Book
Open access
Sep 2026
Unlocking Software-defined GPU Fabric Scheduling in the LLM Era
This study describes GPU-fabric contention in LLM workloads and presents GPUWeaver, a context-aware communication scheduler that monitors application progress and fabric state, identifies contention, and dynamically regulates communication injection according to application performance goals.
Dan-Yang Chen, Yu-Feng Gu, Yi-Bo Huang et al.
· Proceedings of the 17th ACM... · 2 citations