XWind is a reactive cross-site router for LLM inference at wind farms that cuts P99 latency by up to 52% versus strong baselines in a 64-GPU emulation of three sites.
Wright, and Yong Chen
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
EnergAIzer predicts module-level GPU utilization from structured kernel patterns and feeds it into a power model to estimate dynamic power with 8% error on Ampere GPUs and 7% on H100 forecasts.
citing papers explorer
-
XWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms
XWind is a reactive cross-site router for LLM inference at wind farms that cuts P99 latency by up to 52% versus strong baselines in a 64-GPU emulation of three sites.
-
EnergAIzer: Fast and Accurate GPU Power Estimation Framework for AI Workloads
EnergAIzer predicts module-level GPU utilization from structured kernel patterns and feeds it into a power model to estimate dynamic power with 8% error on Ampere GPUs and 7% on H100 forecasts.