Poster · Sydney
NyoomFloat12: Accelerating LLM Inference via Lossless 12-bit Weight Compression
- When
- Thu 10 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 6
- Authors
- Sylvie Liberman, Xinyu Fang, Tianyi Zhang, Tri Dao, Dan Fu
- Organisations
- Together AI, Johns Hopkins University, Princeton University, University of California, San Diego
- QRS classification
- Language models