← back to paper

Review history

arxiv: 2608.06557 · 2 revisions

Cascade: Exploiting SLO-Aware latency budget for fair and high goodput LLM inference serving

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   123032 ms 19671 in 15610 out 2026-08-15T14:31:25.419231+00:00
2. 2026-08-10 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   118461 ms 3483 in 4074 out 2026-08-10T04:16:47.204738+00:00