量子位 QbitAI· 思邈·· 2d agoAI score38
Shishi Technology launches multimodal model service with 2.48x video generation speedup
提速2.48倍且画质不掉线,AI视频“降本增效”有了新解法
Summary
Chinese AI company Shishi Technology released a multimodal model service that it says speeds up video generation inference by an average of 2.48x end-to-end versus a Dense baseline while maintaining quality, using adaptive acceleration based on historical cache residuals. The service also pairs cache and memory management with SGLang and adds training-free modality-adaptive token compression, which it reports as 1.33x faster on the WorldSense benchmark.
This site provides summaries and links to the originals only.
Source: 量子位 QbitAI · qbitai.com