Qrazor: Reliable and Effortless 4-bit LLM Quantization by Significant Data Razoring

Documenti analoghi

• SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization
  di: Park, Yeonsik, et al.
  Pubblicazione: (2026)
• LO-BCQ: Block Clustered Quantization for 4-bit (W4A4) LLM Inference
  di: Elangovan, Reena, et al.
  Pubblicazione: (2025)
• Atom: Low-bit Quantization for Efficient and Accurate LLM Serving
  di: Zhao, Yilong, et al.
  Pubblicazione: (2023)
• Post-Training Quantization via Residual Truncation and Zero Suppression for Diffusion Models
  di: Kim, Donghoon, et al.
  Pubblicazione: (2025)
• SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training
  di: Jia, Jinda, et al.
  Pubblicazione: (2024)