FlashMap is released
The story so far
Polymathic AI and researchers from Princeton University released FlashMap, a flowchart drawer that can increase the decoding speed of LLMs by 6.14 times. By replacing the discrete diffusion drawer with a continuous flowchart, FlashMap achieved this improvement on the GSM8K task with Qwen3-8B, with its drawer weights open-sourced on Hugging Face and supporting vLLM and SGLang plugins.
AI-written from the reports · Updated 21 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- MarkTechPostPolymathic AI and Princeton Researchers Release FlashMap, a Flow Map Drafter for 6.14x Faster LLM Decoding
FlashMap replaces the discrete diffusion drawer with a continuous flow drawer, achieving up to 6.14 times lossless speed improvement on Qwen3-8B for GSM8K. Its drawer weights (Qwen3-8B and Qwen3-4B) have been open-sourced to Hugging Face, supporting vLLM and SGLang plugins.