zyxxmu/cam

Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference

Python

Issues

Questions about the CAM algorithm
#4 opened 2 months ago by icoderzqliu
0
Higher PPL on wikitext of dense llama-7b model
#3 opened 4 months ago by zhenyuliu1225
0
can not reproduce results in the paper
#2 opened 5 months ago by 0-KaiKai-0
2
problem about your packages
#1 opened 5 months ago by 0-KaiKai-0
4