QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead

Cite

Text

Zandieh et al. "QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I24.34773

Markdown

[Zandieh et al. "QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/zandieh2025aaai-qjl/) doi:10.1609/AAAI.V39I24.34773

BibTeX

@inproceedings{zandieh2025aaai-qjl,
  title     = {{QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead}},
  author    = {Zandieh, Amir and Daliri, Majid and Han, Insu},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {25805-25813},
  doi       = {10.1609/AAAI.V39I24.34773},
  url       = {https://mlanthology.org/aaai/2025/zandieh2025aaai-qjl/}
}