MicroMix: Efficient Mixed-Precision Quantization with Microscaling Formats for Large Language Models

Ähnliche Einträge

• ARCQuant: Boosting NVFP4 Quantization with Augmented Residual Channels for LLMs
  von: Meng, Haoqian, et al.
  Veröffentlicht: (2026)
• CrossQuant: A Post-Training Quantization Method with Smaller Quantization Kernel for Precise Large Language Model Compression
  von: Liu, Wenyuan, et al.
  Veröffentlicht: (2024)
• Post-Training Quantization of OpenPangu Models for Efficient Deployment on Atlas A2
  von: Luo, Yilun, et al.
  Veröffentlicht: (2025)
• Post Training Quantization of Large Language Models with Microscaling Formats
  von: Sharify, Sayeh, et al.
  Veröffentlicht: (2024)
• Mixed-Precision Quantization for Language Models: Techniques and Prospects
  von: Rakka, Mariam, et al.
  Veröffentlicht: (2025)