Skip to main content
Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time
- Item #:
- 075280-2279
- UPC:
Details
-
DOI:
https://doi.org/10.52202/075280-2279
-
Author(s):
Aditya Desai, Anastasios Kyrillidis, Fangshuo Liao, Zichang Liu, Anshumali Shrivastava, Weitao Wang, Victor Xie, Zhaozhuo Xu
-
Pages:
52342-52364 (23 pages)
-
Format:
PDF Paper Download
-
Conference:
Advances in Neural Information Processing Systems 36
-
Date/Location:
Held 10-16 December 2023, New Orleans, Louisiana, USA.
-
Series:
Advances in Neural Information Processing Systems 36
-
Publisher:
Neural Information Processing Systems Foundation, Inc. (NeurIPS)
-
DOI:
https://doi.org/10.52202/075280-2279
-
Author(s):
Aditya Desai, Anastasios Kyrillidis, Fangshuo Liao, Zichang Liu, Anshumali Shrivastava, Weitao Wang, Victor Xie, Zhaozhuo Xu
-
Pages:
52342-52364 (23 pages)
-
Format:
PDF Paper Download
-
Conference:
Advances in Neural Information Processing Systems 36
-
Date/Location:
Held 10-16 December 2023, New Orleans, Louisiana, USA.
-
Series:
Advances in Neural Information Processing Systems 36
-
Publisher:
Neural Information Processing Systems Foundation, Inc. (NeurIPS)