Astro: Activation-guided Structured Regularization for Outlier-Robust LLM Post-Training Quantization

Documenti analoghi

• Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?
  di: Chen, Xi, et al.
  Pubblicazione: (2024)
• DeepFaith: A Domain-Free and Model-Agnostic Unified Framework for Highly Faithful Explanations
  di: Guo, Yuhan, et al.
  Pubblicazione: (2025)
• DREAM: Domain-agnostic Reverse Engineering Attributes of Black-box Model
  di: Li, Rongqing, et al.
  Pubblicazione: (2024)
• Macformer: Transformer with Random Maclaurin Feature Attention
  di: Guo, Yuhan, et al.
  Pubblicazione: (2024)
• DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization
  di: Lee, Dongyeun, et al.
  Pubblicazione: (2025)