[model] feat: add NPU GRPO training scripts for Qwen2.5-32B/Qwen3-30B (Megaton/vLLM backends)#4984
Open
psyloy wants to merge 1 commit intoverl-project:mainfrom
Open
[model] feat: add NPU GRPO training scripts for Qwen2.5-32B/Qwen3-30B (Megaton/vLLM backends)#4984psyloy wants to merge 1 commit intoverl-project:mainfrom
psyloy wants to merge 1 commit intoverl-project:mainfrom
