MF-QAT: Multi-Format Quantization-Aware Training for Elastic Inference

Documenti analoghi

• DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers
  di: Sharify, Sayeh, et al.
  Pubblicazione: (2026)
• 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)
• ResQ: Mixed-Precision Quantization of Large Language Models with Low-Rank Residuals
  di: Saxena, Utkarsh, et al.
  Pubblicazione: (2024)
• Post Training Quantization of Large Language Models with Microscaling Formats
  di: Sharify, Sayeh, et al.
  Pubblicazione: (2024)