Poster · Sydney
vExpert: Virtualizing Expert Storage for Adaptive Load Balancing in Distributed MoE Inference
- When
- Thu 10 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 5
- Authors
- Wenxun Wang, Xiuhong Li, Yida Wang, Chen Tang, Zongle Huang, Ke Hong, Yu Wang, Yongpan Liu
- Organisations
- Tsinghua University, Peking University, Capital Normal University
- QRS classification
- Efficient and distributed ML systems