SignRoundV2: Toward Closing the Performance Gap in Extremely Low-Bit Post-Training Quantization for LLMs

Ähnliche Einträge

• Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs
  von: Cheng, Wenhua, et al.
  Veröffentlicht: (2023)
• Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens
  von: Ouyang, Xu, et al.
  Veröffentlicht: (2024)
• Efficient Post-training Quantization with FP8 Formats
  von: Shen, Haihao, et al.
  Veröffentlicht: (2023)
• OneBit: Towards Extremely Low-bit Large Language Models
  von: Xu, Yuzhuang, et al.
  Veröffentlicht: (2024)
• What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study
  von: Lv, Keyu, et al.
  Veröffentlicht: (2026)