Offloading to CXL-based Computational Memory

Distributed, Parallel, and Cluster Computing

MoSKA: Mixture of Shared KV Attention for Efficient Long-Sequence LLM Inference

Machine Learning (CS)

Cocoon: A System Architecture for Differentially Private Training with Correlated Noises

Hardware Architecture

cMPI: Using CXL Memory Sharing for MPI One-Sided and Two-Sided Inter-Node Communications

Distributed, Parallel, and Cluster Computing

Rethinking Caching for LLM Serving Systems: Beyond Traditional Heuristics

Databases