STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models

• URL: http://arxiv.org/abs/2606.04945v2
• Date: Mon, 08 Jun 2026 08:41:05 GMT
• Title: STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models
• Abstract summary: We propose STaR-Quant, a state-time consistent PTQ framework forDLLMs.<n> STaR-Quant consistently improves low-bit weight-activation quantization over strong PTQ baselines.<n>It delivers up to 1.69x speedup and 3.14x memory saving over FP16 deployment.
• Score: 4.885217497915749
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion large language models (DLLMs) have recently emerged as a promising alternative to autoregressive LLMs by generating text through iterative masked denoising with bidirectional context. However, their large model sizes and iterative denoising process introduce substantial memory and computational overhead, motivating post-training quantization for efficient deployment. In this paper, we identify two key challenges for low-bit DLLM quantization: state-dependent activation disparity and temporal error accumulation. Masked and unmasked tokens exhibit different activation distributions within each denoising step, while quantization errors can accumulate across steps during iterative decoding. To address these challenges, we propose STaR-Quant, a state-time consistent PTQ framework for DLLMs. STaR-Quant introduces State-Guided Activation Transformation (SGAT) to assign masked and unmasked tokens to different activation transformation spaces with a unified static weight-side transformation. It further introduces Temporal Attention Compensation (TAC) to correct the quantized attention representation via a lightweight block-diagonal affine mapping. Experiments on representative DLLMs demonstrate that STaR-Quant consistently improves low-bit weight-activation quantization over strong PTQ baselines, while delivering up to 1.69x speedup and 3.14x memory saving over FP16 deployment.

Related papers

• DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models [61.26694413585136]
  Drift-Aware Post-Training Quantization (DA-PTQ) formulates quantization as a drift-aware optimization problem over sequential decision processes.<n>DA-PTQ significantly reduces kinematic drift and achieves comparable performance to full-precision models under low-bit settings.
  arXiv  Detail & Related papers  (2026-04-13T14:51:43Z)
• DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention [2.7422645382944935]
  We present DyLLM, a training-free inference framework that accelerates decoding by selectively computing only salient tokens.<n>Across diverse reasoning and code-generation benchmarks, DyLLM achieves up to 9.6x higher throughput.
  arXiv  Detail & Related papers  (2026-03-09T07:02:01Z)
• FreeAct: Freeing Activations for LLM Quantization [89.97086263978058]
  Quantization is pivotal for mitigating the significant memory and computational overhead of Large Language Models.<n>FreeAct is a novel quantization framework that relaxes the static one-to-one constraint to accommodate dynamic activation disparities.<n>Experiments across dLLMs and MLLMs demonstrate that FreeAct significantly outperforms baselines, up to 5.3% performance improvement.
  arXiv  Detail & Related papers  (2026-03-02T12:02:17Z)
• STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization [21.93314755695813]
  Quantization is the key method for reducing inference latency, power and memory footprint of generative AI models.<n>We propose textitSequence Transformation and Mixed Precision (STaMP) quantization.
  arXiv  Detail & Related papers  (2025-10-30T17:53:42Z)
• DLLMQuant: Quantizing Diffusion-based Large Language Models [15.318057331535982]
  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.
  arXiv  Detail & Related papers  (2025-08-14T09:30:17Z)
• LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation [41.66473889057111]
  Diffusion Transformers (DiTs) have achieved impressive performance in text-to-image and text-to-video generation.<n>DiTs' high computational cost and large parameter sizes pose significant challenges for usage in resource-constrained scenarios.<n>We propose LRQ-DiT, an efficient and accurate post-training quantization framework for image and video generation.
  arXiv  Detail & Related papers  (2025-08-05T14:16:11Z)
• MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation [74.34220141721231]
  We present MPQ-DMv2, an improved textbfMixed textbfPrecision textbfQuantization framework for extremely low-bit textbfDiffusion textbfModels.
  arXiv  Detail & Related papers  (2025-07-06T08:16:50Z)
• 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)
• Progressive Mixed-Precision Decoding for Efficient LLM Inference [49.05448842542558]
  We introduce Progressive Mixed-Precision Decoding (PMPD) to address the memory-boundedness of decoding.<n>PMPD achieves 1.4$-$12.2$times$ speedup in matrix-vector multiplications over fp16 models.<n>Our approach delivers a throughput gain of 3.8$-$8.0$times$ over fp16 models and up to 1.54$times$ over uniform quantization approaches.
  arXiv  Detail & Related papers  (2024-10-17T11:46:33Z)
• Advancing Multimodal Large Language Models with Quantization-Aware Scale Learning for Efficient Adaptation [70.22782550540714]
  Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW. We introduce a Quantization-aware Scale LeArning method based on multimodal Warmup, termed QSLAW.
  arXiv  Detail & Related papers  (2024-08-07T12:42:09Z)
• WKVQuant: Quantizing Weight and Key/Value Cache for Large Language Models Gains More [55.0856305773081]
  Large Language Models (LLMs) face significant deployment challenges due to their substantial memory requirements and the computational demands of auto-regressive text generation process. This paper addresses these challenges by focusing on the quantization of LLMs, a technique that reduces memory consumption by converting model parameters and activations into low-bit integers.
  arXiv  Detail & Related papers  (2024-02-19T11:33:21Z)
• 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)

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.