CaM: Cache Merging for Memory-efficient LLMs Inference

Yuxin Zhang, Yuxuan Du, Gen Luo, Yunshan Zhong, Zhenyu (Allen) Zhang +2 more
2/12/2026

No official code found. Best implementation: zyxxmu/cam (51 stars, last commit 2024-06-19).

Semantic Scholar

Code Implementations(1)

zyxxmu/camCommunity60%

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

513PythonMay 22, 20242 years ago

Similar Papers

Online Control for Meta-optimization

79% match2026

LOGO - Long cOntext aliGnment via efficient preference Optimization

79% match1 repo262026

Near-optimal Sketchy Natural Gradients for Physics-Informed Neural Networks

74% match2026

PN-GAIL: Leveraging Non-optimal Information from Imperfect Demonstrations

74% match1 repo52026

Energy-efficient Hybrid Model Predictive Trajectory Planning for Autonomous Electric Vehicles

74% match2024

Revisit Finetuning strategy for Few-Shot Learning to Transfer the Emdeddings

70% match2026

Cite this paper

@article{zhang2026cam,
  title  = {CaM: Cache Merging for Memory-efficient LLMs Inference},
  author = {Yuxin Zhang and Yuxuan Du and Gen Luo and Yunshan Zhong and Zhenyu (Allen) Zhang and Shiwei Liu and Rongrong Ji},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:3ebf3cf8f370c02393c965fcbbb77ef35545ceb8},
  journal = {ICML 2024 2024}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/3ebf3cf8f370c02393c965fcbbb77ef35545ceb8.svg)](https://codeofpaper.com/paper/3ebf3cf8f370c02393c965fcbbb77ef35545ceb8)

Discussion