# SiLQ: Simple Large Language Model Quantization-Aware Training

arXiv: https://arxiv.org/abs/2507.16933 · HTML: https://mlsanity.com/paper/2507.16933/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 24 references that are in the map.
- First posted on arXiv 22 Jul 2025.

## Builds on (most cited first, 11 of 11)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [DataComp-LM: In search of the next generation of training sets for language models](https://mlsanity.com/paper/2406.11794/) (2024)
- [BitDistiller: Unleashing the Potential of Sub-4-Bit LLMs via Self-Distillation](https://mlsanity.com/paper/2402.10631/) (2024)
- [An empirical study of LLaMA3 quantization: from LLMs to MLLMs](https://mlsanity.com/paper/2404.14047/) (2024)
- [Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler](https://mlsanity.com/paper/2408.13359/) (2024)

## Built on by (most cited first, 2 of 2)

- [A Scalable NorthPole System with End-to-End Vertical Integration for Low-Latency and Energy-Efficient LLM Inference](https://mlsanity.com/paper/2511.15950/) (2025)
- [AtteConDA: Attention-Based Conflict Suppression in Multi-Condition Diffusion Models and Synthetic Data Augmentation](https://mlsanity.com/paper/2605.09425/) (2026)

## Abstract (arXiv)

Large language models can be quantized to reduce inference time latency, model size, and energy consumption, thereby delivering a better user experience at lower cost. A challenge exists to deliver quantized models with minimal loss of accuracy in reasonable time, and in particular to do so without requiring mechanisms incompatible with specialized inference accelerators. Here, we demonstrate a simple, end-to-end quantization-aware training approach that, with an increase in total model training budget of less than 0.1%, outperforms the leading published quantization methods by large margins on several modern benchmarks, with both base and instruct model variants. The approach easily generalizes across different model architectures, can be applied to activations, cache, and weights, and requires the introduction of no additional operations to the model other than the quantization itself.