Skip to main content
KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments
- Item #:
- 085713-0210
- UPC:
Details
-
DOI:
https://doi.org/10.52202/085713-0210
-
Author(s):
Junyoung Park, Dalton Jones, Matthew Morse, Raghavv Goel, Mingu Lee, Christopher Lott
-
Pages:
6771-6807 (37 pages)
-
Format:
PDF Paper Download
-
Conference:
Advances in Neural Information Processing Systems 38
-
Date/Location:
Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
-
Series:
Advances in Neural Information Processing Systems 38
-
Publisher:
Neural Information Processing Systems Foundation, Inc. (NeurIPS)
-
DOI:
https://doi.org/10.52202/085713-0210
-
Author(s):
Junyoung Park, Dalton Jones, Matthew Morse, Raghavv Goel, Mingu Lee, Christopher Lott
-
Pages:
6771-6807 (37 pages)
-
Format:
PDF Paper Download
-
Conference:
Advances in Neural Information Processing Systems 38
-
Date/Location:
Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
-
Series:
Advances in Neural Information Processing Systems 38
-
Publisher:
Neural Information Processing Systems Foundation, Inc. (NeurIPS)