LLM-augmented data workflows often involve multiple heterogeneous models operating over substantial shared context, such as schemas, tool specifications, interaction history, and intermediate results. Although prefix caching can reduce prefilling overhead, existing approaches are largely limited to reuse within the sam...
Zhan-Yang Jin, Yu-Ze Luo, Bin Cui et al.· 0 citations
Janus is a Service-Engine co-designed multi-model serving system built around dual-timescale scheduling that maintains 0.97-1.0 SLO attainment, versus 0.80-0.92 for the strongest baseline, while using 13,440 device-hours/day, 27% less than static Serverless-LLM.
Tian-Bao Zhou, Yi Wang, Yu Zhou et al.· Proceedings of the ACM SIGOP...· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.