Harris Nover

Harris Nover is a distinguished software engineer at NVIDIA. His current focus is on optimizing LLM inference performance, particularly for hybrid models. He previously worked on telepresence, computer vision, big data processing, hardware design, and cryptography. He holds a PhD from the University of Wisconsin–Madison and a BS from the California Institute of Technology, both in mathematics.
Harris Nover

Posts by Harris Nover

Agentic AI / Generative AI

ReplaySSM: Rethinking State Storage for Faster Hybrid-Model Decoding

Hybrid models interleave state-space model (SSM) layers with a few attention layers. NVIDIA Nemotron 3, Qwen3.5 through Qwen3.8, Kimi-K3, and GLM-5.3-Flash are... 14 MIN READ