EfficientQAT: Efficient Quantization-Aware Training for Large Language Models

Documenti analoghi

• BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
  di: Xu, Peng, et al.
  Pubblicazione: (2024)
• OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
  di: Shao, Wenqi, et al.
  Pubblicazione: (2023)
• PrefixQuant: Eliminating Outliers by Prefixed Tokens for Large Language Models Quantization
  di: Chen, Mengzhao, et al.
  Pubblicazione: (2024)
• Optimizing Large Language Models through Quantization: A Comparative Analysis of PTQ and QAT Techniques
  di: Hasan, Jahid
  Pubblicazione: (2024)
• Attn-QAT: 4-Bit Attention With Quantization-Aware Training
  di: Zhang, Peiyuan, et al.
  Pubblicazione: (2026)