4 papers
Probe and Skip: Self-Predictive Token Skipping for Efficient Long-Context LLM Inference
Zimeng Wu, Donghao Wang, Chaozhe Jin +2
Long-context inference enhances the reasoning capability of Large Language Models (LLMs), but incurs significant computational overhead. Token-oriented methods, such as pruning and…
MegaScale-MoE: Large-Scale Communication-Efficient Training of Mixture-of-Experts Models in Production
Chao Jin, Ziheng Jiang, Zhihao Bai +16
We present MegaScale-MoE, a production system tailored for the efficient training of large-scale mixture-of-experts (MoE) models. MoE emerges as a promising architecture to scale l…
MegaScale-Infer: Serving Mixture-of-Experts at Scale with Disaggregated Expert Parallelism
Ruidong Zhu, Ziheng Jiang, Chao Jin +17
Mixture-of-Experts (MoE) showcases tremendous potential to scale large language models (LLMs) with enhanced performance and reduced computational complexity. However, its sparsely…
StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation
Yinmin Zhong, Zili Zhang, Xiaoniu Song +11
Reinforcement learning (RL) has become the core post-training technique for large language models (LLMs). RL for LLMs involves two stages: generation and training. The LLM first ge…