mlsanityData to 7 Oct 2026

LPCD: Unified Framework from Layer-Wise to Submodule Quantization

arXiv 2512.01546 ↗First posted 1 Dec 2025stat.ML cs.AI cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Post-training quantization (PTQ) aims to preserve model-level behavior; however, most methods focus on individual linear layers. Even recent extensions, such as QEP and LoaQ, which mitigate error propagation or target specific submodules, still rely on layer-wise formulations and fail to capture the behavior of larger submodules. We introduce Layer-Projected Coordinate Descent (LPCD), a unified framework that extends PTQ beyond layers by optimizing relaxed objectives across arbitrary submodules and projecting the solutions with layer-wise quantizers. LPCD generalizes existing methods and provides a principled approach to quantizing complex submodules while maintaining the efficiency and compatibility of layer-wise PTQ pipelines. Across diverse LLM architectures and bit-widths, LPCD-based submodule quantization consistently enhances both layer-wise PTQ methods and existing submodule approaches.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 18 of its 27 references that are in the map. First posted on arXiv 1 Dec 2025.

Builds on

18 of 27 references.

References · 18

  1. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
  2. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  3. 2022GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformerscited by 1,838
  4. 2023AWQ: Activation-aware Weight Quantization for LLM Compression and Accelerationcited by 1,234
  5. 2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 791
  6. 2024QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMscited by 598
  7. 2022ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformerscited by 517
  8. 2024SpinQuant: LLM quantization with learned rotationscited by 446
  9. 2023QuIP: 2-Bit Quantization of Large Language Models With Guaranteescited by 397
  10. 2023SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compressioncited by 359
  11. 2024QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebookscited by 354
  12. 2022The case for 4-bit precision: k-bit Inference Scaling Lawscited by 247
6 more
  1. 2024Extreme Compression of Large Language Models via Additive Quantizationcited by 223
  2. 2024PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compressioncited by 59
  3. 2025Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantizationcited by 36
  4. 2023QuantEase: Optimization-based Quantization for Language Modelscited by 28
  5. 2025Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantizationcited by 24
  6. 2025LoaQ: Layer-wise Output Approximation Quantizationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantizationcited by 3
  2. 2026OneComp: One-Line Revolution for Generative AI Model Compressioncited by 3
  3. 2026A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challengescited by 2
  4. 2026Signs Beat Floats: Low-Rank Double-Binary Adaptation for On-Device Fine-Tuningcited by 0
  5. 2026From Sweep to Seam: Interleaved Cross-Block Post-Training Quantizationcited by 0
  6. 2026SchurQuant: Groupwise Discrete Optimization for Layer-Wise LLM Quantizationcited by 0