Neural Network Quantization

Follow this topic Ask about this topic

Momentum

36 papers in the last four weeks, up 125% on the four weeks before. 0.4% of all new papers.

Jul 13Week of Sep 28

Latest papers 270

May 8, 2026cs.LG

Finer is Better (with the Right Scaling)

Microscaling is a critical technique for preserving the quality of Large Language Models (LLMs) quantized to ultra-low precision formats. Intuitively, finer block sizes should yield lower quantization error; however, a paradox recently identified by Fasoli et al. (2026) demonstrates that standard abs-max scaling can actually result in degraded model quality as block sizes shrink. In this work, we investigate the underlying mechanics of this phenomenon. We demonstrate that this degradation is not an inherent limitation of finer granularity, but is primarily driven by how elements in smaller blocks statistically cluster closer to their local block maximum, interacting poorly with the coarse subnormal E4M3 values used as scaling factors. Specifically, we show that i) preventing the scaling factor from underflowing to zero mitigates errors caused by extreme underflow, ii) targeted algorithmic interventions like the 4-over-6 methodology that give more flexibility to the choice of scaling factor resolve the paradox for larger values, and iii) a brute-force search establishes an optimal baseline, confirming that the theoretical Mean Squared Error (MSE) strictly improves with finer block sizes. Ultimately, our findings highlight a critical insight for hardware-software co-design: the block-size paradox is partially an artifact of naive scale selection. While using hierarchical scaling factors or wider formats like UE5M3 interchangeably resolves much of the quality loss, we found the 4-over-6 scale selection heuristic can even further improve quality, especially for very small block sizes. Consequently, maximizing the performance of next-generation ML accelerators will require treating silicon format specifications and software scaling algorithms as tightly coupled design choices.

Clemens Schaefer, Gil Tabak

Google LLC, Mountain View, Ca

LLM Quantization 4-Bit Quantization Low-Bit Quantization Neural Network Quantization

May 8, 2026cs.LG

Direction-Preserving Number Representations

Low-precision number formats are widely used in modern machine learning systems due to their efficiency. Accurate direction representation is key to the accuracy of vector operations. This work precisely explores the extent to which the direction of a vector can be represented by selecting its scalar elements from a common finite alphabet of a given size. This is standard practice in machine learning, where low-precision significands may be narrow-width floating-point or integer values. A geometric framework is introduced for analyzing the directional coverage of such product-structured codes. This work analytically quantifies the suboptimality gap between such product-structured codes and spherical codes for the vector as a whole, in both low and asymptotically high dimensions. Furthermore, within the product code class, it is proven that the standard formats of two's complement, fixed-point, and floating-point are suboptimal, again with quantified gap, pointing to the potential to develop new scalar number formats. Such scalar alphabets are numerically optimized across multiple block dimensions for directional coverage, including the dimension used in NVIDIA's NVFP4 format. Experimental results are presented comparing the performance of standard formats and the optimized alphabet. We find that for four bits, NVIDIA's choice of E2M1 closely approximates the optimized alphabet, providing a geometric explanation for its strong performance in low-precision machine learning workloads and an analytical understanding of the link between that superiority and block size. We provide open-source formal proofs in Lean for the theorems in this work, along with the experimental code and the optimized alphabets obtained.

Bardia Zadeh, George A. Constantinides

Department of Electrical and Electronic Engineering Imperial College London London, United Kingdom

4-Bit Quantization Low-Bit Quantization Neural Network Quantization

May 8, 2026cs.CV

Amortized-Precision Quantization for Early-Exit Vision Transformers

Vision Transformers (ViTs) achieve strong performance across vision tasks, yet their deployment with low-precision early exiting remains fragile. Existing quantization methods assume static full-depth execution, making them unstable when exit decisions are perturbed by quantization noise, which can amplify errors along dynamic inference paths. In this paper, we introduce Amortized-Precision Quantization (APQ), a utilization-aware formulation that accounts for layer-wise stochastic exposure to quantization noise and reveals depth-precision trade-offs. Building on APQ, we propose Mutual Adaptive Quantization with Early Exiting (MAQEE), a bi-level framework that jointly optimizes exit thresholds and bit-widths under explicit risk control to improve inference stability. MAQEE establishes a superior Pareto frontier in the accuracy-efficiency trade-off, reducing BOPs by up to 95% while maintaining accuracy and outperforming strong baselines by up to 20% across classification, detection, and segmentation tasks.

Rui Fang, Hsi-Wen Chen, Ming-Syan Chen

National Taiwan University

Mixed-Precision Quantization Dynamic Neural Networks Vision Transformer Efficient ViTs Neural Network Quantization Early-Exit Neural Networks

May 7, 2026cs.AR

PoTAcc: A Pipeline for End-to-End Acceleration of Power-of-Two Quantized DNNs

Power-of-two (PoT) quantization significantly reduces the size of deep neural networks (DNNs) and replaces multiplications with bit-shift operations for inference. Prior work has shown that PoT-quantized DNNs can preserve accuracy for tasks such as image classification; however, their performance on resource-constrained edge devices remains insufficiently understood. While general-purpose edge CPUs and GPUs do not provide optimized backends for bit-shift operations, custom hardware accelerators can better exploit PoT quantization by implementing dedicated shift-based processing elements. However, deploying PoT-quantized models on such accelerators is challenging due to limited support in existing inference frameworks. In addition, the impact of different PoT quantization strategies on hardware design, performance, and energy efficiency during full inference has not been systematically explored. To address these challenges, we propose PoTAcc, an open-source end-to-end pipeline for accelerating and evaluating PoT-quantized DNNs on resource-constrained edge devices. PoTAcc enables seamless preparation and deployment of PoT-quantized models via TensorFlow Lite (TFLite) across heterogeneous platforms, including CPU-only systems and hybrid CPU-FPGA systems with custom accelerators. We design shift-based processing element (shift-PE) accelerators for three PoT quantization methods and implement them on two FPGA platforms. We evaluate accuracy, performance, energy efficiency, and resource utilization across a range of models, including CNNs and Transformer-based architectures. Results show that our CPU-accelerator design achieves up to 3.6x speedup and 78% energy reduction compared to CPU-only execution for PoT-quantized DNNs on PYNQ-Z2 and Kria boards. The code will be publicly released at https://github.com/gicLAB/PoTAcc

Rappy Saha, Jude Haris, Nicolas Bohm Agostini +2

Efficient Neural Network Inference FPGA-Based Neural Network Acceleration Neural Network Quantization On-Device Inference

May 7, 2026cs.PF

When Quantization Is Free: An int4 KV Cache That Outruns fp16 on Apple Silicon

KV-cache quantization is framed as a quality--latency trade-off. We show it is \emph{inverted} on Apple Silicon's unified memory: a single fused Metal kernel (sign-randomized FFT

+

per-channel

λ

+

per-group abs-max

+

int4 nibble pack), exposed as a HuggingFace \texttt{Cache} subclass, runs \emph{faster than fp16} across

256

--

4096

-token prefixes on Gemma-3 1B (

-3

to

-8\%

ms/tok) and at short context on Qwen2.5-1.5B (

-0.7

to

-2.6\%

through

1

K), with

3\times

persistent memory compression and quality preserved (

\dPPL = 0.000

Qwen short-prompt;

+3.6

hook

\dPPL

Gemma). The kernel's

\sim\!25

,ns/vec overhead is below the bandwidth savings from

3\times

compression. The fused kernel also closes Qwen's 4-bit per-token catastrophe (

\dPPL = +7975 \to +638.6

,

12.5\times

reduction) at

182

,GFLOPS /

D{=}128

. Supporting findings:

\SRFT

and

\SRHT

are statistically indistinguishable for KV quality (we pick

\SRFT

for mixed-radix and matrix-multiply alignment); a learned-rotation ablation surfaces a regularization role for the fixed random SRFT base (learning

R+λ

without SRFT lowers calibration MSE

84.9\%

vs

50.3\%

but yields worse PPL); Householder rotations at

k{=}d/2

reflectors are effectively lossless at

d{=}256

.

Mohamed Amine Bergach

Illumina, San Diego, CA, USA

GPU Kernel Optimization KV Caching 4-Bit Quantization Rotation-Based Quantization LLM Inference Acceleration Attention Quantization+3

May 7, 2026cs.AI

Saliency-Aware Regularized Quantization Calibration for Large Language Models

Post-training quantization (PTQ) is an effective approach for deploying large language models (LLMs) under memory and latency constraints. Most existing PTQ methods determine quantization parameters by minimizing a layer-wise reconstruction error on a predetermined calibration dataset, typically optimized via either scale search or Gram-based methods. However, from the perspective of generalization risk, existing PTQ calibration objectives based solely on empirical reconstruction error over limited or unrepresentative calibration data may move the quantized weights away from the original floating-point weights, potentially degrading downstream performance. To address this issue, we propose \emph{Regularized Quantization Calibration} (RQC), a unified framework that augments standard PTQ objectives with a regularizer that explicitly controls weight deviation from the original weights. We further generalize this framework to incorporate a saliency-aware regularizer, resulting in \emph{Saliency-Aware Regularized Quantization Calibration} (SARQC). The proposed regularization encourages quantized weights to remain close to the original weights during calibration, leading to improved generalization at inference time. SARQC integrates seamlessly into existing PTQ pipelines and enhances both scale-search-based and Gram-based methods under a unified formulation. Extensive experiments on dense and Mixture-of-Experts LLMs demonstrate consistent improvements in perplexity and zero-shot accuracy, without introducing additional inference overhead.

Yanlong Zhao, Xiaoyuan Cheng, Huihang Liu +6

University of Science and Technology of China · University College London · 3Shanghai University of Finance and Economics +5

LLM Quantization Language Model Calibration Post-Training Quantization Neural Network Quantization

May 6, 2026cs.LG

OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization

Large Language Models (LLMs) have demonstrated remarkable capabilities. However, their massive parameter scale leads to significant resource consumption and latency during inference. Post-training weight-only quantization offers a promising solution by reducing model size and accelerating token generation through alleviating the memory-bound issue. Nevertheless, the presence of inherent systematic outliers in weights continues to be a major obstacle. While existing methods, such as scaling and rotation, attempt to address this issue, the performance remains unsatisfactory. In this paper, we propose Outlier Self-Absorption Quantization (OSAQ), which performs additive weight suppression guided by the second-order low-rank property for low-bit weight-only quantization of LLMs. Specifically, we observe that the Hessian exhibits low-rank consistency across different inputs, with certain directions consistently showing vanishing curvature. Leveraging this property, we identify a stable null space of the Hessian and then construct an additive weight transformation by linearly combining the vectors within this null space, thereby suppressing weight outliers without affecting the task loss. This additive transformation can be absorbed into the weights offline, requiring no inter-layer transformations and introducing no inference overhead. Moreover, the construction is efficiently achieved by a closed-form solution, without resource-intensive training or iterative procedures. Extensive experiments demonstrate that OSAQ effectively suppresses outliers and enhances low-bit quantization performance. For instance, in 2-bit quantization, OSAQ, when integrated with GPTQ, achieves over 40% lower perplexity compared to vanilla GPTQ.

Zhikai Li, Zhen Dong, Xuewen Liu +2

Institute of Automation, Chinese Academy of Sciences · University of California, Santa Barbara.

LLM Quantization Weight-Only Quantization Post-Training Quantization Low-Bit Quantization Neural Network Quantization

May 5, 2026cs.LG

Hardware-Aware Neural Feature Extraction for Resource-Constrained Devices

Visual SLAM is a core component of spatial computing systems, yet deploying learned local feature extractors on microcontroller-class hardware remains challenging due to memory, bandwidth, and quantization constraints. While modern neural descriptors provide strong robustness, their practical adoption is often hindered by system-level bottlenecks that are not captured by FLOP-based efficiency metrics. In this work, we introduce Gideon, a hardware-aware neural feature extractor explicitly designed for resource-constrained devices. Our approach combines relational knowledge distillation from a SuperPoint teacher with differentiable neural architecture search (DNAS) under strict memory and operator constraints. Unlike conventional design pipelines, we treat quantization stability and dynamic-range compactness as first-class objectives. We show that architectural choices such as replacing Batch Normalization with affine layers significantly improve INT8 robustness, and that descriptor dimensionality directly governs quantization resilience. Deployed on STM32N6, Gideon achieves 9.003 ms inference time (111 fps) while remaining below a 1.5 MB memory footprint. Remarkably, INT8 quantization induces negligible degradation and occasionally matches full-precision performance. These results demonstrate that robust learned feature extraction can be reconciled with embedded hardware constraints through holistic hardware-algorithm co-design.

Francesco Tosini, Simone Pedroni, Christian Veronesi +5

Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Italy · Department of Electronics, Informationة · Smart Eyewear Lab, EssilorLuxottica, Milan, Italy

Edge Inference Visual SLAM Hardware-Aware NAS Neural Network Quantization

May 5, 2026cs.CV

Topology-Constrained Quantized nnUNet for Efficient and Anatomically Accurate 3D Tooth Segmentation

We propose a topology-constrained quantized nnUNet framework for efficient and anatomically accurate 3D tooth segmentation, addressing the challenges of spatial distortion introduced by quantization in deep learning models. The proposed method integrates a novel tooth-specific topological loss into quantization-aware training, preserving critical anatomical structures such as tooth count, adjacency relationships, and cavity integrity while maintaining computational efficiency. The system employs an 8-bit quantized nnUNet backbone, where weights and activations are dynamically calibrated to minimize precision loss during inference. Furthermore, the topological loss combines connected-component analysis, adjacency consistency, and hole detection penalties, ensuring anatomical fidelity without modifying the underlying network architecture. The joint optimization objective harmonizes cross-entropy loss, quantization regularization, and topological constraints, enabling end-to-end training with gradient approximations for persistent homology terms. Experiments demonstrate that our approach significantly reduces topological errors compared to conventional quantized models, achieving clinically plausible segmentations on dental CBCT scans. The method retains the hardware efficiency of integer-only inference, making it suitable for deployment in resource-constrained clinical environments. This work bridges the gap between computational efficiency and anatomical precision in medical image segmentation, offering a practical solution for real-world dental applications.

Paarth Prasad, Ruchika Malhotra

Department of Software Engineering, Delhi Technological University

Quantization-Aware Training Topology-Preserving Image Segmentation 3D Medical Image Segmentation Neural Network Quantization

May 5, 2026cs.LG

HeadQ: Model-Visible Distortion and Score-Space Correction for KV-Cache Quantization

KV-cache quantizers usually optimize storage-space reconstruction, even though attention reads keys through logits and values through attention-weighted readout. We argue that persistent cache error should be measured in model-visible coordinates. For keys, the visible object is score error modulo constant shifts; this yields HeadQ, a key-side method that stores a low-rank residual side code in a calibration-learned query basis and applies it as an additive logit correction. For values, fixed-attention readout gives an

A^2

-weighted token-distortion surrogate. Across six models, Fisher/score-space error predicts attention KL far better than raw key MSE; same-budget counterexamples, null-space interventions, query-PCA controls, and wrong-sign HeadQ falsify storage-MSE alternatives. Matched Pythia checkpoints localize the main anomaly to a small-model low-entropy route-flip boundary. In K-only WikiText-103 decode experiments with dense values, HeadQ removes roughly

84

--

94\%

of the excess perplexity on the strongest 2-bit rows; in an auxiliary full-KV 2-bit composition, HeadQ plus an

A^2

value policy improves all six models.

Jorge L. Ruiz Williams

Independent Researcher

Self-Attention KV Caching Attention Quantization KV-Cache Compression KV-Cache Quantization Post-Training Quantization+1

May 5, 2026cs.LG

QuIDE: Mastering the Quantized Intelligence Trade-off via Active Optimization

There is currently no unified metric for evaluating the efficiency of quantized neural networks. We propose QuIDE, built around the Intelligence Index I = (C x P)/log_2(T+1), which collapses the compression-accuracy-latency trade-off into a single score. Experiments across six settings -- SimpleCNN (MNIST, CIFAR), ResNet-18 (ImageNet-1K), and Llama-3-8B -- show a task-dependent Pareto Knee. 4-bit quantization is optimal for MNIST and large LLMs, while 8-bit is the sweet spot for complex CNN tasks (ResNet-18 on ImageNet), where 4-bit PTQ collapses accuracy catastrophically. The accuracy-gated variant I' correctly flags these non-viable configurations that the raw I would reward. QuIDE provides a reproducible evaluation protocol and a ready-to-use fitness function for mixed-precision search.

Xiantao Jiang

College of Information Engineering, Shanghai Maritime University Shanghai 201306, China

Mixed-Precision Quantization LLM Quantization Post-Training Quantization Neural Network Quantization

May 4, 2026cs.LG

Statistically-Lossless Quantization of Large Language Models

Model quantization has become essential for efficient large language model deployment, yet existing approaches involve clear trade-offs: methods such as GPTQ and AWQ achieve practical compression but are lossy, while lossless techniques preserve fidelity but typically do not accelerate inference. This paper explores the middle ground of statistically-lossless compression through three complementary notions of losslessness for quantized LLMs. First, task-lossless compression preserves zero-shot benchmark accuracy within natural sampling variance and remains achievable at aggressive bitwidths. Second, we formalize the stricter notion of distribution-lossless compression, requiring the quantized model's next-token distribution to be practically indistinguishable from the original, and propose the Expected Acceptance Rate (EAR), the maximum token-agreement probability under optimal coupling, as a directly interpretable fidelity metric (for example, EAR >= 0.99 indicates 99% agreement). Third, we prove a gamma-squared variance law showing that symmetric quantization inflates noise variance by gamma squared relative to asymmetric quantization, making asymmetry necessary for distribution-lossless fidelity but not for task-level preservation. Using SLQ, a layer-wise non-uniform method with asymmetric quantization and wide bitwidth search, we achieve task-lossless compression at well below 4 bits per parameter (as low as 3.3 bits depending on the model), distribution-lossless compression at 5 to 6 bits per parameter on average, and inference speedups of 1.7 to 3.6x relative to FP16 with optimized kernels. Source code is available at https://github.com/IST-DASLab/SLQ.

Michael Helcig, Eldar Kurtic, Dan Alistarh

ETH Z̈urich · ISTA

LLM Quantization LLM Inference Acceleration Post-Training Quantization Low-Bit Quantization Neural Network Quantization

May 3, 2026cs.AR

ViM-Q: Scalable Algorithm-Hardware Co-Design for Vision Mamba Model Inference on FPGA

Vision Mamba (ViM) models offer a compelling efficiency advantage over Transformers by leveraging the linear complexity of State Space Models (SSMs), yet efficiently deploying them on FPGAs remains challenging. Linear layers struggle with dynamic activation outliers that render static quantization ineffective, while uniform quantization fails to capture the weight distribution at low bit-widths. Furthermore, while associative scan accelerates SSMs on GPUs, its memory access patterns are misaligned with the streaming dataflow required by FPGAs. To address these challenges, we present ViM-Q, a scalable algorithm-hardware co-design for end-to-end ViM inference on the edge. We introduce a hardware-aware quantization scheme combining dynamic per-token activation quantization and per-channel smoothing to mitigate outliers, alongside a custom 4-bit per-block Additive Power-of-Two (APoT) weight quantization. The models are deployed on a runtime-parameterizable FPGA accelerator featuring a linear engine employing a Lookup-Table (LUT) unit to replace multiplications with shift-add operations, and a fine-grained pipelined SSM engine that parallelizes the state dimension while preserving sequential recurrence. Crucially, the hardware supports runtime configuration, adapting to diverse dimensions and input resolutions across the ViM family. Implemented on an AMD ZCU102 FPGA, ViM-Q achieves an average 4.96x speedup and 59.8x energy efficiency gain over a quantized NVIDIA RTX 3090 GPU baseline for low-batch inference on ViM-tiny. This co-design shows a viable path for deploying ViM models on resource-constrained edge devices.

Shengzhe Lyu, Yuhan She, Patrick S. Y. Hung +2

City University of Hong Kong, Hong Kong

Efficient Neural Network Inference Edge Inference Activation Quantization Hardware-Software Co-Design FPGA-Based Neural Network Acceleration Neural Network Quantization

May 3, 2026cs.NE

ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantization

Spiking neural networks (SNNs) are promising for edge sensing due to their event-driven computation and temporal filtering capability. However, standard leaky integrate-and-fire (LIF) neurons communicate only through binary spikes, which severely limit representational capacity. Existing multi-level spiking neurons improve information transmission, but often rely on uniform quantization that mismatches membrane-potential distributions or introduces costly synaptic multiplications. In this paper, we propose ShiftLIF, a multi-level spiking neuron that maps membrane potentials to a logarithmically spaced power-of-two spike set. This design provides finer representation in the small-amplitude regime, where membrane potentials are densely concentrated, while enabling multiplier-free synaptic computation through bit-shift and accumulation operations. As a result, ShiftLIF improves spike-level expressiveness without sacrificing the hardware-friendly nature of standard SNN computation. We evaluate ShiftLIF on 10 datasets spanning wireless, acoustic, motion, and visual sensing tasks. Results show that ShiftLIF consistently matches or exceeds the accuracy of existing multi-level spiking neurons while maintaining synaptic energy consumption close to standard binary LIF. These results indicate that ShiftLIF provides a favorable accuracy-efficiency trade-off for cross-modal edge sensing.

Kaiwen Tang, Di Yu, Jiaqi Zheng +4

Zhejiang University · Shandong University

Spiking Neural Networks Neural Network Quantization

Apr 30, 2026cs.LG

Technical Report: Activation Residual Hessian Quantization (ARHQ) for Low-Bit LLM Quantization

We present Activation Residual Hessian Quantization (ARHQ), a post-training weight splitting method designed to mitigate error propagation in low-bit activation-weight quantization. By constructing an input-side residual Hessian from activation quantization residuals (G_x), ARHQ analytically identifies and isolates error-sensitive weight directions into a high-precision low-rank branch. This is achieved via a closed-form truncated SVD on the scaled weight matrix W G^{1/2}_x . Experimental results on Qwen3-4B-Thinking-2507 demonstrate that ARHQ significantly improves layer-wise SNR and preserves downstream reasoning performance on ZebraLogic even under aggressive quantization. The code is available at https://github.com/BeautMoonQ/ARHQ.

YiFeng Wang, Zhun Sun, Keisuke Sakaguchi

Graduate School of Information Sciences Tohoku University

LLM Quantization Activation Quantization Post-Training Quantization Low-Bit Quantization Neural Network Quantization

Apr 29, 2026cs.CR

Quantamination: Dynamic Quantization Leaks Your Data Across the Batch

Dynamic quantization emerged as a practical approach to increase the utilization and efficiency of the machine learning serving flow. Unlike static quantization, which applies quantization offline, dynamic quantization operates on tensors at run-time, adapting its parameters to the actual input data. Today's mainstream machine learning frameworks, including ML compilers and inference engines, frequently recommend dynamic quantization as an initial step for optimizing model serving. This is because dynamic quantization can significantly reduce memory usage and computational load, leading to faster token generation and improved model serving efficiency without substantial loss in model accuracy. In this paper, we reveal a critical vulnerability in dynamic quantization: an adversary can exploit such quantization strategy to steal sensitive user data placed in the same batch as the adversary's input. Our analysis demonstrates that dynamic quantization, when improperly implemented or configured, can create side channels that expose information about other inputs within the same batch. We call this phenomenon Quantamination, describing contamination from quantization. Specifically, we show that at least 4 of the most popular ML frameworks in use today either default to or can use configurations that leak data across the batch boundary. This data leakage, in theory, allows attackers to partially or even fully recover other users' batched input data, representing a serious privacy risk for existing ML serving frameworks.

Hanna Foerster, Ilia Shumailov, Cheng Zhang +3

University of Cambridge · 2AI Sequrity Company · 3Google DeepMind

Data Leakage Privacy-Preserving ML Neural Network Quantization

Apr 29, 2026cs.LG

CoQuant: Joint Weight-Activation Subspace Projection for Mixed-Precision LLMs

Post-training quantization (PTQ) has become an important technique for reducing the inference cost of Large Language Models (LLMs). While recent mixed-precision methods improve ultra-low bit quantization by preserving critical subspaces in high precision, they typically construct these subspaces relying solely on activation statistics. This ignores the fundamental nature of linear operations, where the output perturbation is jointly driven by both activation and weight quantization noise. In this paper, we propose CoQuant, a joint weight-activation subspace projection method. By theoretically modeling the expected output error, CoQuant formulates a closed-form weighted PCA solution that balances activation and weight covariances to select the optimal high-precision subspace. Extensive experiments on Llama-3.2 and Qwen2.5 models show that CoQuant consistently outperforms strong PTQ baselines in both WikiText perplexity and zero-shot common-sense reasoning accuracy. These results demonstrate that joint weight-activation subspace modeling provides a principled and effective direction for low-bit LLM quantization. The source code is available at https://github.com/Zachary5895/CoQuant.

Zhe Ding, Su Pan, Duowei Pan

School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing, China · Amazon AGI, Seattle, WA, USA

Mixed-Precision Quantization LLM Quantization Activation Quantization Post-Training Quantization Low-Bit Quantization Neural Network Quantization

Apr 28, 2026cs.AR

Multibit neural inference in a N-ary crossbar architecture

In-memory computing (IMC) is a paradigm that enables neural network inference by computing analog matrix-vector multiplications (MVM) directly in memory crossbar arrays, with the potential for energy efficiency gains over conventional von Neumann architectures. In this work we present a simulation framework for N-ary crossbar architectures that retrieves MVM results with minimal implementation assumptions. The XOR and MNIST classification tasks were successfully inferred using a simulated crossbar array of (4x4) 4-states magnetic tunnel junctions (MTJ). MNIST accuracy reached 93.56% (vs. 97.56% software baseline). PCA dimensionality reduction was shown to drastically lower the number of required operations and improve the software baseline, for only a modest reduction in crossbar inference accuracy. We identified weight quantization as the primary error source, and studied its impact alongside systematic non-idealities and random noise. We find that cell-specific random noise is less detrimental than systematic errors due to averaging across the array. Finally, we demonstrate an optimal number of states per cell that balances quantization error against resistance state resolution to minimize total MVM error.

Anatole Moureaux, Anthony Lopes Temporao, Flavio Abreu Araujo

Universit´e catholique de Louvain, Institute of Condensed Matter and Nanosciences, Louvain-la-Neuve, 1348, Belgium

Efficient Neural Network Inference Compute-in-Memory Neural Network Quantization

Apr 28, 2026cs.LG

QFlash: Bridging Quantization and Memory Efficiency in Vision Transformer Attention

FlashAttention improves efficiency through tiling, but its online softmax still relies on floating-point arithmetic for numerical stability, making full quantization difficult. We identify three main obstacles to integer-only FlashAttention: (1) scale explosion during tile-wise accumulation, (2) inefficient shift-based exponential operations on GPUs, and (3) quantization granularity constraints requiring uniform scales for integer comparison. To address these challenges, we propose \textit{QFlash}, an end-to-end integer FlashAttention design that performs softmax entirely in the integer domain and runs as a single Triton kernel. On seven attention workloads from ViT, DeiT, and Swin models, QFlash achieves up to 6.73

\times

speedup over I-ViT and up to 8.69

\times

speedup on Swin, while reducing energy consumption by 18.8% compared to FP16 FlashAttention, without sacrificing Top-1 accuracy on ViT/DeiT and remaining competitive on Swin under per-tensor quantization. Our code is publicly available at https://github.com/EfficientCompLab/qflash.

Sehyeon Oh, Yongin Kwon, Jemin Lee

University of Science and Technology, Daejeon, Republic of Korea · Electronics and Telecommunications Research Institute, Daejeon, Republic of Korea · Pusan National University, Busan, Republic of Korea +1

Softmax Attention GPU Acceleration Vision Transformer Efficient ViTs Attention Quantization Attention Mechanisms+2

Apr 27, 2026cs.CV

Deployment-Aligned Low-Precision Neural Architecture Search for Spaceborne Edge AI

Designing deep networks that meet strict latency and accuracy constraints on edge accelerators increasingly relies on hardware-aware optimization, including neural architecture search (NAS) guided by device-level metrics. Yet most hardware-aware NAS pipelines still optimize architectures under full-precision assumptions and apply low-precision adaptation only after the search, leading to a mismatch between optimization-time behavior and deployment-time execution on low-precision hardware that can substantially degrade accuracy. We address this limitation by integrating deployment-aligned low-precision training directly into hardware-aware NAS. Candidate architectures are exposed to FP16 numerical constraints during fine-tuning and evaluation, enabling joint optimization of architectural efficiency and numerical robustness without modifying the search space or evolutionary strategy. We evaluate the proposed framework on vessel segmentation for spaceborne maritime monitoring, targeting the Intel Movidius Myriad X Visual Processing Unit (VPU). While post-training precision conversion reduces on-device performance from 0.85 to 0.78 mIoU, deployment-aligned low-precision training achieves 0.826 mIoU on-device for the same architecture (95,791 parameters), recovering approximately two-thirds of deployment-induced accuracy gap without increasing model complexity. These results demonstrate that incorporating deployment-consistent numerical constraints into hardware-aware NAS substantially improves robustness and alignment between optimization and deployment for resource-constrained edge Artificial Intelligence (AI).

Parampuneet Kaur Thind, Vaibhav Katturu, Giacomo Zema +1

1Sapienza University of Rome · 2 Φ-lab, ESA ESRIN · 4Argotec Srl +1

Edge Computing Hardware-Aware NAS Neural Architecture Search Neural Network Quantization

Apr 25, 2026cs.CV

Enhanced Privacy and Communication Efficiency in Non-IID Federated Learning with Adaptive Quantization and Differential Privacy

Federated learning (FL) is a distributed machine learning method where multiple devices collaboratively train a model under the management of a central server without sharing underlying data. One of the key challenges of FL is the communication bottleneck caused by variations in connection speed and bandwidth across devices. Therefore, it is essential to reduce the size of transmitted data during training. Additionally, there is a potential risk of exposing sensitive information through the model or gradient analysis during training. To address both privacy and communication efficiency, we combine differential privacy (DP) and adaptive quantization methods. We use Laplacian-based DP to preserve privacy, which is relatively underexplored in FL and offers tighter privacy guarantees than Gaussian-based DP. We propose a simple and efficient global bit-length scheduler using round-based cosine annealing, along with a client-based scheduler that dynamically adapts based on client contribution estimated through dataset entropy analysis. We evaluate our approach through extensive experiments on CIFAR10, MNIST, and medical imaging datasets, using non-IID data distributions across varying client counts, bit-length schedulers, and privacy budgets. The results show that our adaptive quantization methods reduce total communicated data by up to 52.64% for MNIST, 45.06% for CIFAR10, and 31% to 37% for medical imaging datasets compared to 32-bit float training while maintaining competitive model accuracy and ensuring robust privacy through differential privacy.

Emre Ardıç, Yakup Genç

Department of Computer Engineering, Gebze Technical University, Gebze, Kocaeli 41400, Türkiye

Non-IID Federated Learning Differentially Private Federated Learning Neural Network Quantization Federated Learning

Apr 25, 2026cs.LG

Efficient VQ-QAT and Mixed Vector/Linear quantized Neural Networks

In this work, we developed and tested 3 techniques for vector quantization (VQ) based model weight compression. To mitigate codebook collapse and enable end-to-end training, we adopted cosine similarity-based assignment. Building on ideas from attention-based formulations in Differentiable K-Means (DKM), we further improved this approach by using cosine similarity for assignment combined with top-1 sampling and a straight-through estimator, thereby eliminating the need for weighted-average reconstruction. Finally, we investigated the use of differentiable neural architecture search (NAS) to adaptively select layer-wise quantization configurations, further optimizing the compression process. Although our method does not consistently outperform existing approaches across all quantization levels, it provides useful insights into the design trade-offs and behaviors of VQ-based model compression methods.

Terry Gou, Puneet Gupta

Quantization-Aware Training Vector Quantization Neural Network Quantization Neural Network Compression

Apr 24, 2026cs.AR

HGQ-LUT: Fast LUT-Aware Training and Efficient Architectures for DNN Inference

Lookup-table (LUT) based neural networks can deliver ultra-low latency and excellent hardware efficiency on FPGAs by mapping arithmetic operations directly onto the logic primitives. However, state-of-the-art LUT-aware training (LAT) approaches remain difficult to use in practice: they are often orders of magnitude slower to train than conventional networks, require non-trivial manual tuning for hardware efficiency, and lack an end-to-end workflow. This work presents HGQ-LUT, integrated in https://github.com/calad0i/HGQ2, a new LAT approach that achieves state-of-the-art hardware efficiency while accelerating training by over 100 times on modern GPUs. HGQ-LUT introduces LUT-Dense and LUT-Conv layers that are implemented with regular, accelerator-efficient tensor operations during training, which are then compiled into logic LUTs for hardware. By combining these layers with fine-grained, element-wise heterogeneous quantization (including zero-bit pruning) and a LUT-aware resource surrogate, HGQ-LUT enables the automatic exploration of accuracy-resource trade-offs without manual bit-width tuning. We further integrate HGQ-LUT into open-source toolchains, enabling unified design, compilation, and bit-exact verification of hybrid architectures that mix LUT-based with conventional arithmetic blocks. These features make LAT-based DNNs practical for real-world deployment, such as at the CERN Large Hadron Collider's experiments.

Chang Sun, Zhiqiang Que, Bakhtiar Zadeh +4

California Institute of Technology, Pasadena, CA, USA · University of Bristol, UK · Imperial College London, UK +1

Efficient Neural Network Inference FPGA-Based Neural Network Acceleration Neural Network Quantization

Apr 22, 2026cs.LG

FASQ: Flexible Accelerated Subspace Quantization for Calibration-Free LLM Compression

Compressing large language models (LLMs) for deployment on commodity GPUs remains challenging: conventional scalar quantization is limited to fixed bit-widths (e.g., 8/4/3-bit), offers only a few discrete compression points, and typically requires calibration data. We present FASQ (Flexible Accelerated Subspace Quantization), a calibration-free framework that applies product quantization to LLM weight matrices. By tuning two parameters, sub-vector size and codebook cardinality, FASQ exposes a continuous design space spanning 27-49% of the original FP16 model size, filling compression gaps that fixed-bit schemes cannot reach. On Meta-Llama-3-8B, FASQ surpasses 4-bit GPTQ and AWQ in accuracy (67.1-67.7 avg.) at 37-42% model size, with consistent results on Qwen3-8B and Qwen3.5-9B-Base. To make product quantization practical at inference time, we design custom CUDA kernels: a LUT-free direct-compute GEMV for decode and an output-stationary double-buffered LUT GEMM for prefill, both with split-K parallelism. On an RTX~3090, FASQ achieves 45.2 tok/s decode at effective 4-bit (2.56x memory reduction) and 51.8 tok/s at effective 3-bit (2.80x), both surpassing FP16 tensor-core performance (43.9 tok/s) and delivering 1.6 to 1.8x the throughput of AWQ, 2.5 to 2.5x of GPTQ, and 4.3 to 5x of RTN. FASQ is the only compressed method that accelerates decode beyond FP16, offering calibration-free compression, continuous size-quality trade-offs, and real-time inference on a single consumer GPU.

Ye Qiao, Yian Wang, Zhiheng Chen +2

University of California, Irvine Irvine, California, USA

LLM Compression GPU Acceleration Vector Quantization LLM Inference Acceleration Product Quantization Post-Training Quantization+1

Apr 22, 2026cs.NE

Quantization robustness from dense representations of sparse functions in high-capacity kernel associative memory

High-capacity associative memories based on Kernel Logistic Regression (KLR) achieve strong retrieval performance but typically require substantial computational resources. This paper investigates the compressibility of KLR Hopfield networks to clarify the geometric principles underlying their robust representations. We present a geometric interpretation based on spontaneous symmetry breaking and Walsh analysis, and examine it through compression experiments involving quantization and pruning. The experiments reveal a clear asymmetry: the network remains robust under low-precision quantization while exhibiting strong sensitivity to pruning. We interpret this behavior through a "sparse function, dense representation" principle, in which a sparse input mapping is implemented through a dense bimodal parameterization. These findings suggest a practical route toward hardware-efficient kernel associative memories and provide insight into the geometric principles underlying robust representation in neural systems.

Akira Tamamori

Faculty of Information Science, Aichi Institute of Technology 1247 Yachigusa, Yakusa-cho, Toyota-shi, Aichi 470-0392, Japan

Neural Representation Geometry Hopfield Networks Associative Memory Neural Network Quantization

Apr 22, 2026cs.LG

FairyFuse: Multiplication-Free LLM Inference on CPUs via Fused Ternary Kernels

Large language models are increasingly deployed on CPU-only platforms where memory bandwidth is the primary bottleneck for autoregressive generation. Weight quantization to four bits or below reduces memory pressure, yet existing systems still dequantize weights and perform floating-point multiplications, limiting the achievable gains. Ternary weights in {-1, 0, +1} provide a more efficient alternative, replacing multiplications with conditional additions, subtractions, or no-ops. While Fairy2i shows that ternary LLMs can match FP16 quality, its runtime does not exploit this structure. We present FairyFuse, an inference system that enables multiplication-free execution on commodity CPUs by fusing the eight real-valued sub-GEMVs of each widely-linear layer into a single AVX-512 loop using masked additions and subtractions, with zero floating-point multiplications. Roofline analysis shows that 16x weight compression shifts memory-bound GEMV toward the compute regime on bandwidth-limited CPUs, yielding a 29.6x kernel speedup while offering little benefit on GPUs. End-to-end, FairyFuse achieves 32.4 tokens per second on a single Intel Xeon 8558P, outperforming llama.cpp Q4_K_M by 1.24x with near-lossless quality (WikiText-2 perplexity 5.52 vs. 5.47 FP16; downstream accuracy 66.0%).

Fei Zuo, Xiaoyan Xi, Quanyi Zeng +2

BA TechWorks · Peking University

Efficient Neural Network Inference Ternary Quantization Inference-Time Optimization LLM Inference Acceleration Neural Network Quantization

Apr 22, 2026cs.LG

On the Quantization Robustness of Diffusion Language Models in Coding Benchmarks

Auto-regressive Large Language Models (LLMs) achieve strong performance on coding tasks, but incur high memory and inference costs. Diffusion-based language models (d-LLMs) offer bounded inference cost via iterative denoising, but their behavior under post-training quantization (PTQ) has been sparsely explored. We investigate the application and robustness of PTQ techniques, specifically GPTQ and a modified Hessian-Aware Quantization (HAWQ) algorithm, on a diffusion-based coding LLM (CoDA) and observe that these methods applied to CoDA exhibit greater robustness at low bitwidths compared to Qwen3-1.7B, its auto-regressive counterpart, under a standardized evaluation pipeline. We find that in our setup, CoDA exhibits greater robustness at low bitwidths (2-4 bits), with smaller accuracy degradation across HumanEval and MBPP benchmarks. Additionally, mixed-precision configurations derived from HAWQ provide smooth trade-offs across accuracy, latency, and memory. The results suggest that diffusion LLMs may offer advantages for efficient deployment due to more quantization-resilience.

Aarav Gupta, Gururaj Deshpande, Chandreyi Chakraborty

College of Computing · Georgia Institute of Technology

Mixed-Precision Quantization Diffusion Model Quantization Diffusion Language Models Post-Training Quantization Neural Network Quantization

Apr 21, 2026cs.CL

From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization

Post-Training Quantization (PTQ) is critical for the efficient deployment of Large Language Models (LLMs). While 4-bit quantization is widely regarded as an optimal trade-off, reducing the precision to 2-bit usually triggers a catastrophic ``performance cliff.'' It remains unclear whether the underlying mechanisms differ fundamentally. Consequently, we conduct a systematic mechanistic analysis, revealing two qualitatively distinct failure modes: Signal Degradation, where the computational patterns remain intact but information precision is impaired by cumulative error; and Computation Collapse, where key components fail to function, preventing correct information processing and destroying the signal in the early layers. Guided by this diagnosis, we conduct mechanism-aware interventions, demonstrating that targeted, training-free repair can mitigate Signal Degradation, but remains ineffective for Computation Collapse. Our findings provide a systematic diagnostic framework for PTQ failures and suggest that addressing Computation Collapse requires structural reconstruction rather than mere compensation.

Chenxi Zhou, Pengfei Cao, Jiang Li +4

School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences · College of Computer Science, Inner Mongolia University +1

LLM Quantization Post-Training Quantization Low-Bit Quantization Neural Network Quantization

Apr 21, 2026cs.LG

SAW-INT4: System-Aware 4-Bit KV-Cache Quantization for Real-World LLM Serving

KV-cache memory is a major bottleneck in real-world LLM serving, where systems must simultaneously support latency-sensitive small-batch requests and high-throughput concurrent workloads. Although many KV-cache compression methods improve offline accuracy or compression ratio, they often violate practical serving constraints such as paged memory layouts, regular memory access, and fused attention execution, limiting their effectiveness in deployment. In this work, we identify the minimal set of 4-bit KV-cache quantization methods that remain viable under these constraints. Our central finding is that a simple design--token-wise INT4 quantization with block-diagonal Hadamard rotation--consistently achieves the best accuracy-efficiency trade-off. Across multiple models and benchmarks, this approach recovers nearly all of the accuracy lost by naive INT4, while more complex methods such as vector quantization and Hessian-aware quantization provide only marginal additional gains once serving compatibility is taken into account. To make this practical, we implement a fused rotation-quantization kernel that integrates directly into paged KV-cache layouts and introduces zero measurable end-to-end overhead, matching plain INT4 throughput across concurrency levels. Our results show that effective KV-cache compression is fundamentally a systems co-design problem: under real serving constraints, lightweight block-diagonal Hadamard rotation is a viable method that delivers near-lossless accuracy without sacrificing serving efficiency.

Jinda Jia, Jisen Li, Zhongzhu Zhou +8

Together AI

LLM Serving KV Caching Memory-Efficient Optimization 4-Bit Quantization Rotation-Based Quantization LLM Inference Acceleration+2

Apr 20, 2026cs.CL

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Quantization has become a standard tool for efficient LLM deployment, especially for local inference, where models are now routinely served at 2-3 bits per parameter. The state of the art is currently split into simple scalar quantization techniques, such as GPTQ or AWQ, which are widely deployed but plateau in accuracy at 3-4 bits per parameter (bpp), and "second-generation" vector- or trellis-quantized methods, such as QTIP, GPTVQ and AQLM, which push the accuracy frontier but are notoriously hard to implement and to scale. In this paper, we ask whether this gap is fundamental, or whether a carefully optimized

\textit{scalar}

quantizer can recover most of it. We answer in the affirmative, by introducing GSQ (Gumbel-Softmax Quantization), a post-training scalar quantization method which jointly learns the per-coordinate grid assignments and the per-group scales using a Gumbel-Softmax relaxation of the discrete grid. GSQ matches the cardinality of the relaxation to the small number of levels available in the target bit-width regime (e.g., 3-8 levels for ternary and 3 bpp, respectively), making optimization tractable. Practically, on the standard Llama-3.1-8B/70B-Instruct models, GSQ closes most of the gap between scalar quantization and the QTIP frontier at 2 and 3 bits, while using a symmetric scalar grid with group-wise quantization, and thus remains compatible with existing scalar inference kernels. We further show that the same discrete-assignment optimization can be applied to practical GGUF K-Quant checkpoints: starting from publicly released GGUF models, GSQ improves accuracy while projecting the result back into the same deployment format. Finally, GSQ scales to trillion-scale Mixture-of-Experts models such as Kimi-K2.5, where vector-quantized methods are difficult to apply. The source code is publicly available at https://github.com/IST-DASLab/GSQ.

Alireza Dadgarnia, Soroush Tabesh, Mahdi Nikdan +4

ISTA · ETH Zürich · ISTA & Red Hat AI +1

LLM Quantization Post-Training Quantization Low-Bit Quantization Neural Network Quantization