Zebin Ren, Krijn Doekemeijer, Tiziano De Matteis, Christian Pinto, Radu Stoica, Animesh Trivedi. An I/O Characterizing Study of Offloading LLM Models and KV Caches to NVMe SSD. In Proceedings of the 5th Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems, CHEOPS 2025, Rotterdam, The Netherlands, 30 March 2025 - 3 April 2025. pages 23-33, ACM, 2025. [doi]
Abstract is missing.