Liquid AI发布LFM2.5-DSpark模型，解码速度提升3.18倍

精选理由

Liquid AI给LFM2.5模型加了三个drafters，解码速度能快3.18倍，但输出结果和原来一模一样，不用改现有应用就能用。

AI 摘要

Liquid AI发布了LFM2.5-DSpark模型。该模型通过推测性解码技术，在保持输出结果不变的情况下，将解码速度提升了最高3.18倍。新模型包含三个约3亿参数的drafters。

Liquid AI发布LFM2.5-DSpark模型，解码速度提升3.18倍 — 图片来源 · marktechpost

原文 · marktechpost

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

Three ~300M drafters bring speculative decoding to LFM2.5, delivering up to 3.18x faster decoding with identical greedy output. The post Liquid AI Releases LFM2.5-DSpark Draft Models That Deliver Up to 3.18x Faster Decoding Without Changing Model Outputs appeared first on MarkTechPost .

阅读原文