collaborators
Showing cs.DCShow all

11 papers · 1 filter

cs.DC2026

SMetric: Rethink LLM Scheduling for Serving Agents with Balanced Session-centric Scheduling

Jiahao Wang, Kaizhan Lin, Kaixi Zhang +7

LLM scheduling is critical to serving, yet it remains unclear how well existing designs fit agentic serving--with LLM requests issued by agents instead of humans. This shifts the w…

cs.DC2026

CoAgent: Concurrency Control for Multi-Agent Systems

Hongtao Lyu, Dingyan Zhang, Mingyu Wu +2

Multi-agent LLM systems -- coding agents, devops agents, document agents -- now routinely run several agents in parallel against the same git tree, Kubernetes cluster, or document.…

cs.DC2026

Simple is Better: Multiplication May Be All You Need for LLM Request Scheduling

Dingyan Zhang, Jinbo Han, Kaixi Zhang +6

High-quality LLM request scheduling requires meeting two key objectives: ensuring the routed instance has KVCache to accelerate request execution, and ensuring that the workload is…

cs.DC2026

KVCache Cache in the Wild: Characterizing and Optimizing KVCache Cache at a Large Cloud Provider

Jiahao Wang, Jinbo Han, Xingda Wei +6

Serving large language models (LLMs) is important for cloud providers, and caching intermediate results (KV$) after processing each request substantially improves serving throughp…

cs.DC2025

Fast LLM Post-training via Decoupled and Fastest-of-N Speculation

Rongxin Cheng, Kai Zhou, Xingda Wei +8

Rollout dominates the training time in large language model (LLM) post-training, where the trained model is used to generate tokens given a batch of prompts. This work, SpecActor,…

cs.DC2025

KunServe: Parameter-centric Memory Management for Efficient Memory Overloading Handling in LLM Serving

Rongxin Cheng, Yuxin Lai, Xingda Wei +2

Serving LLMs with a cluster of GPUs is common nowadays, where the serving system must meet strict latency SLOs required by applications. However, the stateful nature of LLM serving…