Liu, Yuhan, Li, Hanchen, Cheng, Yihua, Ray, Siddhant, Huang, Yuyang, Zhang, Qizheng, Du, Kuntai, Yao, Jiayi, Lu, Shan, Ananthanarayanan, Ganesh, Maire, Michael, Hoffmann, Henry, Holtzman, Ari, and Jiang, Junchen. CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving. Retrieved from https://par.nsf.gov/biblio/10583499. Web. doi:10.1145/3651890.3672274.

Liu, Yuhan, Li, Hanchen, Cheng, Yihua, Ray, Siddhant, Huang, Yuyang, Zhang, Qizheng, Du, Kuntai, Yao, Jiayi, Lu, Shan, Ananthanarayanan, Ganesh, Maire, Michael, Hoffmann, Henry, Holtzman, Ari, & Jiang, Junchen. CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving. Retrieved from https://par.nsf.gov/biblio/10583499. https://doi.org/10.1145/3651890.3672274

Liu, Yuhan, Li, Hanchen, Cheng, Yihua, Ray, Siddhant, Huang, Yuyang, Zhang, Qizheng, Du, Kuntai, Yao, Jiayi, Lu, Shan, Ananthanarayanan, Ganesh, Maire, Michael, Hoffmann, Henry, Holtzman, Ari, and Jiang, Junchen. "CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving". Country unknown/Code not available: ACM. https://doi.org/10.1145/3651890.3672274. https://par.nsf.gov/biblio/10583499.

@article{osti_10583499,
place = {Country unknown/Code not available}, title = {CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving}, url = {https://par.nsf.gov/biblio/10583499}, DOI = {10.1145/3651890.3672274}, abstractNote = {}, journal = {}, publisher = {ACM}, author = {Liu, Yuhan and Li, Hanchen and Cheng, Yihua and Ray, Siddhant and Huang, Yuyang and Zhang, Qizheng and Du, Kuntai and Yao, Jiayi and Lu, Shan and Ananthanarayanan, Ganesh and Maire, Michael and Hoffmann, Henry and Holtzman, Ari and Jiang, Junchen}, }