Tag
GSPO
Posts and notes tagged with GSPO.
- September 12, 202611 min read
Group Sequence Policy Optimization (GSPO)
How GSPO fixes the instability of GRPO by moving the importance ratio from tokens to whole responses: one length-normalized sequence ratio, sequence-level clipping, and equal weights for every token, which stabilizes large Mixture-of-Experts training and powered Qwen3.