GPTQ-intrinsic LoRA: A Near-optimal Algorithm for Low-precision Quantization with Low-rank Adaptation

Documenti analoghi

• Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks
  di: Zhang, Shihao, et al.
  Pubblicazione: (2025)
• The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm
  di: Chen, Jiale, et al.
  Pubblicazione: (2025)
• Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos
  di: Zhang, Haoyu, et al.
  Pubblicazione: (2025)
• Beacon: Post-Training Quantization with Integrated Grid Selection
  di: Zhang, Shihao, et al.
  Pubblicazione: (2025)
• FedLoDrop: Federated LoRA with Dropout for Generalized LLM Fine-tuning
  di: Xie, Sijing, et al.
  Pubblicazione: (2025)