Posts by Yuhan Yang

Debugging Logprob Mismatches in LLM Reinforcement Learning

• 23 September 2026
Xinyu Kang , Yuhan Yang , Yuankai Chen , Liz Li
English
Software tools & optimizations
Reinforcement Learning AI/ML LLM PyTorch

In online reinforcement learning (RL), a language model generates responses, receives rewards, and updates its weights to improve future responses. Many systems split this loop between a rollout engine, which generates the responses, and a trainer, which learns from them. Both engines evaluate token probabilities: rollout records the log-probability, or logprob, of each token it generates, while the trainer evaluates those same tokens when computing its loss. After the update, the new weights are sent back to rollout, and the loop begins again.

Read more ...

---

veRL on AMD: Production-Ready RL Post-Training on ROCm

• 08 September 2026
Fuwei Yang , Zhaodong Bing , Mingjie Lu , Xiaohong Kou , Yuhan Yang , Wei Cai , Liz Li , Yuankai Chen , Yao Fu , Dong Li , Zhenyu Gu
English
Software tools & optimizations
Reinforcement Learning AI/ML Fine-Tuning LLM

Reinforcement learning post-training on AMD Instinct GPUs is here — with a turnkey container, AITER-accelerated vLLM and SGLang rollout, and accuracy validated on both MI300 and MI355.

Read more ...

---