@article{osti_10654606,
place = {Country unknown/Code not available},
title = {FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inference},
url = {https://par.nsf.gov/biblio/10654606},
abstractNote = {},
journal = {},
publisher = {Association for Computational Linguistics},
author = {Wang, Dongwei and Liu, Zijie and Wang, Song and Ren, Yuxin and Deng, Jianing and Hu, Jingtong and Chen, Tianlong and Yang, Huanrui},
}
Warning: Leaving National Science Foundation Website
You are now leaving the National Science Foundation website to go to a non-government website.
Website:
NSF takes no responsibility for and exercises no control over the views expressed or the accuracy of
the information contained on this site. Also be aware that NSF's privacy policy does not apply to this site.