Sustainable LLM Inference for Edge AI: Evaluating Quantized LLMs for Energy Efficiency, Output Accuracy, and Inference Latency

Documenti analoghi

• The Price of Prompting: Profiling Energy Use in Large Language Models Inference
  di: Husom, Erik Johannes, et al.
  Pubblicazione: (2024)
• A Comparative Study on Large Language Models for Log Parsing
  di: Astekin, Merve, et al.
  Pubblicazione: (2024)
• Greening AI Inference with Accuracy and Latency-aware User Incentives
  di: Siris, Vasilios A., et al.
  Pubblicazione: (2026)
• Privacy Policy Analysis through Prompt Engineering for LLMs
  di: Goknil, Arda, et al.
  Pubblicazione: (2024)
• Security Modelling for Cyber-Physical Systems: A Systematic Literature Review
  di: Huang, Shaofei, et al.
  Pubblicazione: (2024)