Harry Xu

Inference providers must maintain availability for many LLMs, including low-volume but essential models, making resource efficiency increasingly important as token prices fall. Analysis of production traces reveals a dynamic _bursty-group pattern_ in which sets of models become active together an...

There is increasing interest in privacy-preserving data analytics applications. These applications rely on Secure Computation (SC), a family of cryptographic techniques for computing on encrypted data. Unfortunately, SC amplifies the memory overhead of data-intensive data analytics applications,...