Yinmin Zhong

Optimizing RLHF Training for Large Language Models with Stage Fusion

2024 · arXiv (Cornell University)

We present RLHFuse, an efficient training system with stage fusion for Reinforcement Learning from Human Feedback (RLHF). Due to the intrinsic nature of RLHF training, i.e., the data skewness in the generation stage and the …

LoongServe: Efficiently Serving Long-Context Large Language Models with Elastic Sequence Parallelism

2024

The context window of large language models (LLMs) is rapidly increasing, leading to a huge variance in resource usage between different requests as well as between different phases of the same request. Restricted by static …