ASER: Activation Smoothing and Error Reconstruction for Large Language Model Quantization

Ähnliche Einträge

• Saliency-Aware Regularized Quantization Calibration for Large Language Models
  von: Zhao, Yanlong, et al.
  Veröffentlicht: (2026)
• Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs
  von: Cho, Yoonjun, et al.
  Veröffentlicht: (2026)
• Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models
  von: Zhang, Zhengxin, et al.
  Veröffentlicht: (2024)
• SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
  von: Xiao, Guangxuan, et al.
  Veröffentlicht: (2022)
• BiSup: Bidirectional Quantization Error Suppression for Large Language Models
  von: Zou, Minghui, et al.
  Veröffentlicht: (2024)