Michael W. Mahoney

An LLM Compiler for Parallel Function Calling

A. Gholami, Nicholas Lee, Kurt Keutzer, 2023, ArXiv.

KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

A. Gholami, Y. Shao, Sehoon Kim, 2024, ArXiv.

Towards Scalable and Versatile Weight Space Learning

Konstantin Schürholt, Damian Borth, Michael W. Mahoney, 2024, 2406.09997.

Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior

Shashank Subramanian, W. Bhimji, Kurt Keutzer, 2022 .