24 citations · 31 across the 13 of their papers we have counts for
3 papers · 1 filter
Towards Full Pipeline FP8 Reinforcement Learning for LLMs
Fanchao Chen, Ziheng Jiang, Ziyun Wei +5
Reinforcement learning (RL) has become a key technique for improving the reasoning and agentic abilities of large language models (LLMs). Although FP8 quantization can accelerate R…
DisagMoE: Computation-Communication overlapped MoE Training via Disaggregated AF-Pipe Parallelism
Zhichen Zeng, Chi-Chih Chang, Jiayi Wang +10
Mixture-of-experts (MoE) architectures enable trillion-parameter LLMs with sparsely activated experts. Expert parallelism (EP) is a widely adopted MoE training strategy, but it suf…
SRT: Accelerating Reinforcement Learning via Speculative Rollout with Tree-Structured Cache
Chi-Chih Chang, Siqi Zhu, Zhichen Zeng +5
We present Speculative Rollout with Tree-Structured Cache (SRT), a simple, model-free approach to accelerate on-policy reinforcement learning (RL) for language models without sacri…