The Draft Race
Animated simulation of autoregressive vs speculative decoding. Adjust acceptance rate α and draft depth K to see how speedup changes — and what happens when a draft node defects.
⬢ loading artifact…
Appears in
The Biased Draft: Speculative Decoding's Trust Gap in Decentralized Inference
Speculative decoding accelerates LLM inference 2–4× by splitting work between a cheap draft model and an expensive verifier. When those run on different nodes in a decentralized network, three properties of the protocol that are trivially safe on one machine become open attack surfaces.
6 min read ⬢ interactive