ReaDy: Recurrent States as Dynamic Context for Speculative Drafting in Hybrid Linear Attention Large Language Models
ReaDy uses recurrent states for speculative drafting, reaching 3.16× speedup on Qwen3.8-27B.
Stories per day · 30 days
2 RSS
3 stories, newest first · one card per story
Stories tagged #dspark
ReaDy uses HLA recurrent states to speed speculative decoding
On Qwen3.8-27B and one B200, ReaDy averages 3.16 times autoregressive speed and beats DSpark on every benchmark.
Liquid AI Releases LFM2.5-VL-3B-DSpark: Speculative Decoding for Vision-Language Models With Up to 3.13x Faster Decoding
Liquid AI released a 280M drafter that speeds LFM2.5-VL-3B decoding by up to 3.13x.