Predicting Probabilities of Error to Combine Quantization and Early Exiting: QuEE

Documenti analoghi

• Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN
  di: Regol, Florence, et al.
  Pubblicazione: (2023)
• Dynamic layer selection in decoder-only transformers
  di: Glavas, Theodore, et al.
  Pubblicazione: (2024)
• Interacting Diffusion Processes for Event Sequence Forecasting
  di: Zeng, Mai, et al.
  Pubblicazione: (2023)
• When to retrain a machine learning model
  di: Florence, Regol, et al.
  Pubblicazione: (2025)
• Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generation
  di: Sommer, Johanna, et al.
  Pubblicazione: (2025)