<p>FlashMap is a speculative decoding drafter from Polymathic AI, Princeton and USC ISI researchers. It drafts 16 tokens jointly in one pass and reaches up to 6.14x lossless speedup on Qwen3-8B.</p> <p>The post <a href="https://www.marktechpost.com/2026/10/28/flashmap-flow-map-speculative-decoding/">Polymathic AI and Princeton Researchers Release FlashMap, a Flow Map Drafter for 6.14x Faster LLM Decoding</a> appeared first on <a href="https://www.marktechpost.com">MarkTechPost</a>.</p>