Yuan,  Jiayi, Liu,  Hongyi, Zhong,  Shaochen, Chuang,  Yu-Neng, Li,  Songchen, Wang,  Guanchu, Le,  Duy, Jin,  Hongye, Chaudhary,  Vipin, Xu,  Zhaozhuo, Liu, Zirui, and Hu, Xia. KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches. Retrieved from https://par.nsf.gov/biblio/10577773.

Yuan,  Jiayi, Liu,  Hongyi, Zhong,  Shaochen, Chuang,  Yu-Neng, Li,  Songchen, Wang,  Guanchu, Le,  Duy, Jin,  Hongye, Chaudhary,  Vipin, Xu,  Zhaozhuo, Liu, Zirui, & Hu, Xia. KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches. Retrieved from https://par.nsf.gov/biblio/10577773.

Yuan,  Jiayi, Liu,  Hongyi, Zhong,  Shaochen, Chuang,  Yu-Neng, Li,  Songchen, Wang,  Guanchu, Le,  Duy, Jin,  Hongye, Chaudhary,  Vipin, Xu,  Zhaozhuo, Liu, Zirui, and Hu, Xia. "KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches". Country unknown/Code not available: The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP). https://par.nsf.gov/biblio/10577773.

@article{osti_10577773,
place = {Country unknown/Code not available}, title = {KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches}, url = {https://par.nsf.gov/biblio/10577773}, abstractNote = {}, journal = {}, publisher = {The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP)}, author = {Yuan,  Jiayi and Liu,  Hongyi and Zhong,  Shaochen and Chuang,  Yu-Neng and Li,  Songchen and Wang,  Guanchu and Le,  Duy and Jin,  Hongye and Chaudhary,  Vipin and Xu,  Zhaozhuo and Liu, Zirui and Hu, Xia}, }