2 papers
cs.NI2025
PRIME: Pseudo-Random Integrated Multi-Part Entropy for Adaptive Packet Spraying in AI/ML Data centers
Ashkan Sobhani, Sogand Sadrhaghighi, Xingjun Chu
Large-scale distributed training in production data centers place significant demands on network infrastructure. In particular, significant load balancing challenges arise when pro…
cs.DC2024
P/D-Serve: Serving Disaggregated Large Language Model at Scale
Yibo Jin, Tao Wang, Huimin Lin +27
Serving disaggregated large language models (LLMs) over tens of thousands of xPU devices (GPUs or NPUs) with reliable performance faces multiple challenges. 1) Ignoring the diversi…