Area of research
Computational Theory and Mathematics · Artificial Intelligence
Research interest
Research focused on Politeness and Paging, with related work in Algebraic number, Throughput, Cache. Notable publications include 'Efficient Memory Management for Large Language Model Serving with PagedAttention', 'Polite Combination of Algebraic Datatypes', and 'MoE-L ightning : High-Throughput MoE Inference on Memory-constrained GPUs'.