A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Document] Add ms-swift library to rlhf.md (#27469)
jinghanhu committed
Oct 25, 2025 at 04:31 UTC
17af6aa0da5e825007d1d32cf6df8b3c78c5558d
1 file changed
+1
docs/training/rlhf.md
+1
@@ -5,6 +5,7 @@ Reinforcement Learning from Human Feedback (RLHF) is a technique that fine-tunes
5
The following open-source RL libraries use vLLM for fast rollouts (sorted alphabetically and non-exhaustive):
6
7
- [Cosmos-RL](https://github.com/nvidia-cosmos/cosmos-rl)
8
+- [ms-swift](https://github.com/modelscope/ms-swift/tree/main)
9
- [NeMo-RL](https://github.com/NVIDIA-NeMo/RL)
10
- [Open Instruct](https://github.com/allenai/open-instruct)
11
- [OpenRLHF](https://github.com/OpenRLHF/OpenRLHF)