🛰️ Daily AI Frontier
‹ back to 2026-08-10

ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization

Research Efficiency & Systems

Ranking

Overall 70
Content 80
Popularity 46

Observed public metrics from 1 member.

Merged summary

TL;DR - ReQuant is a backpropagation-free refinement stage that keeps post-training-quantized LLM weights improvable after quantization, iteratively revisiting discrete weight assignments on the fixed quantization grid. It matters because it plugs into any existing PTQ pipeline to recover accuracy without changing the deployed quantized format.

  • Treats PTQ output as a feasible starting point rather than a final answer: it iteratively revisits integer weight assignments, accepting only updates that strictly reduce mean squared reconstruction error and stay on the original grid.
  • Initializer-agnostic and plug-and-play — no backpropagation required, and the quantized format is preserved, so refined models remain directly executable.
  • Reported gains hold across model families, bit-widths, and downstream tasks, with the largest improvements on simple initializers and lower bit-widths.
  • Notably, repeated sweeps can lift plain round-to-nearest initialization to approach or surpass GPTAQ under the same quantization format.

Sources (1)

ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization

arXiv cs.AI Yongge Ma, Guoan Wang, Feiyu Wang, Yaoming Li, Qian Zhang, Zihan Yan, Yinjun Han, Tong Yang 2026-08-07 arXiv:2608.07019
Public signals Hugging Face upvotes 0
Providers: Hugging Face · Upvotes 0 OpenAlex · N/A Publisher · N/A Semantic Scholar · N/A X · N/A Fetched 2026-09-09 08:18:14.250962 UTC

TL;DR - ReQuant is a backpropagation-free refinement stage that keeps post-training-quantized LLM weights improvable after quantization, iteratively revisiting discrete weight assignments on the fixed quantization grid. It matters because it plugs into any existing PTQ pipeline to recover accuracy without changing the deployed quantized format.

  • Treats PTQ output as a feasible starting point rather than a final answer: it iteratively revisits integer weight assignments, accepting only updates that strictly reduce mean squared reconstruction error and stay on the original grid.
  • Initializer-agnostic and plug-and-play — no backpropagation required, and the quantized format is preserved, so refined models remain directly executable.
  • Reported gains hold across model families, bit-widths, and downstream tasks, with the largest improvements on simple initializers and lower bit-widths.
  • Notably, repeated sweeps can lift plain round-to-nearest initialization to approach or surpass GPTAQ under the same quantization format.
item →