<  Back to the Polytechnique Montréal portal

XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference

João Monteiro, Étienne Marcotte, Pierre-André Noël, Valentina Zantedeschi, David Vázquez, Nicolas Chapados, Christopher J. Pal and Perouz Taslakian

Paper (2024)

An external link is available for this item
Department: Department of Computer Engineering and Software Engineering
PolyPublie URL: https://publications.polymtl.ca/74682/
Conference Title: Findings of the Association for Computational Linguistics (ACL 2024)
Conference Location: Miami, FL, USA
Conference Date(s): 2024-11-12 - 2024-11-16
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2024.findings-emnlp.896
Official URL: https://doi.org/10.18653/v1/2024.findings-emnlp.89...
Date Deposited: 10 Apr 2026 10:20
Last Modified: 10 Apr 2026 10:20
Cite in APA 7: Monteiro, J., Marcotte, É., Noël, P.-A., Zantedeschi, V., Vázquez, D., Chapados, N., Pal, C. J., & Taslakian, P. (2024, November). XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference [Paper]. Findings of the Association for Computational Linguistics (ACL 2024), Miami, FL, USA. https://doi.org/10.18653/v1/2024.findings-emnlp.896

Statistics

Dimensions

Repository Staff Only

View Item View Item