2 papers
cs.AR2026
ODMA: On-Demand Memory Allocation Strategy for LLM Serving on LPDDR-Class Accelerators
Guoqiang Zou, Wanyu Wang, Hao Zheng +2
Existing memory management techniques severely hinder efficient Large Language Model serving on accelerators constrained by poor random-access bandwidth.While static pre-allocation…
cs.DC2025
KAITIAN: A Unified Communication Framework for Enabling Efficient Collaboration Across Heterogeneous Accelerators in Embodied AI Systems
Jieke Lin, Wanyu Wang, Longxiang Yin +1
Embodied Artificial Intelligence (AI) systems, such as autonomous robots and intelligent vehicles, are increasingly reliant on diverse heterogeneous accelerators (e.g., GPGPUs, NPU…