Yoed Ginzburg

Yoed Ginzburg is a software engineering team lead at NVIDIA, working on exploring and building advanced GPU sharing technologies by adopting resource management techniques from the virtualization and containerization worlds. Prior to that, Yoed worked at Run:ai on Run:ai GPU fractions and GPU memory swap technologies, and has joined NVIDIA in 2024 as part of the Run:ai acquisition. Yoed is passionate about high-performance and utilization improvements, as well as interested in orchestration, operating systems, and low-level programming.
Avatar photo

Posts by Yoed Ginzburg

AI Platforms / Deployment Sep 02, 2025

Cut Model Deployment Costs While Keeping Performance With GPU Memory Swap

Deploying large language models (LLMs) at scale presents a dual challenge: ensuring fast responsiveness during high demand, while managing the costs of GPUs.... 6 MIN READ