Poster · Atlanta
KVBuffer: IO-aware Serving for Linear Attention
- When
- Wed 9 Dec 2026, 16:30–19:30 EST
- Where
- Hall C1, Georgia World Congress Center
- Session
- Atlanta Poster Session 2
- Authors
- Longwei Zou, Lin Zhong
- Organisations
- Yale University
- QRS classification
- Attention and transformers