NVlabs/GDPO · AI Repo StatsNVNVlabs/GDPO
Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
LLM & foundation modelsPython Apache-2.0 38created 2025-12-09 #agentic-ai#grpo#llm#reasoning#rl#trl#verl