Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding 事件

Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding arXiv:2606.01019v1 Announce Type: new Abstract: Large Language Model (LLM) generation remains expensive because autoregressive decoding calls the model once for each new token. Speculative decoding reduces this cost by drafting multiple tokens and verifying them with the target model in one step, but its speedup depends on how many drafted tokens are accepted. Parameter-free draft sources can propose long contin