Poster · Sydney
TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks
- When
- Wed 9 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 3
- Authors
- Hanzhang Shen, Haoran Wu, Yiren Zhao, Robert Mullins
- Organisations
- University of Illinois Urbana-Champaign, University of Cambridge, Imperial College London
- QRS classification
- Agentic AI, Efficient and distributed ML systems