QQQ: Quality Quattuor-Bit Quantization for Large Language Models

Documenti analoghi

• First Activations Matter: Training-Free Methods for Dynamic Activation in Large Language Models
  di: Ma, Chi, et al.
  Pubblicazione: (2024)
• Re-evaluating the Memory-balanced Pipeline Parallelism: BPipe
  di: Huang, Mincong, et al.
  Pubblicazione: (2024)
• Dynamic Activation Pitfalls in LLaMA Models: An Empirical Study
  di: Ma, Chi, et al.
  Pubblicazione: (2024)
• BAQ: Efficient Bit Allocation Quantization for Large Language Models
  di: Zhang, Chao, et al.
  Pubblicazione: (2025)
• MOYU: A Theoretical Study on Massive Over-activation Yielded Uplifts in LLMs
  di: Ma, Chi, et al.
  Pubblicazione: (2024)