Priority-Based Data Transfer Control for LLM Inference Streaming Leveraging Prompt Importance

Hiroki Baba, Kenshiro Wada, Kentaro Hayashi 0001, Kenzo Okuda, Naoki Kimishima, Tomonori Takeda. Priority-Based Data Transfer Control for LLM Inference Streaming Leveraging Prompt Importance. In 12th IEEE International Conference on Network Softwarization, NetSoft 2026, Berlin, Germany, June 29 - July 3, 2026. pages 108-116, IEEE, 2026. [doi]

Abstract

Abstract is missing.