Dynamic memory compression: Retrofitting LLMs for accelerated inference

Piotr Nawrot^*, Adrian Łańcucki, Marcin Chochowski, David Tarjan, Edoardo M. Ponti

^*Corresponding author for this work

Research output: Contribution to conference › Poster › peer-review

Original language	English
DOIs	https://doi.org/10.48550/arXiv.2403.09636
Publication status	Accepted/In press - 2 May 2024
Event	The 41st International Conference on Machine Learning - Vienna, Austria Duration: 21 Jul 2024 → 27 Jul 2024 https://icml.cc/

Conference	The 41st International Conference on Machine Learning
Abbreviated title	ICML 2024
Country/Territory	Austria
City	Vienna
Period	21/07/24 → 27/07/24
Internet address	https://icml.cc/

Access to Document

@conference{f0e43097fbdb4100a4ac787ba7f336e1,

title = "Dynamic memory compression: Retrofitting LLMs for accelerated inference",

author = "Piotr Nawrot and Adrian {\L}a{\'n}cucki and Marcin Chochowski and David Tarjan and Ponti, {Edoardo M.}",

year = "2024",

month = may,

day = "2",

doi = "10.48550/arXiv.2403.09636",

language = "English",

note = "The 41st International Conference on Machine Learning, ICML 2024 ; Conference date: 21-07-2024 Through 27-07-2024",

url = "https://icml.cc/",

}