News for hackers. Stuff that matters.
Re:Built RL for long-horizon agents – tested on 32x H100s bu... by Danau5tin on Wednesday July 30, 2025 @09:53AM (#44734233)
Exactly my first thought when I realised the cost! Currently LoRA is not supported by rLLM (The team told me they aim to support in next release), but it is certainly possible to port to verl directly or another RL framework for sure. I just did not have the time to port again (already done 2x as other RL frameworks had issues)

There are no comments on this comment yet.