Speculative decoding

PicoSpec

A Pipelined Collaborative Speculative Decoding Framework for Efficient Edge-Cloud LLM Inference

On the frontierfirst seen Mar 19, 2026

Current frontier — recent, not yet superseded in the knowledge base

0 papers critique it · 0 beat it on benchmarks

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.