Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation
Zhenyu Liu, Yunzhen Liu, Zehao Fan +5
Mixture-of-Experts (MoE) models scale capacity via sparse activation but stress memory and bandwidth. Offloading alleviates GPU memory by fetching experts on demand, yet token-leve…
cs.LG2025
Context-Aware Mixture-of-Experts Inference on CXL-Enabled GPU-NDP Systems
Zehao Fan, Zhenyu Liu, Yunzhen Liu +4
Mixture-of-Experts (MoE) models scale large language models through conditional computation, but inference becomes memory-bound once expert weights exceed the capacity of GPU memor…