RepQuant: Towards Accurate Post-Training Quantization of Large Transformer Models via Scale Reparameterization

Documenti analoghi

• OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization
  di: Li, Zhikai, et al.
  Pubblicazione: (2026)
• EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models
  di: Liu, Xuewen, et al.
  Pubblicazione: (2024)
• DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation
  di: Liu, Xuewen, et al.
  Pubblicazione: (2024)
• CacheQuant: Comprehensively Accelerated Diffusion Models
  di: Liu, Xuewen, et al.
  Pubblicazione: (2025)
• TTAQ: Towards Stable Post-training Quantization in Continuous Domain Adaptation
  di: Xiao, Junrui, et al.
  Pubblicazione: (2024)