Wenyuan Yu

High-quality LLM request scheduling requires meeting two key objectives: ensuring the routed instance has KV$ to accelerate request execution, and ensuring that the workload is balanced across instances. Achieving both objectives is challenging because pursuing one may compromise the other. Curre...

Large Language Model (LLM) inference services in production operate under stringent, fine-grained Service Level Objectives (SLOs). Unlike throughput-oriented LLM training, even sporadic performance anomalies during inference can violate SLOs, underscoring the need for improved tracing and diagnos...