Lei Chen

Modern GPU workloads increasingly rely on dynamic and fine-grained memory allocation, yet GPU memory management remains CPU-centric. In current GPU runtimes, allocation metadata updates, page-table construction, translation-state propagation, and TLB shootdowns are largely serialized through the...

Serving deep learning based recommendation models (DLRM) at scale is challenging. Existing approaches rely on dedicated ANN indexing and filtering services on CPUs, suffering from non-negligible costs and missing co-design opportunities. Such inefficiency makes them difficult to support complex m...