token-drafting

Tag

Cards List
#token-drafting

MMFlash: Faster Speculative Decoding for Vision-Language Models

Hugging Face Daily Papers ↗ · 2026-11-13 Cached

MMFlash improves multimodal speculative decoding by adaptively upweighting visually dependent tokens and using sparse attention for long video inputs, achieving up to 3.58× lossless decoding speedup and outperforming EAGLE-3 and DFlash.

0 favorites 0 likes
← Back to home

Submit Feedback