A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Models

• URL: http://arxiv.org/abs/2608.26926v1
• Date: Thu, 27 Aug 2026 10:23:01 GMT
• Title: A Layer Importance Metric for Quantization Accounting for the Speed-Quality Trade-off in Autoregressive Models
• Abstract summary: Small language models (sLLMs) are nowadays hosted on devices with limited memory and computational budget.<n>We propose a composite metric that combines information retention (measured in terms of a normalized SQNR-based coefficient) and throughput gains.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Small language models (sLLMs) are nowadays hosted on devices with limited memory and computational budget. In an autoregressive setup, inference is memory-bandwidth bound: uniform quantization is often detrimental to such models, since their architecture has limited redundancies and only a few layers are not very sensitive to lower precision. We propose a composite metric that combines two orthogonal criteria: information retention (measured in terms of a normalized SQNR-based coefficient) and throughput gains (modeled using a roofline-based latency analysis). By profiling Gemma 3 1B, we find that Feed-Forward Network blocks and the embedding matrix are the most promising targets for acceleration. For each candidate, we estimate a normalized quality score based on simulated quantization and a normalized speed score based on roofline modeling with no actual execution needed. We combine the two scores in a composite priority coefficient, allowing us to tune the trade-off between speed and quality as needed. Our metric is general and can be used to prioritize individual blocks, their projection sublayers, or transformer layers as a whole. We evaluate our approach on several model architectures, showing that our estimates have at around 4% prediction error for the accelerated speedup. We find that our method generally allocates more resources to the most expressive layers compared to evolutionary search, specialized accelerators, or Shapley-value-based approaches that require expensive approximate inference. Our analytical approach makes sLLM quantization a predictable engineering task.

Related papers

• Context Features Are Cheap: Rank-Aware Decomposition for Efficient Feature Interaction in Recommender Systems [0.0]
  We present a rank-aware decomposition applicable to the dominant interaction mechanisms in recommender systems.<n>The decomposition moves context-only computation from once-per-candidate to once-per-request, identity-equivalent to the original model.<n> Applied to a production DLRM-style ranker without any architectural change, the decomposition increases per-pod throughput by 87.5%.
  arXiv  Detail & Related papers  (2026-05-24T13:35:36Z)
• A KL Lens on Quantization: Fast, Forward-Only Sensitivity for Mixed-Precision SSM-Transformer Models [9.31160191200499]
  Large Language Models (LLMs) on edge devices face severe computational and memory constraints.<n>We propose a lightweight, backpropagation-free, surrogate-based sensitivity analysis framework to identify hybrid SSM-Transformer components most susceptible to quantization-induced degradation.
  arXiv  Detail & Related papers  (2026-04-15T03:40:30Z)
• QuantVSR: Low-Bit Post-Training Quantization for Real-World Video Super-Resolution [53.13952833016505]
  We propose a low-bit quantization model for real-world video super-resolution (VSR)<n>We use a calibration dataset to measure both spatial and temporal complexity for each layer.<n>We refine the FP and low-bit branches to achieve simultaneous optimization.
  arXiv  Detail & Related papers  (2025-08-06T14:35:59Z)
• 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)
• Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model [0.0]
  Mix-QSAM is a mixed-precision Post-Training Quantization (PTQ) framework for the Segment Anything Model (SAM)<n>We introduce a layer-wise importance score, derived using Kullback-Leibler (KL) divergence, to quantify each layer's contribution to the model's output.<n>We also introduce cross-layer synergy, a novel metric based on causal mutual information, to capture dependencies between adjacent layers.
  arXiv  Detail & Related papers  (2025-05-08T00:08:31Z)
• TFMQ-DM: Temporal Feature Maintenance Quantization for Diffusion Models [52.454274602380124]
  Diffusion models heavily depend on the time-step $t$ to achieve satisfactory multi-round denoising. We propose a Temporal Feature Maintenance Quantization (TFMQ) framework building upon a Temporal Information Block. Powered by the pioneering block design, we devise temporal information aware reconstruction (TIAR) and finite set calibration (FSC) to align the full-precision temporal features.
  arXiv  Detail & Related papers  (2023-11-27T12:59:52Z)
• QuantEase: Optimization-based Quantization for Language Models [17.333778751252392]
  This work introduces Quantization (PTQ) of various quantization layers from recent advances of Large Language Models (LLMs) Our CD-based approach features straightforward updates, relying solely on vector operations. We also explore an outlier approach, allowing for retaining significant weights (outoutliers) with complete precision.
  arXiv  Detail & Related papers  (2023-09-05T01:39:09Z)
• 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)
• Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization [7.392278887917975]
  We propose a mixed-precision post training quantization approach that assigns different numerical precisions to tensors in a network based on their specific needs. Our experiments demonstrate latency reductions compared to a 16-bit baseline of $25.48%$, $21.69%$, and $33.28%$ respectively.
  arXiv  Detail & Related papers  (2023-06-08T02:18:58Z)
• ANNETTE: Accurate Neural Network Execution Time Estimation with Stacked Models [56.21470608621633]
  We propose a time estimation framework to decouple the architectural search from the target hardware. The proposed methodology extracts a set of models from micro- kernel and multi-layer benchmarks and generates a stacked model for mapping and network execution time estimation. We compare estimation accuracy and fidelity of the generated mixed models, statistical models with the roofline model, and a refined roofline model for evaluation.
  arXiv  Detail & Related papers  (2021-05-07T11:39:05Z)
• Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search [112.05977301976613]
  We propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides. We first propose the joint training of architecture and quantization with a shared step size to acquire a large number of quantized models. Then a bit-inheritance scheme is introduced to transfer the quantized models to the lower bit, which further reduces the time cost and improves the quantization accuracy.
  arXiv  Detail & Related papers  (2020-10-09T03:52:16Z)
• APQ: Joint Search for Network Architecture, Pruning and Quantization Policy [49.3037538647714]
  We present APQ for efficient deep learning inference on resource-constrained hardware. Unlike previous methods that separately search the neural architecture, pruning policy, and quantization policy, we optimize them in a joint manner. With the same accuracy, APQ reduces the latency/energy by 2x/1.3x over MobileNetV2+HAQ.
  arXiv  Detail & Related papers  (2020-06-15T16:09:17Z)

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.