Showing cs.DCShow all
2 papers · 1 filter
cs.DC2025
Bounded Memory in Distributed Networks
Ran Ben Basat, Keren Censor-Hillel, Yi-Jun Chang +3
The recent advent of programmable switches makes distributed algorithms readily deployable in real-world datacenter networks. However, there are still gaps between theory and pract…
cs.DC2025
HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference
Zeyu Zhang, Haiying Shen, Shay Vargaftik +3
Disaggregated Large Language Model (LLM) inference has gained popularity as it separates the computation-intensive prefill stage from the memory-intensive decode stage, avoiding th…