Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression

• URL: http://arxiv.org/abs/2504.07389v2
• Date: Thu, 17 Jul 2025 13:24:18 GMT
• Title: Task-Circuit Quantization: Leveraging Knowledge Localization and Interpretability for Compression
• Authors: Hanqi Xiao, Yi-Lin Sung, Elias Stengel-Eskin, Mohit Bansal,
• Abstract summary: Post-training quantization (PTQ) reduces a model's memory footprint by mapping full precision weights into low bit weights without costly retraining.<n>We develop a new mixed-precision PTQ approach, Task-Circuit Quantization (TaCQ), that draws parallels to automated circuit discovery.
• Score: 55.323397702682506
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Post-training quantization (PTQ) reduces a model's memory footprint by mapping full precision weights into low bit weights without costly retraining, but can degrade its downstream performance especially in low 2- to 3-bit settings. We develop a new mixed-precision PTQ approach, Task-Circuit Quantization (TaCQ), that draws parallels to automated circuit discovery, directly conditioning the quantization process on specific weight circuits -- which we define as sets of weights associated with downstream task performance. These weights are kept as 16-bit weights, while others are quantized, maintaining performance while only adding a marginal memory cost. Specifically, TaCQ contrasts unquantized model weights with a uniformly-quantized model to estimate the expected change in weights due to quantization and uses gradient information to predict the resulting impact on task performance, allowing us to preserve task-specific weights. We compare TaCQ-based quantization to existing mixed-precision quantization methods when conditioning both on general-purpose and task-specific data. Across QA, math reasoning, and text-to-SQL tasks for both Llama-3 and Qwen2.5, we find that TaCQ outperforms baselines using the same calibration data and a lower weight budget, achieving major improvements in the 2 and 3-bit regime. With only 3.1 bits we are able to recover 96% of Llama-3-8B-Instruct's unquantized 16-bit MMLU performance, obtaining a 5.25% absolute improvement over SPQR. We also observe consistently large gains over existing methods in the 2-bit regime, with an average gain of 14.74% over the strongest baseline, SliM-LLM. Moreover, we observe a 7.20% gain without conditioning on specific tasks, showing TaCQ's ability to identify important weights is not limited to task-conditioned settings.

Related papers

• What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study [59.44848132298657]
  Post-training quantization (PTQ) usually comes with the cost of large accuracy drops, especially for reasoning tasks under low-bit settings.<n>In this study, we present a systematic empirical study of quantization-aware training (QAT) for reasoning models.
  arXiv  Detail & Related papers  (2026-01-21T11:22:29Z)
• Intrinsic Structure as a Proxy for Saliency: SVD-Based Weight Preservation for Mixed-Precision Quantization in Large Language Models [0.0]
  Post-Training Quantization (PTQ) addresses this by reducing the precision of model weights, typically to 4-bit or lower.<n>Current state-of-the-art methods rely on calibration data to identify salient weights.<n>We propose a data-free, structure-aware hypothesis: that the weights identified as Principal Components via Singular Value Decomposition (SVD) are intrinsically important to the model's downstream performance.
  arXiv  Detail & Related papers  (2025-12-01T06:58:30Z)
• You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations [7.404908118728373]
  We propose to use hidden representations that encode task-salient signals as a guideline for quantization.<n>This paper compares two new task-aware PTQ methods: Task-Aware Quantization (TAQ), which allocates bitwidths using task-conditioned statistics from hidden activations, and TAQO, which allocates precision based on direct layer sensitivity tests.<n>Across models, TAQ and TAQO outperform the baselines; TAQ leads on Phi-4, while TAQO leads on Llama-3.1, Qwen3, and Qwen2.5.
  arXiv  Detail & Related papers  (2025-11-09T19:58:24Z)
• CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training [73.46600457802693]
  We introduce a new method that counteracts the loss induced by quantization.<n>CAGE significantly improves upon the state-of-theart methods in terms of accuracy, for similar computational cost.<n>For QAT pre-training of Llama models, CAGE matches the accuracy achieved at 4-bits (W4A4) with the prior best method.
  arXiv  Detail & Related papers  (2025-10-21T16:33:57Z)
• PTQAT: A Hybrid Parameter-Efficient Quantization Algorithm for 3D Perception Tasks [9.463776523295303]
  Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) represent two mainstream model quantization approaches.<n>We propose PTQAT, a novel general hybrid quantization algorithm for the efficient deployment of 3D perception networks.
  arXiv  Detail & Related papers  (2025-08-14T11:55:21Z)
• Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models [4.238165821317982]
  LieQ is a metric-driven framework that addresses the challenge of maintaining accuracy in sub-7B models under extreme low-bit compression.<n>Our method introduces three complementary layer-wise diagnostics-Perplexity Drop, Representational Compactness, and Top-k Energy Gain.<n>On Qwen3-4B, LieQ recovers 95.9% of FP16 baseline performance at 2.05-bit quantization, outperforming GPTQ by 19.7% and AWQ by 18.1% on average across seven zero-shot reasoning tasks.
  arXiv  Detail & Related papers  (2025-08-05T11:17:04Z)
• LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning [27.07694377337617]
  Quantization and fine-tuning are crucial for deploying large language models (LLMs) on resource-constrained edge devices.<n> fine-tuning quantized models presents significant challenges, primarily stemming from the mismatch in data types between the low-precision quantized weights and the high-precision adaptation weights.<n>LoTA-QAF is a novel fine-tuning method specifically designed for quantized LLMs.
  arXiv  Detail & Related papers  (2025-05-24T14:47:28Z)
• Pushing the Limits of Low-Bit Optimizers: A Focus on EMA Dynamics [65.37942405146232]
  We present a novel type of overload that carries with extremely lightweight state elements, achieved through ultra-low-precision quantization. The proposed SOLO achieves substantial memory savings (approximately 45 GB when training a 7B model) with minimal accuracy loss.
  arXiv  Detail & Related papers  (2025-05-01T06:47:45Z)
• RSQ: Learning from Important Tokens Leads to Better Quantized LLMs [65.5558181902098]
  Layer-wise quantization is a key technique for efficiently compressing large models without expensive retraining.<n>We propose RSQ (Rotate, Scale, then Quantize), which applies rotations to the model to mitigate outliers.<n>We demonstrate that RSQ consistently outperforms baseline methods across multiple downstream tasks and three model families.
  arXiv  Detail & Related papers  (2025-03-03T18:46:33Z)
• PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language Models [64.84734437930362]
  Large Language Models (LLMs) suffer severe performance degradation when facing extremely low-bit (sub 2-bit) quantization.<n>We propose an extremely low-bit PTQ method called PTQ1.61, which enables weight quantization to 1.61-bit for the first time.<n>Experiments indicate our PTQ1.61 achieves state-of-the-art performance in extremely low-bit quantization.
  arXiv  Detail & Related papers  (2025-02-18T08:04:58Z)
• ParetoQ: Scaling Laws in Extremely Low-bit LLM Quantization [58.84018707089315]
  We present a unified framework for rigorous comparisons across 1-bit, 1.58-bit, 2-bit, 3-bit, and 4-bit quantization settings.<n>We show that ternary, 2-bit, and 3-bit quantization maintains comparable performance in the size-accuracy trade-off.<n>Considering hardware constraints, 2-bit quantization offers promising potential for memory reduction and speedup.
  arXiv  Detail & Related papers  (2025-02-04T18:59:26Z)
• Rethinking Post-Training Quantization: Introducing a Statistical Pre-Calibration Approach [22.25748046511075]
  Post-training Quantization (PTQ) techniques rely on calibration processes to maintain their accuracy. We propose a weight-adaptive PTQ method that can be considered a precursor to calibration-based PTQ methods. We show that our proposed approach can perform on par with most common calibration-based PTQ methods.
  arXiv  Detail & Related papers  (2025-01-15T19:44:15Z)
• SLiM: One-shot Quantization and Sparsity with Low-rank Approximation for LLM Weight Compression [7.6131620435684875]
  SLIM is a new one-shot compression framework that holistically integrates hardware-friendly quantization, sparsity, and low-rank approximation.<n>SLIM improves model accuracy by up to 5.66% (LLaMA-2-7B) for 2:4 sparsity with 4-bit weight quantization, outperforming prior methods.<n>We also propose an optional PEFT recipe that further improves accuracy by up to 1.66% (LLaMA-2-13B) compared to SLIM without fine-tuning.
  arXiv  Detail & Related papers  (2024-10-12T18:36:07Z)
• L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models [5.304907804008533]
  We propose L4Q, a method that integrates Quantization-Aware Training (QAT) with Low-Rank Adaptation (LoRA)<n>By employing a memory-optimized layer design, L4Q significantly reduces QAT's memory overhead, making its training cost comparable to LoRA.<n>Our experiments demonstrate that this combined approach to quantization and fine-tuning achieves superior accuracy.
  arXiv  Detail & Related papers  (2024-02-07T14:35:05Z)
• EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models [21.17675493267517]
  Post-training quantization (PTQ) and quantization-aware training (QAT) are two main approaches to compress and accelerate diffusion models. We introduce a data-free and parameter-efficient fine-tuning framework for low-bit diffusion models, dubbed EfficientDM, to achieve QAT-level performance with PTQ-like efficiency. Our method significantly outperforms previous PTQ-based diffusion models while maintaining similar time and data efficiency.
  arXiv  Detail & Related papers  (2023-10-05T02:51:53Z)
• Norm Tweaking: High-performance Low-bit Quantization of Large Language Models [21.855106896725598]
  We introduce a technique called norm tweaking, which can be used as a plugin in current PTQ methods to achieve high precision. Our method demonstrates significant improvements in both weight-only quantization and joint quantization of weights and activations. Our simple and effective approach makes it more practical for real-world applications.
  arXiv  Detail & Related papers  (2023-09-06T06:51:15Z)
• On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks [52.97107229149988]
  We propose an On-Chip Hardware-Aware Quantization framework, performing hardware-aware mixed-precision quantization on deployed edge devices. For efficiency metrics, we built an On-Chip Quantization Aware pipeline, which allows the quantization process to perceive the actual hardware efficiency of the quantization operator. For accuracy metrics, we propose Mask-Guided Quantization Estimation technology to effectively estimate the accuracy impact of operators in the on-chip scenario.
  arXiv  Detail & Related papers  (2023-09-05T04:39:34Z)
• A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance [49.1574468325115]
  accumulator-aware quantization (A2Q) is a novel weight quantization method designed to train quantized neural networks (QNNs) to avoid overflow during inference. A2Q introduces a unique formulation inspired by weight normalization that constrains the L1-norm of model weights according to accumulator bit width bounds. We show A2Q can train QNNs for low-precision accumulators while maintaining model accuracy competitive with a floating-point baseline.
  arXiv  Detail & Related papers  (2023-08-25T17:28:58Z)
• Weight Re-Mapping for Variational Quantum Algorithms [54.854986762287126]
  We introduce the concept of weight re-mapping for variational quantum circuits (VQCs) We employ seven distinct weight re-mapping functions to assess their impact on eight classification datasets. Our results indicate that weight re-mapping can enhance the convergence speed of the VQC.
  arXiv  Detail & Related papers  (2023-06-09T09:42:21Z)
• Quantization-Guided Training for Compact TinyML Models [8.266286436571887]
  We propose a Quantization Guided Training (QGT) method to guide DNN training towards optimized low-bit-precision targets. QGT uses customized regularization to encourage weight values towards a distribution that maximizes accuracy while reducing quantization errors.
  arXiv  Detail & Related papers  (2021-03-10T18:06:05Z)

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.