QuBLAST: A Framework for Quantizing Large Language Models with Block-Level Compression Approach and Activation Scaling Strategy

• URL: http://arxiv.org/abs/2606.04620v1
• Date: Wed, 03 Jun 2026 08:55:59 GMT
• Title: QuBLAST: A Framework for Quantizing Large Language Models with Block-Level Compression Approach and Activation Scaling Strategy
• Abstract summary: QuBLAST is a block-level compression approach with activation scaling strategy for LLMs.<n>It reduces model sizes by 40%-45.2% across different model architectures.<n>It maintains the performance within 5% perplexity increase for the WikiText-2 and WikiText-103 datasets.
• Score: 4.215434651178227
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLMs have become the state-of-the-art algorithms for solving NLP tasks. However, they typically come at huge computational and memory costs, thus making them difficult to deploy on embedded systems. Toward this, state-of-the-art methods typically employ uniform post-training quantization (PTQ) across attention blocks of the network, hence overlooking the potential of applying different quantization levels in the same network. They also employ complex operations to mitigate the negative impact of activation outliers, hence incurring high computational overheads. Moreover, they have not considered evaluation using emerging LLMs with non-conventional attention architectures (e.g., state-space models), which pose different challenges in applying quantization. To address these limitations, we propose QuBLAST, a novel PTQ methodology that employs block-level compression approach with activation scaling strategy for LLMs. Block-level compression approach enables mixed-precision quantization across blocks of the network, while activation scaling strategy efficiently mitigates the negative impact of activation outliers. Specifically, QuBLAST first analyzes the sensitivity of different attention blocks in the pre-trained model through the cross-entropy loss analysis. QuBLAST leverages this sensitivity analysis to determine the weight quantization level for each attention block in the model. Furthermore, QuBLAST employs the activation scaling map for each block to control the range of activation values and mitigate the negative impact of activation outliers, thereby enabling better quantization results. Experimental results show that, QuBLAST reduces model sizes by 40%-45.2% across different model architectures (i.e., Qwen3-8B, Llama3-8B, Mistral v0.1-8B, and Falcon H1R-7B), while maintaining the performance within 5% perplexity increase for the WikiText-2 and WikiText-103 datasets.

Related papers

• Breaking the Rounding Trap: Securing LLMs against Quantization-Conditioned Backdoors [11.27557330957057]
  Model quantization is a key technique for reducing storage and inference costs when deploying large language models in practice.<n>Recent studies show that the discretization and rounding errors introduced by quantization can be exploited by adversaries to construct quantization-conditioned backdoor attacks.<n>We propose a proactive pre-quantization defense method, QuantGuard. Our method introduces differentiable rounding control variables and combines error-guided rounding reversal constraints, output-distribution consistency, and weight-distance regularization to finely regulate critical rounding behaviors.
  arXiv  Detail & Related papers  (2026-06-28T07:06:46Z)
• OffQ: Taming Structured Outliers in LLM Quantization by Offsetting [46.325071880831445]
  OffQ mitigates activation outliers in low-bit quantization through a novel offsetting mechanism.<n>OffQ consistently improves model accuracy while preserving low-bit efficiency.
  arXiv  Detail & Related papers  (2026-06-05T10:11:34Z)
• LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs [52.1276403258812]
  We introduce Logit-aware Final-block Quantization (LFQ), a simple yet effective enhancement to block-wise PTQ.<n>LFQ consistently improves the accuracy of complex generation tasks over state-of-the-art block-wise PTQ.
  arXiv  Detail & Related papers  (2026-05-28T11:02:23Z)
• Fine-Grained Post-Training Quantization for Large Vision Language Models with Quantization-Aware Integrated Gradients [36.01708036519368]
  Large Vision Language Models (LVLMs) have achieved remarkable success in a range of downstream tasks that require multimodal interaction.<n>Existing LVLM quantization methods measure token sensitivity at the modality level, which fails to capture the complex cross-token interactions.<n>Inspired by axiomatic attribution in mechanistic interpretability, we introduce a fine-grained quantization strategy on Quantization-aware Integrated Gradients (QIG)<n>Our method improves the average accuracy of LLaVA-onevision-7B by 1.60%, reducing the gap to its full-precision counterpart to only 1.33%.
  arXiv  Detail & Related papers  (2026-03-18T15:03:43Z)
• Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs [78.09559830840595]
  We present the first systematic study on quantizing diffusion-based language models.<n>We identify the presence of activation outliers, characterized by abnormally large activation values.<n>We implement state-of-the-art PTQ methods and conduct a comprehensive evaluation.
  arXiv  Detail & Related papers  (2025-08-20T17:59:51Z)
• 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)
• Interactions Across Blocks in Post-Training Quantization of Large Language Models [34.32577674735222]
  Post-training quantization is widely employed to reduce the computational demands of neural networks. We introduce two multi-block fine-tuning strategies and compare them against the baseline of fine-tuning single transformer blocks. Our findings indicate that the effectiveness of these methods depends on the specific network model.
  arXiv  Detail & Related papers  (2024-11-06T14:11:39Z)
• Q-VLM: Post-training Quantization for Large Vision-Language Models [73.19871905102545]
  We propose a post-training quantization framework of large vision-language models (LVLMs) for efficient multi-modal inference.<n>We mine the cross-layer dependency that significantly influences discretization errors of the entire vision-language model, and embed this dependency into optimal quantization strategy.<n> Experimental results demonstrate that our method compresses the memory by 2.78x and increase generate speed by 1.44x about 13B LLaVA model without performance degradation.
  arXiv  Detail & Related papers  (2024-10-10T17:02:48Z)
• ApiQ: Finetuning of 2-Bit Quantized Large Language Model [12.328293460903911]
  ApiQ is designed to restore the lost information from quantization by concurrently initializing the LoRA components and quantizing the weights of LLMs. It consistently achieves superior finetuning results across various bit-widths.
  arXiv  Detail & Related papers  (2024-02-07T09:36:54Z)
• 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)
• BiTAT: Neural Network Binarization with Task-dependent Aggregated Transformation [116.26521375592759]
  Quantization aims to transform high-precision weights and activations of a given neural network into low-precision weights/activations for reduced memory usage and computation. Extreme quantization (1-bit weight/1-bit activations) of compactly-designed backbone architectures results in severe performance degeneration. This paper proposes a novel Quantization-Aware Training (QAT) method that can effectively alleviate performance degeneration.
  arXiv  Detail & Related papers  (2022-07-04T13:25:49Z)

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.