4 citations · 6 across the 4 of their papers we have counts for
4 papers
ReviveMoE: Fast Recovery for Hardware Failures in Large-Scale MoE LLM Inference Deployments
Haley Li, Xinglu Wang, Cong Feng +12
As LLM deployments scale over more hardware, the probability of a single failure in a system increases significantly, and cloud operators must consider robust countermeasures to ha…
SuperNIC: A Hardware-Based, Programmable, and Multi-Tenant SmartNIC
Yizhou Shan, Will Lin, Ryan Kosta +2
With CPU scaling slowing down in today's data centers, more functionalities are being offloaded from the CPU to auxiliary devices. One such device is the SmartNIC, which is being i…
Clio: A Hardware-Software Co-Designed Disaggregated Memory System
Zhiyuan Guo, Yizhou Shan, Xuhao Luo +2
Memory disaggregation has attracted great attention recently because of its benefits in efficient memory utilization and ease of management. So far, memory disaggregation research…
Storm: a fast transactional dataplane for remote data structures
Stanko Novakovic, Yizhou Shan, Aasheesh Kolli +7
RDMA is an exciting technology that enables a host to access the memory of a remote host without involving the remote CPU. Prior work shows how to use RDMA to improve the performan…