C-PTQ: Fisher-weighted Channel-wise Sensitivity for Post-training Quantization of MLLMs

• URL: http://arxiv.org/abs/2607.21076v1
• Date: Thu, 23 Jul 2026 09:08:57 GMT
• Title: C-PTQ: Fisher-weighted Channel-wise Sensitivity for Post-training Quantization of MLLMs
• Abstract summary: Multimodal large language models (MLLMs) require huge memory and computational costs.<n>Post-training quantization (PTQ) techniques offer an efficient solution for model compression and inference acceleration.<n>We propose C-PTQ, a unified channel-wise PTQ method that harmonizes task-specific loss perturbation and quantization error.
• Score: 23.275426637407033
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal large language models (MLLMs) require huge memory and computational costs, which limits their practical deployment. Post-training quantization (PTQ) techniques offer an efficient solution for model compression and inference acceleration. Yet, the quantized model faces performance degradation due to outlier channels, which are highly sensitive to quantization and substantially impair activation fidelity and task accuracy. To protect these salient channels during quantization, existing PTQ methods leverage modality- or token-level metrics to guide channel-wise scaling (CWS) of LLM decoders. However, these orthogonal measurements fail to capture channel-wise impacts on task-specific loss, and the misalignment between importance and scaling factors ultimately leads to suboptimal performance. To address this issue, we propose C-PTQ, a unified channel-wise PTQ method that harmonizes task-specific loss perturbation and quantization error. Motivated by second-order derivatives, we design a Fisher-weighted objective as a tractable Hessian approximation, seamlessly injecting task sensitivity into the scaling process. Notably, we achieve state-of-the-art performance without auxiliary modules like LoRA, thereby maintaining high efficiency. Experiments on Qwen2.5VL, InternVL2 and LLaVA-OV across 8 benchmarks demonstrate our effectiveness in both weight-only and weight-activation settings.

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)
• Spike-driven Large Language Model [49.52947423982696]
  Spiking Neural Networks (SNNs) possess spike-driven characteristics.<n>Current Large Language Models (LLMs) are primarily based on large-scale dense matrix multiplications.<n>We propose SDLLM, a spike-driven large language model that eliminates dense matrix multiplications through sparse addition operations.
  arXiv  Detail & Related papers  (2026-04-11T17:58:35Z)
• LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution [52.627063566555194]
  We introduce LSGQuant, a layer-sensitivity guided quantizing approach for one-step diffusion-based real-world VSR.<n>Our method incorporates a Dynamic Range Adaptive Quantizer (DRAQ) to fit video token activations.<n>Our method has nearly performance to origin model with full-precision and significantly exceeds existing quantization techniques.
  arXiv  Detail & Related papers  (2026-02-03T06:53:19Z)
• End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost [53.25965863436039]
  Quantization-aware training (QAT) provides a more principled solution, but its reliance on backpropagation incurs prohibitive memory costs.<n>We propose ZeroQAT, a zeroth-order optimization-based QAT framework that supports both weight and activation quantization.<n>Experiments show that ZeroQAT consistently outperforms representative PTQ and QAT baselines while requiring significantly less memory.
  arXiv  Detail & Related papers  (2025-08-21T01:18:27Z)
• 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)
• KLLM: Fast LLM Inference with K-Means Quantization [6.266554375328823]
  We propose KLLM, an inference accelerator for efficient execution with K-Means-quantized weights and activations.<n> KLLM features an index-based computation scheme for efficient execution of MatMuls and nonlinear operations on K-Means-quantized data.
  arXiv  Detail & Related papers  (2025-07-30T19:01:25Z)
• DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization [29.066284789131494]
  Recent post-training quantization methods overlook outliers, leading to degraded performance at low bit-widths.<n>We propose a DMQ which combines Learned Equivalent Scaling and channel-wise Power-of-Two Scaling.<n>Our method significantly outperforms existing works, especially at low bit-widths.
  arXiv  Detail & Related papers  (2025-07-17T09:15:29Z)
• FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation [55.12070409045766]
  Post-training quantization (PTQ) has stood out as a cost-effective and promising model compression paradigm in recent years.<n>Current PTQ methods for Vision Transformers (ViTs) still suffer from significant accuracy degradation, especially under low-bit quantization.
  arXiv  Detail & Related papers  (2025-06-13T07:57:38Z)
• RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models [53.571195477043496]
  We propose an algorithm named Rotated Straight-Through-Estimator (RoSTE)<n>RoSTE combines quantization-aware supervised fine-tuning (QA-SFT) with an adaptive rotation strategy to reduce activation outliers.<n>Our findings reveal that the prediction error is directly proportional to the quantization error of the converged weights, which can be effectively managed through an optimized rotation configuration.
  arXiv  Detail & Related papers  (2025-02-13T06:44:33Z)
• DopQ-ViT: Towards Distribution-Friendly and Outlier-Aware Post-Training Quantization for Vision Transformers [31.791935689364866]
  We propose DopQ-ViT, a Distribution-friendly and Outlier-aware Post-training Quantization method for Vision Transformers (ViTs)<n>First, DopQ-ViT introduces the Tan Quantizer (TanQ), which better preserves the power-law distribution of post-Softmax activations by focusing more on values near 1.<n>Second, DopQ-ViT presents the MAD-guided Optimal Scaling Factor (MOSF), which selects the optimal scaling factor without introducing additional calculations.
  arXiv  Detail & Related papers  (2024-08-06T16:40:04Z)
• PikeLPN: Mitigating Overlooked Inefficiencies of Low-Precision Neural Networks [4.827161693957252]
  Non-quantized elementwise operations dominate the inference cost of low-precision models. PikeLPN model addresses these issues by applying quantization to both elementwise operations and multiply-accumulate operations.
  arXiv  Detail & Related papers  (2024-03-29T18:23:34Z)
• QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning [52.157939524815866]
  In this paper, we identify imbalanced activation distributions as a primary source of quantization difficulty.<n>We propose to adjust these distributions through weight finetuning to be more quantization-friendly.<n>Our method demonstrates its efficacy across three high-resolution image generation tasks.
  arXiv  Detail & Related papers  (2024-02-06T03:39:44Z)
• QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models [44.515165695546614]
  Quantization-Aware Training (QAT) offers a solution, but its extensive training costs make Post-Training Quantization (PTQ) a more practical approach for Large Language Models (LLMs) We propose QLLM, an accurate and efficient low-bitwidth PTQ method designed for LLMs.
  arXiv  Detail & Related papers  (2023-10-12T05:25:49Z)

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.