# DLLMQuant: Quantizing Diffusion-based Large Language Models

arXiv: https://arxiv.org/abs/2508.14090 · HTML: https://mlsanity.com/paper/2508.14090/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2025.

## Built on by (most cited first, 11 of 11)

- [dParallel: Learnable Parallel Decoding for dLLMs](https://mlsanity.com/paper/2509.26488/) (2025)
- [Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs](https://mlsanity.com/paper/2508.14896/) (2025)
- [DMax: Aggressive Parallel Decoding for dLLMs](https://mlsanity.com/paper/2604.08302/) (2026)
- [R2-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction](https://mlsanity.com/paper/2604.18995/) (2026)
- [FreeAct: Freeing Activations for LLM Quantization](https://mlsanity.com/paper/2603.01776/) (2026)
- [Window-Diffusion: Accelerating Diffusion Language Model Inference with Windowed Token Pruning and Caching](https://mlsanity.com/paper/2601.20332/) (2026)
- [Layer Collapse in Diffusion Language Models](https://mlsanity.com/paper/2605.06366/) (2026)
- [Neural Weight Compression for Language Models](https://mlsanity.com/paper/2510.11234/) (2025)
- [Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques](https://mlsanity.com/paper/2607.12829/) (2026)
- [Preserving Mathematical Reasoning in Compressed Diffusion Language Models via Trajectory-Aware Low-Rank Approximation](https://mlsanity.com/paper/2610.03326/) (2026)
- [SoloQ: Calibration-Free Quantization for Diffusion Language Models](https://mlsanity.com/paper/2610.07121/) (2026)

## Abstract (arXiv)

Diffusion-based large language models (DLLMs) have shown promise for non-autoregressive text generation, but their deployment is constrained by large model sizes and heavy computational costs. Post-training quantization (PTQ), a widely used method for compressing and accelerating Large Language Models (LLMs), suffers from severe accuracy degradation and reduced generalization performance when directly applied to DLLMs (e.g., AWQ suffers a 16% accuracy drop on LLADA under W4A4). This paper explores how DLLMs' key mechanisms - dynamic masking, iterative generation, bidirectional attention - clash with quantization. We identify three core issues: 1) Iterative generation and dynamic masking ratios lead to distinct token distributions across decoding steps, which are not adequately captured by existing PTQ calibration methods; 2) Quantization errors are accumulated and amplified progressively during iteration in DLLMs, causing quantized models to perform worse as decoding steps progress; 3) Unmasked tokens stabilize while masked remain probabilistic, making overall feature distribution incompatible with existing PTQ methods. To address these issues, we propose DLLMQuant, a PTQ framework tailored for DLLMs, which incorporates three novel techniques: 1) Temporal-Mask Adaptive Sampling (TMAS), a calibration method that accounts for both time and mask factors, with the capacity to capture distributions across timesteps. 2) Interaction-Aware Activation Quantization (IA-AQ), which utilizes bidirectional attention's interaction signals to dynamically allocate quantization resources. 3) Certainty-Guided Quantization (CGQ), which integrates mask status and token scores as key weighting criteria into error compensation, making weight quantization more suitable for DLLMs. Experiments show that DLLMQuant achieves significant performance gains while enhancing efficiency.