DLLMQuant: Quantizing Diffusion-based Large Language Models

• URL: http://arxiv.org/abs/2508.14090v2
• Date: Tue, 26 Aug 2025 02:18:25 GMT
• Title: DLLMQuant: Quantizing Diffusion-based Large Language Models
• Authors: Chen Xu, Dawei Yang,
• Abstract summary: Diffusion-based large language models (Ms) have shown promise for non-autoregressive text generation.<n>Post-training quantization (PTQ) suffers from severe accuracy degradation and reduced performance when applied to allocateMs.<n>We proposeMQuant, a PTQ framework tailored forMs, which incorporates three novel techniques.
• Score: 15.318057331535982
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• SPEED-Q: Staged Processing with Enhanced Distillation towards Efficient Low-bit On-device VLM Quantization [6.872509247180761]
  Vision-Language Models (VLMs) are crucial for enabling low-latency and privacy-preserving intelligent applications.<n>We propose SPEED-Q, a novel framework for low-bit weight-only quantization of VLM models.<n>Speedy-Q achieves up to 6x higher accuracy than existing quantization methods under 2-bit settings.
  arXiv  Detail & Related papers  (2025-11-12T02:47:24Z)
• Quant-dLLM: Post-Training Extreme Low-Bit Quantization for Diffusion Large Language Models [47.41616630151171]
  Diffusion large language models (dLLMs) offer bidirectional context and flexible masked-denoising generation.<n>We propose Quant-dLLM, an ultra-lowbit PTQ framework tailored to dLLMs.<n> Quant-dLLM consistently achieves higher accuracy than state-of-the-art (SOTA) AR-transfer PTQ methods on dLLMs.
  arXiv  Detail & Related papers  (2025-09-27T13:50:42Z)
• LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Text-to-Image Generation [34.14174796390669]
  Post-training quantization (PTQ) is a promising solution to reduce memory usage and accelerate inference.<n>Existing PTQ methods suffer from severe performance degradation under extreme low-bit settings.<n>We propose LRQ-DiT, an efficient and accurate PTQ framework.
  arXiv  Detail & Related papers  (2025-08-05T14:16:11Z)
• Accelerating Diffusion LLMs via Adaptive Parallel Decoding [60.407727995313074]
  We introduce adaptive parallel decoding (APD), a novel method that dynamically adjusts the number of tokens sampled in parallel.<n>APD provides markedly higher throughput with minimal quality degradations on downstream benchmarks.
  arXiv  Detail & Related papers  (2025-05-31T06:10:10Z)
• Quantizing Large Language Models for Code Generation: A Differentiated Replication [51.85505914274633]
  Large Language Models (LLMs) have shown an impressive capability in code generation and, specifically, to automatically implement requirements described in natural language.<n>LLMs pose significant challenges related to their memory (and, consequently, carbon) footprint.<n>New frontier for LLM quantization is 4-bit precision, resulting in an average memory footprint reduction of 70%.
  arXiv  Detail & Related papers  (2025-03-10T09:26:08Z)
• RSQ: Learning from Important Tokens Leads to Better Quantized LLMs [65.5558181902098]
  Layer-wise quantization is a key technique for efficiently compressing large models without expensive retraining.<n>We propose RSQ (Rotate, Scale, then Quantize), which applies rotations to the model to mitigate outliers.<n>We demonstrate that RSQ consistently outperforms baseline methods across multiple downstream tasks and three model families.
  arXiv  Detail & Related papers  (2025-03-03T18:46:33Z)
• MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization [15.01214559812713]
  MQuant is a post-training quantization framework designed to tackle the challenges of multimodal large language models (MLLMs)<n>On five mainstream MLLMs, MQuant under W4A8 achieves near-floating-point accuracy while reducing inference latency by up to 30%.<n>Our MQuant effectively bridges the gap for efficient and accurate MLLMs inference in resource-constrained devices.
  arXiv  Detail & Related papers  (2025-02-01T13:08:02Z)
• SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models [63.118592279833656]
  Post-training quantization (PTQ) is an effective technique for compressing large language models (LLMs)<n>We propose SliM-LLM, a salience-driven mixed-precision quantization framework that allocates bit-widths at the group-wise.<n> Experiments show that SliM-LLM achieves superior performance across various LLMs at low bit-widths.
  arXiv  Detail & Related papers  (2024-05-23T16:21:48Z)
• CBQ: Cross-Block Quantization for Large Language Models [66.82132832702895]
  Post-training quantization (PTQ) has played a key role in compressing large language models (LLMs) with ultra-low costs.<n>We propose CBQ, a cross-block reconstruction-based PTQ method for LLMs.<n> CBQ employs a cross-block dependency using a reconstruction scheme, establishing long-range dependencies across multiple blocks to minimize error accumulation.
  arXiv  Detail & Related papers  (2023-12-13T07:56:27Z)
• Norm Tweaking: High-performance Low-bit Quantization of Large Language Models [21.855106896725598]
  We introduce a technique called norm tweaking, which can be used as a plugin in current PTQ methods to achieve high precision. Our method demonstrates significant improvements in both weight-only quantization and joint quantization of weights and activations. Our simple and effective approach makes it more practical for real-world applications.
  arXiv  Detail & Related papers  (2023-09-06T06:51:15Z)
• SqueezeLLM: Dense-and-Sparse Quantization [80.32162537942138]
  Main bottleneck for generative inference with LLMs is memory bandwidth, rather than compute, for single batch inference. We introduce SqueezeLLM, a post-training quantization framework that enables lossless compression to ultra-low precisions of up to 3-bit. Our framework incorporates two novel ideas: (i) sensitivity-based non-uniform quantization, which searches for the optimal bit precision assignment based on second-order information; and (ii) the Dense-and-Sparse decomposition that stores outliers and sensitive weight values in an efficient sparse format.
  arXiv  Detail & Related papers  (2023-06-13T08:57:54Z)
• Mixed Precision Low-bit Quantization of Neural Network Language Models for Speech Recognition [67.95996816744251]
  State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Current quantization methods are based on uniform precision and fail to account for the varying performance sensitivity at different parts of LMs to quantization errors. Novel mixed precision neural network LM quantization methods are proposed in this paper.
  arXiv  Detail & Related papers  (2021-11-29T12:24:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.