GPTQ-2D: Cubic-Time Two-Sided Adaptive Rounding
Not on the map. Why?
Abstract (arXiv)
Adaptive rounding methods such as GPTQ, or equivalently Babai's nearest plane algorithm, round a real matrix to integers under a quadratic metric. They process the entries in a fixed order, one at a time, propagating each rounding error to the entries not yet processed through a triangular feedback matrix. We study the two-sided version of this task, in which fixed nonsingular basis matrices act on both the left and the right of the residual; the familiar one-sided case is the special case of an identity right basis. Vectorizing the matrix turns the two-sided objective into a quadratic metric whose Gram matrix is a Kronecker product, so the one-dimensional algorithm applies verbatim, but takes quartic time in the matrix dimension. We present GPTQ-2D, which produces the identical rounded matrix in cubic time. It rounds the entries anti-diagonal by anti-diagonal; entries on the same anti-diagonal are independent and are rounded in parallel.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 5 of its 9 references that are in the map. First posted on arXiv 29 Jul 2026.
Builds on
5 of 9 references.
References · 5
- 2023QuIP: 2-Bit Quantization of Large Language Models With Guaranteescited by 397
- 2022Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruningcited by 317
- 2025Model-Preserving Adaptive Roundingcited by 20
- 2025The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithmcited by 18
- 2025The Lattice Geometry of Neural Network Quantization -- A Short Equivalence Proof of GPTQ and Babai's Algorithmcited by 7
Built on by
Citing papers per year: 2026: 2.
2 papers.