SGLang6 min read
Up to 3.2x Faster Inference with LFM2.5-DSpark
Today, we release DSpark draft model checkpoints for three models from our LFM2.5 family: LFM2.5-1.2B-Instruct, LFM2.5-2.6B, and LFM2.5-8B-A1B. These add a speculative decoding path that trades a minimal memory increase for a large decoding speedup without changing output quality:
By xx, Leonie Monigatti, Fernando Fernandes Neto, Tarek Dakhran, nathan ranchinHugging Face Blog
Read the full story
Originally published by Hugging Face Blog on Aug 20, 2026.
Comments
Sign in to join the discussion.