Cheng, Feng, Guo, Cong, Wei, Chiyue, Zhang, Junyao, Zhou, Changchun, Hanson, Edward, Zhang, Jiaqi, Liu, Xiaoxiao, Li, Hai, and Chen, Yiran. Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-Aware Cache Compression. Retrieved from https://par.nsf.gov/biblio/10624035. Web. doi:10.1145/3695053.3731024.

Cheng, Feng, Guo, Cong, Wei, Chiyue, Zhang, Junyao, Zhou, Changchun, Hanson, Edward, Zhang, Jiaqi, Liu, Xiaoxiao, Li, Hai, & Chen, Yiran. Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-Aware Cache Compression. Retrieved from https://par.nsf.gov/biblio/10624035. https://doi.org/10.1145/3695053.3731024

Cheng, Feng, Guo, Cong, Wei, Chiyue, Zhang, Junyao, Zhou, Changchun, Hanson, Edward, Zhang, Jiaqi, Liu, Xiaoxiao, Li, Hai, and Chen, Yiran. "Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-Aware Cache Compression". Country unknown/Code not available: ACM. https://doi.org/10.1145/3695053.3731024. https://par.nsf.gov/biblio/10624035.

@article{osti_10624035,
place = {Country unknown/Code not available}, title = {Ecco: Improving Memory Bandwidth and Capacity for LLMs via Entropy-Aware Cache Compression}, url = {https://par.nsf.gov/biblio/10624035}, DOI = {10.1145/3695053.3731024}, abstractNote = {}, journal = {}, publisher = {ACM}, author = {Cheng, Feng and Guo, Cong and Wei, Chiyue and Zhang, Junyao and Zhou, Changchun and Hanson, Edward and Zhang, Jiaqi and Liu, Xiaoxiao and Li, Hai and Chen, Yiran}, }