Liquid AI Releases LFM2.5-DSpark Draft Models That Deliver Up to 3.18x Faster Decoding Without Changing Model Outputs

Liquid AI released DSpark draft models adding speculative decoding to LFM2.5, up to 3.18x faster without changing outputs.

MarkTechPost · Asif Razzaq · https://www.facebook.com/MarkTechPost/