Self-Selected Attention Span for Accelerating Large Language Model Inference

Documenti analoghi

• Post Training Quantization of Large Language Models with Microscaling Formats
  di: Sharify, Sayeh, et al.
  Pubblicazione: (2024)
• Scaling Laws for Post Training Quantized Large Language Models
  di: Xu, Zifei, et al.
  Pubblicazione: (2024)
• Early Attentive Sparsification Accelerates Neural Speech Transcription
  di: Xu, Zifei, et al.
  Pubblicazione: (2025)
• Understanding the Difficulty of Low-Precision Post-Training Quantization for LLMs
  di: Xu, Zifei, et al.
  Pubblicazione: (2024)
• MF-QAT: Multi-Format Quantization-Aware Training for Elastic Inference
  di: Xu, Zifei, et al.
  Pubblicazione: (2026)