OutlierTune: Efficient Channel-Wise Quantization for Large Language Models

Documenti analoghi

• MergeQuant: Accurate 4-bit Static Quantization of Large Language Models by Channel-wise Calibration
  di: Wang, Jinguang, et al.
  Pubblicazione: (2025)
• ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data
  di: Wang, Chengsen, et al.
  Pubblicazione: (2024)
• Gradient Flow of Energy: A General and Efficient Approach for Entity Alignment Decoding
  di: Wang, Yuanyi, et al.
  Pubblicazione: (2024)
• Unlocking the Potential of Linear Networks for Irregular Multivariate Time Series Forecasting
  di: Wang, Chengsen, et al.
  Pubblicazione: (2025)
• Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models
  di: Wang, Huazheng, et al.
  Pubblicazione: (2025)