Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
The SIMPLE Law for Energy Cost of LLM Inference
Hiari Pizzini Cavagna, Andrea Proia, Daniele Cesarini +2
Generative AI is billed per token, yet tokens are not equally expensive. Each token enters the KV-cache and raises the cost of those that follow, so energy grows non-linearly along…
cs.AI2026
SweetSpot: An Analytical Model for Predicting Energy Efficiency of LLM Inference
Hiari Pizzini Cavagna, Andrea Proia, Giacomo Madella +5
Large Language Models (LLMs) inference is central to modern AI applications, dominating worldwide datacenter workloads, making it critical to predict its energy footprint. Existing…