Xinyu Yang

TurboBus: Pooling PCIe Bandwidth for LLM Workloads via Scale-Up Fabrics

TurboBus is presented, which pools PCIe bandwidth across co-located jobs via emerging scale-up fabrics and reduces first-token latency by up to 40% for on-demand model loading, achieves up to 1.6x throughput for KV-cache-offloaded inference, and accelerates training by up to 7%, while imposing less than 1% overhead on co-located workloads.