An I/O Characterizing Study of Offloading LLM Models and KV Caches to NVMe SSD
| Title: | An I/O Characterizing Study of Offloading LLM Models and KV Caches to NVMe SSD |
|---|---|
| Authors: | Ren, Zebin; Doekemeijer, Krijn; De Matteis, Tiziano; Pinto, Christian; Stoica, Radu; Trivedi, Animesh |
| Source: | Proceedings of the 5th Workshop on Challenges and Opportunities of Efficient and Performant Storage Systems. :23-33 |
| Availability: | http://dl.acm.org/doi/10.1145/3719330.3721230 |
| Database: | ACM Full-Text Collection |