2 papers
cs.DC2026
VoltanaLLM: Energy-Efficient and SLO-Aware Disaggregated LLM Serving via Adaptive Frequency Control and State-Space Routing
Jiahuan Yu, Aryan Taneja, Junfeng Lin +1
The energy cost of Large Language Model (LLM) inference is rapidly becoming a barrier to sustainable and scalable deployment. Although modern serving architectures expose distinct…
cs.DC2026
SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips
Jiahuan Yu, Mingtao Hu, Zichao Lin +1
Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memory capacity. When high request rates ex…