[feat] Fix Vllm, logprob, add filtering, temperature annealing, lr descent#6250
Merged
YeAnbang merged 4 commits intogrpo-latestfrom Mar 21, 2025
Merged
[feat] Fix Vllm, logprob, add filtering, temperature annealing, lr descent#6250YeAnbang merged 4 commits intogrpo-latestfrom
YeAnbang merged 4 commits intogrpo-latestfrom