Shuang Yu

Shuang Yu is a solution architect at NVIDIA, specializing in NLP and large language models, with a focus on reinforcement learning optimization from both algorithmic and infrastructure perspectives.
Avatar photo

Posts by Shuang Yu

Decorative image.
Agentic AI / Generative AI Apr 20, 2026

Run High-Throughput Reinforcement Learning Training with End-to-End FP8 Precision

As LLMs transition from simple text generation to complex reasoning, reinforcement learning (RL) plays a central role. Algorithms like Group Relative Policy... 9 MIN READ