SOURCE-LINKED INTELLIGENCE

ECHO: Early-layer Collaborative Hierarchical Orchestration with Bonus Logits in Speculative Decoding

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

While draft-model-free speculative decoding offers a promising path to efficient LLM inference, it is frequently constrained by stale draft candidates and the high computational cost of the verification. To address these challenges, we propose ECHO, a hierarchical dual-loop framework that exploits the functional asymmetry between LLM layers. Leveraging the high discriminative efficiency of early layers and the authoritative distribution of final layers, ECHO bifurcates inference into a high-frequency inner loop and a low-frequency outer loop. Within the inner loop, early-layer bonus logits dri

Read original source ↗ Open in workspace

recordType

paper

region

Global