MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference

• URL: http://arxiv.org/abs/2607.17733v1
• Date: Mon, 20 Jul 2026 09:23:10 GMT
• Title: MXSens: Sensitivity-Aware Mixed-Precision Quantization for Efficient LLM Inference
• Abstract summary: We introduce MXSens, a training-free method that assigns mixed mantissa bitwidths based on column- and layer-wise sensitivity.<n> MXSens achieves perplexities of 3.77 and 7.63 on LLaMA-2-70B and LLaMA-3-8B, respectively, substantially improving over existing baselines on WikiText-2.
• Score: 36.01709922688871
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 4-bit quantization enables efficient LLM inference, but suffers from significant accuracy degradation due to outliers. Prior work addresses this problem via data rotation or mixed-precision integer quantization, but often relies on software-managed scaling and frequent dequantization, incurring substantial overhead. Microscaling formats, such as MXINT, eliminate these inefficiencies by encoding scales in hardware, yet remain incompatible with rotation-based methods. Our analysis reveals that outliers vary in severity, from rare extremes to frequent mild deviations, and that quantization sensitivity is unevenly distributed across layers and columns. These insights motivate a fine-grained, sensitivity-guided approach. We introduce MXSens, a training-free method that assigns mixed mantissa bitwidths (4/6/8) based on column- and layer-wise sensitivity, naturally leveraging the block-wise structure of MXINT. MXSens outperforms state-of-the-art quantization methods across a range of models and tasks. Under the W4A4KV4 setting, MXSens achieves perplexities of 3.77 and 7.63 on LLaMA-2-70B and LLaMA-3-8B, respectively, substantially improving over existing baselines on WikiText-2. Our work establishes a new balance between accuracy and resource efficiency for LLM quantization.

Related papers

• Multi-Scale Dequant: Eliminating Dequantization Bottleneck via Activation Decomposition for Efficient LLM Inference [12.249074183271743]
  Quantization is essential for efficient large language model (LLM) inference.<n>Dequantization step-converting low-bit weights back to high-precision for matrix multiplication has become a critical bottleneck on modern AI accelerators.<n>This paper presents Multi-Scale Dequant (MSD), a quantization framework that removes weight/KV dequantization from the GEMM critical path.
  arXiv  Detail & Related papers  (2026-05-13T09:49:56Z)
• SDQ-LLM: Sigma-Delta Quantization for 1-bit LLMs of any size [5.229694155440675]
  Large language models (LLMs) face significant computational and memory challenges.<n>We introduce SDQ-LLM: Sigma-Delta Quantization for 1-bit LLMs of any size.<n>A distinctive feature of SDQ-LLM is the continuous layer of the Over-Sampling Ratio (OSR)
  arXiv  Detail & Related papers  (2025-09-27T14:49:58Z)
• SmoothRot: Combining Channel-Wise Scaling and Rotation for Quantization-Friendly LLMs [0.0]
  We present SmoothRot, a novel post-training quantization technique to enhance the efficiency of 4-bit quantization in Large Language Models (LLMs)<n>Our technique effectively transforms extreme outliers into quantization-friendly activations, significantly improving quantization accuracy.
  arXiv  Detail & Related papers  (2025-06-04T19:07:45Z)
• QUAD: Quantization and Parameter-Efficient Tuning of LLM with Activation Decomposition [21.13478769431063]
  QUAD (Quantization with Activation Decomposition) is a framework leveraging Singular Value Decomposition (SVD) to suppress activation outliers for effective 4-bit quantization.<n>We show QUAD achieves 94% 96% accuracy under W4A4 quantization and 98% accuracy with W4A4/A8 and parameter-efficient fine-tuning for Llama-3 and Qwen-2.5 models.
  arXiv  Detail & Related papers  (2025-03-25T05:03:56Z)
• 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)
• Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference [54.2589824716527]
  Large language models incur substantial computation and memory movement costs due to their large scale. Existing approaches separate outliers and normal values into two matrices or migrate outliers from activations to weights, suffering from high latency or accuracy degradation. We propose Rotated Smooth (RRS), a plug-and-play activation smoother for quantization, consisting of Smooth and Rotation operation. The proposed method outperforms the state-of-the-art method in the LLaMA and Qwen families and improves WikiText-2 perplexity from 57.33 to 6.66 for INT4 inference.
  arXiv  Detail & Related papers  (2024-09-30T14:59:22Z)
• I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models [20.070306492164427]
  Post-training quantization serves as a potent technique to accelerate the inference of large language models. Existing works still necessitate a considerable number of floating-point (FP) operations during inference. This limitation hinders the deployment of large language models on the edge and cloud devices. We propose I-LLM, a novel integer-only fully-quantized PTQ framework tailored for large language models.
  arXiv  Detail & Related papers  (2024-05-28T05:56:11Z)
• 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)
• DB-LLM: Accurate Dual-Binarization for Efficient LLMs [83.70686728471547]
  Large language models (LLMs) have significantly advanced the field of natural language processing. Existing ultra-low-bit quantization always causes severe accuracy drops. We propose a novel Dual-Binarization method for LLMs, namely DB-LLM.
  arXiv  Detail & Related papers  (2024-02-19T09:04:30Z)
• 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.