Amey Naik

Amey Naik is a senior inference architect at NVIDIA. He focuses on LLM inference performance and helps shape next-generation hardware and system architectures from an inference-first perspective, making large-scale AI faster and more efficient to deploy. He holds a master's degree in electrical engineering from the University of Minnesota.
Amey Naik

Posts by Amey Naik

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