KV Cache Quantization Benchmark: 4-Bit KIVI Finds 30 of 30 Needles
Authors
- Oleh Ivchenko (ORCID: https://orcid.org/0000-0002-9540-1637)
Institutions
- Odessa National Polytechnic University (UA)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.5281/zenodo.24295213
- Primary Topic
- Advanced Neural Network Applications
- Type
- preprint