# Polymathic AI and Princeton researchers release FlashMap, a flow map drafter for faster LLM decoding

> Original title: Polymathic AI and Princeton Researchers Release FlashMap, a Flow Map Drafter for 6.14x Faster LLM Decoding

- Source: MarkTechPost
- Published: 2026-10-28T08:18:03.000Z
- Bad Influence: https://badinfluence.news/items/rdr4118vh05vd4x5blf5hfny9
- Original: https://www.marktechpost.com/2026/10/28/flashmap-flow-map-speculative-decoding/

## Summary

Researchers from Polymathic AI, Princeton University, and other institutions released FlashMap, a speculative decoding drafter that proposes a 16-token block in one forward pass. The research team reports up to a 6.14x lossless speedup on GSM8K with Qwen3-8B, with drafter weights on Hugging Face and vLLM and SGLang plugins. The article's comparison notes that the drafter has about half the parameters of DFlash and beats it on acceptance length in 15 of 18 one-step settings.

## Why it matters

The article compares FlashMap with DFlash and EAGLE-3 on matched retrained baselines, showing where its speedup and acceptance gains come from.