Natacha Crooks

Sintr: Safe Interactive Transactions in the Presence of Byzantine Clients

Byzantine fault-tolerant (BFT) systems are, in principle, an appealing foundation for transactional applications involving mutually distrustful participants. Yet their adoption has been hampered by two persistent stumbling blocks—performance and developer convenience—which are often in tension with one another. Recent...

This paper is included in the Proceedings of the 20th USENIX Symposium on Operating Systems Design and Implementation.

Token Latency Fairness: Performance Isolation for Multi-Tenant LLM Serving

FairInference provides the novelelta-token fairness guarantee: for a well-behaved client, if a token is generated in d time units in isolation, it will be generated within d + {\delta} time units in multi-tenant execution, providing strong latency isolation guarantees for LLM serving.