Xingda Wei

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...

Silent Data Corruption (SDC) has emerged as a critical reliability bottleneck in Large Language Model (LLM) training, where hardware faults are frequently indistinguishable from software anomalies. While standard industry practice relies on synthetic microbenchmarks for fault isolation, our exper...

The emergence of AI workloads has placed rigorous bandwidth requirements on cloud storage, which are challenging to meet due to inherent hardware restrictions in cost-efficient disaggregated storage architectures, as well as the non-triviality of implementing application-tailored optimizations. T...