: a candidate row must also carry the recurrent state that native sequential decode would have produced along its root-to-node path. Otherwise, a verifier can use a correct attention mask while still conditioning on an impossible recurrent history. We present GDN Tree-Scan, a served verifier for Gated-DeltaNet hybrid language models integrated into vLLM. The system combi

Read original source ↗ Open in workspace

recordType

paper

region

Global