BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments

Xinghao Wang, Pengyu Wang, Bo Wang, Dong Zhang, Yunhua Zhou +1 more
2/12/2026

No official code found. Best implementation: xinghaow99/BitStack (38 stars, last commit 2025-02-17).

Semantic Scholar

Code Implementations(1)

xinghaow99/BitStackCommunity66%

[ICLR 2025] BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments

380Shell, PythonOct 31, 20241 years ago

Cite this paper

@article{wang2026bitstack,
  title  = {BitStack: Any-Size Compression of Large Language Models in Variable Memory Environments},
  author = {Xinghao Wang and Pengyu Wang and Bo Wang and Dong Zhang and Yunhua Zhou and Xipeng Qiu},
  year   = {2026},
  url    = {https://api.semanticscholar.org/CorpusID:d30a6c8798b828c6f75473d0f7b48a8ae4961d46},
  journal = {ICLR 2025 2025}
}

Discussion