3 papers
cs.LG2026
BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning
Yuhang Xu, Kaibin Tian, Yang Tian +6
Reinforcement Learning (RL) has become a cornerstone for improving the performance of Large Language Models (LLMs). However, its rollout phase constitutes a significant efficiency…
cs.DC2025
Collaborative Lossless LLM Inference Serving with Offloading-based Pipeline Parallelism on Edge Devices
Mingyu Sun, Xiao Zhang, Shen Qu +5
Providing lossless inference services of LLMs on edge devices remains challenging, especially given the extremely tight memory budgets. The existing offloading techniques inevitabl…
cs.DC2024
Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models with Structured Pruning in Resource-Limited Clients
Yan Li, Xiao Zhang, Mingyi Li +7
In this work, we study to release the potential of massive heterogeneous weak computing power to collaboratively train large-scale models on dispersed datasets. In order to improve…