%0 Conference Paper %1 conf/mlsys/0015LCKCW24 %A Zhang, Zhenyu %A Liu, Shiwei %A Chen, Runjin %A Kailkhura, Bhavya %A Chen, Beidi %A Wang, Atlas %B MLSys %D 2024 %E Gibbons, Phillip B. %E Pekhimenko, Gennady %E Sa, Christopher De %I mlsys.org %K dblp %T Q-Hitter: A Better Token Oracle for Efficient LLM Inference via Sparse-Quantized KV Cache. %U http://dblp.uni-trier.de/db/conf/mlsys/mlsys2024.html#0015LCKCW24

@inproceedings{conf/mlsys/0015LCKCW24, added-at = {2024-08-02T00:00:00.000+0200}, author = {Zhang, Zhenyu and Liu, Shiwei and Chen, Runjin and Kailkhura, Bhavya and Chen, Beidi and Wang, Atlas}, biburl = {https://www.bibsonomy.org/bibtex/24400fa2e9dc2cb4969164ea813c5f13f/dblp}, booktitle = {MLSys}, crossref = {conf/mlsys/2024}, editor = {Gibbons, Phillip B. and Pekhimenko, Gennady and Sa, Christopher De}, ee = {https://proceedings.mlsys.org/paper_files/paper/2024/hash/bbb7506579431a85861a05fff048d3e1-Abstract-Conference.html}, interhash = {087647b4bbedf877548a8dfb3e3aa385}, intrahash = {4400fa2e9dc2cb4969164ea813c5f13f}, keywords = {dblp}, publisher = {mlsys.org}, timestamp = {2024-08-05T07:40:45.000+0200}, title = {Q-Hitter: A Better Token Oracle for Efficient LLM Inference via Sparse-Quantized KV Cache.}, url = {http://dblp.uni-trier.de/db/conf/mlsys/mlsys2024.html#0015LCKCW24}, year = 2024 }