2 papers
cs.DC2026
Varuna: Enabling Failure-Type Aware RDMA Failover
Xiaoyang Wang, Yongkun Li, Lulu Yao +7
RDMA link failures can render connections temporarily unavailable, causing both performance degradation and significant recovery overhead. To tolerate such failures, production dat…
cs.AR2025
UB-Mesh: a Hierarchically Localized nD-FullMesh Datacenter Network Architecture
Heng Liao, Bingyang Liu, Xianping Chen +31
As the Large-scale Language Models (LLMs) continue to scale, the requisite computational power and bandwidth escalate. To address this, we introduce UB-Mesh, a novel AI datacenter…