Yu-Feng Gu

Unlocking Software-defined GPU Fabric Scheduling in the LLM Era

Large language model (LLM) systems increasingly rely on techniques such as prefill-decode disaggregation, KV-cache offloading, and computation-communication overlap. These optimizations often treat GPU interconnects as best-effort substrates, overlooking contention across shared PCIe, NVLink, and RDMA fabrics. We chara...