Low-Bit Quantization

Follow this topic Ask about this topic

Momentum

21 papers in the last four weeks, up 62% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 155

Aug 31, 2026cs.LG

Fine-Tuning Low-Bit Models with Gradient in Quantized Code Space

Fine-tuning Low-bit models aims to adapt a quantized model while keeping the final deployed checkpoint in the same low-bit form. This setting is practically important as it reduces memory and inference cost for storage and deployment. Under this constraint, adaptation becomes an optimization problem over quantization codes and scales. Existing continuous low-bit training is efficient, but it can be distorted by straight through estimation error or by post-quantize gap; discrete search is deployment-faithful, but it is often too inefficient under a finite training budget. We propose code surrogate gradient as the first order signal in deployable code space to acceleate optimization, and performing guided search to preserve deployment faithfulness. Experiments across arithmetic reasoning, instruction following, and structured language understanding show that GradCodes consistently improves fine-tuning low-bit models across different quantization datatypes. Code is provided at https://github.com/ovo67/GradCodes.

Shiguang Wu, Zhouchen Lin, Quanming Yao

Department of Electronic Engineering, Tsinghua University · School of Intelligence Science and Technology, Peking University

Fine-Tuning Low-Bit Quantization

Aug 31, 2026cs.LG

RSLM: Training-Free Vector Quantization for Approximate Nearest Neighbor Search

By introducing RSLM (Rotated Scaled Lloyd-Max), a family of training-free vector quantization codecs compressing embeddings to 1--4 bits per dimension, we reduce memory cost and memory bandwidth of a typical large-scale Approximate Nearest Neighbor (ANN) search system, while reducing its complexity and keeping or improving recall across multiple benchmark datasets. State-of-the-art systems filter candidates using coarse partitions, approximately score them to narrow the set, and then rescore the best with higher precision representations (often >=8 bits per dimension). Our relativized codecs can bring this down to 2--4 bits per dimension. We use the properties of the ANN system to encode residual vectors instead of full vectors, both for the approximate scoring phase and the rescoring phase. Since Maximum Inner Product Search (MIPS) is very sensitive to vector norms, we correct the

L_2

norms of quantized vectors. Our major innovation is that we correct the

L_2

norm of the final reconstructed vector rather than just the residual. Our rescaling replaces more complicated schemes, such as Anisotropic loss. The residualization scheme gives us a more favorable quality vs size trade-off than generic quantization methods. Our high-performance implementation leverages a block-wise cascaded Fast Walsh-Hadamard Transform (FWHT) with linear-like complexity, AVX SIMD-optimized codebooks, and a steganographic encoding of scaling factors for perfect cache-line alignment.

Rastislav Lenhardt, Teodora Dobos, Thomas Vecchiato +2

Google Zurich, Switzerland · Technical University of Munich Munich, Germany · University of Copenhagen Copenhagen, Denmark +1

Rotation-Based Quantization Vector Quantization Embedding Compression Low-Bit Quantization Approximate Nearest Neighbor Search

Aug 30, 2026cs.LG

A Target-Centric Survey of Quantization-Aware Training

The rapid development of LLMs incurs prohibitive memory footprints and intensive computational demands. Quantization-Aware Training (QAT) techniques have emerged as a promising solution to address these challenges by explicitly simulating quantization effects during model training, yielding low-bit models that achieve accuracy comparable to their full-precision counterparts. In this work, we provide a target-centric survey of QAT, aimed at clarifying both its theoretical foundations and its evolving implementation landscape. We systematically review existing QAT methods through a target-centric taxonomy and synthesize cross-target differences in error characteristics, numerical formats, and strategy transferability. We further summarize QAT evaluation paradigms and discuss challenges in optimization and deployment, outlining potential directions for future research.

Jiamin Song, Mengjie Zhao, Zijing Wang +6

1Northeastern University, China · 2Shandong University, China · 3CIS, LMU Munich; MCML, Germany

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

Aug 24, 2026cs.LG

Activation-Weighted Seeded Residual Coding for Low-Bit LLM Weight Repair

Low-bit weight quantization saves storage but leaves errors that degrade LLM quality. We introduce activation-weighted seeded residual coding (AWSRC), a compact repair codec for an existing quantization backbone. Given a reconstructed weight

W_0

, AWSRC encodes the residual

W-W_0

using deterministic seed-generated bases. The sidecar stores seed selectors, low-bit coefficients, and scales rather than an explicit codebook. Two variants combine activation weighting with per-module byte quotas (

\mathrm{AWSRC\text{-}U}

), or blended activation/Fisher weighting with globally ranked progressive prefixes (

\mathrm{AWSRC\text{-}P}_{F}

) that support multiple byte budgets without refitting. On Qwen2.5-3B-Instruct, adding

0.162

scope-bits/weight to an RTN-INT4 baseline closes

88.2\%

,

78.9\%

, and

71.3\%

of the PPL, KL, and 11-task mean-accuracy gaps to BF16, respectively. AWSRC achieves the highest mean downstream accuracy in byte-matched residual-codec ablations and improves all metrics across model families with up to 32B parameters.

Zehao Liu, Chuangchuang Fang, Yang Ren

Huawei Technologies Research & Development (UK) Limited, Edinburgh, United Kingdom

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

Aug 23, 2026cs.LG

Beyond Dense Adam States: Adaptive Log-Space Quantization for Memory-Efficient Optimizers

Optimizer-state quantization is commonly designed for Adam's dense, parameter-aligned first- and second-moment arrays. This abstraction breaks for memory-efficient optimizers, whose states may be factored, confidence-modulated, or maintained in a projected space, so similar reconstruction error can produce different update error. We formulate optimizer-state quantization as a joint problem over representation, topology, and update semantics. We then introduce Adaptive Log-Space (AL) quantization for non-negative states. AL fits each block's observed nonzero logarithmic interval and reserves a separate code for exact zero, enforcing

q = 0 \Leftrightarrow x = 0

; signed momentum and state precision remain independently selectable. Controlled probes show that adaptive ranges reduce update error and temporal drift, exact-zero reservation preserves dormant states, and state topology constrains useful block granularity. End-to-end language-model training evaluates the resulting policy across dense, factored, confidence, and projected optimizer states. On TinyLlama-1.1B, AL8 with uniform 8-bit momentum reaches 72.90 perplexity versus 73.54 for bitsandbytes 8-bit AdamW, with comparable optimizer-state storage and higher throughput. CAME matches reference-level final perplexity across three seeds when its non-negative states use AL16, while a semantic grouping-and-protection policy closes most of quantized Adafactor's 100K-step late-loss gap. These results make state topology and update semantics first-class design constraints for optimizer quantization.

Yan Wang

Independent Researcher

Deep Learning Optimization Memory-Efficient Optimization Low-Bit Quantization Neural Network Quantization

Aug 14, 2026cs.LG

QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction

As large language model inference shifts toward lower precision, post-training quantization (PTQ) becomes increasingly brittle, making quantization-aware training (QAT) essential for preserving model quality. However, QAT has a structural mismatch: gradient updates are applied to latent full-precision weights, while the loss and gradients are computed on lossy reconstructions of those weights. This mismatch can lead to suboptimal training trajectories and a higher loss floor. Second-order PTQ methods address a similar problem by minimizing loss-aware reconstruction error, but applying such expensive reconstruction repeatedly during QAT as the weights evolve is impractical. We introduce QUASAR, a QAT method that brings lightweight, loss-aware reconstruction into the training loop. At each training step, QUASAR reconstructs the latent weights by searching over a small set of clipping ranges and fitting dequantization parameters through saliency-weighted least squares. We use an exponential moving average of squared gradients as the per-parameter saliency signal. Our theoretical analysis shows that optimizing QUASAR's reconstruction objective tightens both the convergence and final-loss bounds of QAT. We evaluate QUASAR across four model families and across INT4, INT3, INT2, and NVFP4 quantization formats. QUASAR consistently achieves lower training and evaluation loss than competitive QAT methods and outperforms QAT and PTQ baselines on downstream benchmarks. At INT2, QUASAR improves average accuracy over the best QAT baseline by 13.3 points with quantization-aware distillation and by 10.9 points with QAT on mathematical reasoning data. Notably, after distillation on only about 600M tokens, QUASAR's INT4 Gemma-4 E4B checkpoint outperforms the corresponding QAT checkpoint released by Google, with 66% lower KL divergence and 1.8 points higher average accuracy.

Vincent Counathe, Ben Athiwaratkun, Christopher De Sa +1

Cornell University · Together AI

LLM Quantization Quantization-Aware Training Low-Bit Quantization

Aug 12, 2026cs.CV

HAMP-LIC: Hessian-Aware Mixed-Precision Post-Training Quantization for Learned Image Compression

Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-distortion performance but are hindered by high computational complexity and encoding-decoding mismatches across heterogeneous hardware platforms. Uniform fixed-precision quantization alleviates these issues but suffers severe quality degradation at low bit widths because it ignores differences in the quantization sensitivities of individual layers. To enable efficient and accurate low-bit deployment of pretrained LIC models, we propose HAMP-LIC, a Hessian-aware mixed-precision post-training quantization (PTQ) framework with a four-stage optimization strategy. First, block-wise sensitivity is estimated from the Hessian trace to capture second-order importance. Second, a task-aware refinement module adjusts these sensitivities by jointly considering quantization distortion and rate-distortion performance. Third, guided by the refined sensitivity profile, bit widths are allocated under a global model-size constraint to balance efficiency and reconstruction quality. Finally, block-wise reconstruction using a small calibration set further suppresses quantization error. Experiments on representative LIC models, including Minnen2018 and Cheng2020, demonstrate that HAMP-LIC achieves up to 4.85x model compression with as little as 0.59% BD-rate loss. It consistently outperforms existing fixed- and mixed-precision PTQ methods across multiple datasets while completely eliminating cross-platform encoding-decoding errors.

Yuefeng Zhang

Beijing Institute of Computer Technology and Application, Beijing, China · School of Elite Engineering, Northwestern Polytechnical University, Shaanxi, China

Mixed-Precision Quantization Learned Image Compression Post-Training Quantization Low-Bit Quantization

Aug 12, 2026cs.LG

SoftWater: Class-Aware Rate Allocation for Softmax Quantization

Post-training quantization pipelines routinely leave the softmax output layer in high precision. Yet in small LLMs with modern vocabularies, the head holds 15--30% of all parameters, so a nominal ``2-bit'' model with an fp16 head can store several times as many bits per weight. We pose softmax-layer quantization as a rate-distortion problem under the KL divergence between the original and quantized output distributions. A second-order analysis reveals a class-aware geometry: quantization error is weighted jointly by feature covariance and class-specific softmax curvature. A separability approximation replaces the

Kn\times Kn

Cholesky with one

n\times n

factorization rescaled per class, making the lattice encodable by successive interference cancellation, with both statistics from a single forward pass. The resulting method, SoftWater, gives fine grids to frequent, low-variance classes and coarse grids to rare ones, a large gap under Zipfian token distributions. Across five models from 1B to 32B, SoftWater outperforms the released WaterSIC quantizer (near-optimal under linear-layer WMSE but not output KL) at matched head rates on 59 of 60 test points, using none of that pipeline's refinements and cutting head-induced KL by

6.5\times

--

8.3\times

at 2 bits. On Llama-3.2-1B-Instruct with quantized bodies, a 2-bit head removes 45--60% of stored bytes for a

2.9

--

3.7\%

perplexity increase. Because the class-side statistic comes from calibration data, matching calibration to the deployment domain gives the lowest KL on that domain throughout. On a tied model, a 4-bit head is near-lossless and a 2-bit head costs under 4% perplexity, making head quantization of such models practical.

Joao V. Cavalcanti, Ashia C. Wilson

Department of Electrical Engineering and Computer Science · Massachusetts Institute of Technology · Cambridge, MA 02139, USA

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

Aug 11, 2026cs.LG

ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization

ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (RTN) schemes when quantizing weights near the centers of quantization intervals. Starting from a pretrained LLM, ReRound trains a conditional diffusion model to produce continuous reconstructions of low-bit weights for the LLM. These reconstructed weights act as a guidance signal to disambiguate the rounding direction of weights located close to interval midpoints. To integrate this reconstruction-guided rounding with conventional RTN, ReRound introduces a tolerance metric measuring how far the quantized weight (not the final quantized integer) is away from the midpoint: quantized weights within a tolerance region around midpoints are quantized using diffusion-based reconstructions, whereas weights closer to quantization boundaries are quantized with RTN. By sweeping the tolerance parameter, ReRound generates multiple candidate quantized integer weight matrices and selects the de-quantized weight matrix candidate whose leading singular values most closely match those of the original full-precision weights. This selected candidate determines the tolerance parameter ReRound uses. ReRound is particularly effective for smaller LLMs. Across a range of such models, it consistently outperforms standard RTN for 3-bit and 4-bit weight quantization. ReRound achieves superior accuracy compared to an extensive set of calibration-free methods, remains competitive with calibration-dependent approaches, and operates entirely offline, introducing no additional overhead during low-bit inference. The ReRound strategy represents a new approach for low-bit quantization. The method applies to AI models beyond LLMs. This paper focuses on its applications to small LLMs.

He-Yen Hsieh, H. T. Kung

Harvard University

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

Aug 11, 2026cs.LG

SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features

Quantization-Aware Training (QAT) enables the deployment of quantized models with minimal accuracy degradation. However, in practical scenarios, training labels are often unavailable due to privacy, copyright, or cost constraints. Knowledge Distillation (KD) is a common approach to address this challenge, but we observe that prior work combining QAT with KD suffers from a fundamental limitation: during distillation, the range mismatch between the teacher and the quantized student model induces an unattainable residual, resulting in an irreducible lower bound on the distillation loss. Motivated by this observation, we propose SQuaT (Student-Aware Quantized Teacher Features), a label-free QAT framework with KD that theoretically eliminates this lower bound by applying the student's quantization parameters to quantize the teacher's features during distillation. Through comprehensive experiments across diverse settings, we demonstrate that SQuaT consistently outperforms strong baselines, with particularly pronounced gains in extreme low-bit (e.g., 1- and 2-bit) settings. Furthermore, extensive evaluations across various model design choices show that our approach does not rely on specific architectural assumptions, making it broadly applicable across diverse architectures and quantization settings. The source code is available at https://github.com/lcdbsa522/SQuaT.

HyeonJun Lee, Hyeonsik Jo, Jinwoo Chung +1

Kookmin University

Quantization-Aware Training Self-Supervised Knowledge Distillation Knowledge Distillation Low-Bit Quantization

Aug 10, 2026cs.AI

From Sweep to Seam: Interleaved Cross-Block Post-Training Quantization

Compressing large language models to two bits or fewer is increasingly feasible through block-wise post-training quantization; cross-block variants reconstruct neighboring Transformer blocks within a moving window. In the fixed two-block setting studied here, the matched sequential baseline moves this window through the network once, so errors introduced early in the sweep are not revisited. We propose Interleaved Cross-Block Quantization (ICBQ), a scheduling modification that revisits the boundary pair between consecutive chunks. Each seam pair is refined twice: first at the end of one chunk and again at the start of the next. The method retains the local two-block objective and reuses the calibration inputs of existing block-wise PTQ pipelines. Under stated local contraction and smoothness assumptions, we derive a depth-wise upper-bound comparison in which seam revisits multiply the propagated term while the residual remains bounded independently of depth. In the reported experiments, ICBQ reduces ternary-quantization perplexity relative to the matched Sequential CBQ baseline, yields finite perplexity in configurations where the baseline has severe degradation, and can also be used with 3-bit and 2-bit GPTQ.

Achille Jacquemond, Yuma Ichikawa, Akira Sakai

Fujitsu Limited · RIKEN Center for AIP · Tokai University

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

Aug 8, 2026cs.LG

CurveFP: Co-Designing Numerical Representation and Product Arithmetic for Language Models

Low-precision formats usually optimize scalar fidelity while inheriting conventional product arithmetic. We introduce CurveFP, a block-scaled family that distributes magnitudes across interleaved logarithmic curves. Uniform curve indices make every nonzero product an exact sign and integer-index update, while a rational radix exposes the finite phase schedule required for accumulation. We instantiate the algebra as CurveFP8 E4C3/E5C2 for training and CurveFP7 E3C3 for compact inference. On four 7B-9B models, CurveFP7 beats tensorwise FP8 perplexity with one fewer element bit and stays within 1.32% of native quality. CurveFP8 lowers error in all 36 paired training-GEMM comparisons. Across three matched 3B-token pretraining triplets, it reaches mean BF16-inference perplexity 22.5366 versus 22.5407 for FP8 and has a lower format penalty in every seed. Downstream evaluation shows transfer parity and a consistent WikiText-103 gain. In a preliminary 4x4 Nangate45 spatial accelerator tile, CurveFP8 uses one fewer product register and 4.6% less area than timing-closing FP8 at 500 MHz. These results support CurveFP as a numerical and arithmetic co-design, while leaving system-level efficiency to future study.

Ye Qiao

Department of Electrical Engineering and Computer Science University of California, Irvine Irvine, CA, USA

LLM Quantization Low-Bit Quantization Approximate Computing

Aug 7, 2026cs.LG

CubicQuant: Parametric Non-Uniform Codebooks for High-Throughput LLM Inference with 1-8-Bit Weights

Weight quantization for large-language-model inference must balance adaptive reconstruction levels with representations regular enough for efficient GPU execution. Uniform integers constrain each group to a linear grid. Low-bit floating-point formats use a fixed exponent-mantissa structure, while learned codebooks gain flexibility at the cost of irregular decoding and additional metadata. We introduce CubicQuant, a parametric non-uniform scalar format that preserves a dense integer code stream while adapting reconstruction levels within each weight group. A monotonic cubic curve, specified by two shape parameters and one scale, maps uniformly spaced magnitude codes to non-uniform levels. The family spans 1-8-bit weight payloads, contains symmetric uniform integer quantization as an exact special case, and has effective width B + 64/G bits per weight for payload width B and group size G. We derive population distortion under Uniform, Gaussian, and Laplace distributions, formulate continuous and Dynamic-A8-carrier-aware fitting objectives, and describe direct packed-weight GPU execution. For finite groups of G=128 with 15,360 samples per distribution, W4 CubicQuant reduced reconstruction RMSE relative to optimally clipped four-bit uniform integer quantization by 3.90% on Uniform, 13.49% on Gaussian, and 28.14% on Laplace samples. Relative to the best enumerated four-bit finite floating-point format, the reductions were 3.90%, 9.44%, and 6.27%. Preliminary H200 kernel measurements show a workload-dependent crossover: model-dtype execution is faster for narrow GEMV, while Dynamic A8 becomes favorable as row count grows. The results establish the format's representational promise and direct executability; downstream model quality and cross-device end-to-end performance remain open evaluation questions.

Xuetian Gao

LLM Quantization LLM Inference Acceleration Weight-Only Quantization Low-Bit Quantization Neural Network Quantization

Aug 6, 2026cs.LG

Which Decisions Low-Bit Quantization Breaks, and How to Predict Them

Quantization saves memory by storing model weights with fewer bits. It can also change model decisions, such as whether to call a tool or which option to choose from a finite set. We study these decision changes in 16 language models from 8 families at 4, 3 and 2 bits, across several post-training quantization settings. Our evaluation covers tool use, safety, general knowledge and social bias, using BFCL, XSTest, MMLU, BoolQ, BBQ and synthetic tasks. The decision margin is the score difference between two possible first tokens, measured before and after quantization. Writing the margin before quantization as

m

and the margin after quantization as

m'

, we find an approximately linear relationship across decisions:

m' \approx c m + b

. The slope

c

is usually below one and becomes smaller as precision falls, so quantization progressively shrinks decision margins. The offset

b

is the same for every decision of one kind. Quantization therefore does not simply add random noise, and even a strong preference at full precision can flip. Quantization also affects different kinds of decisions to different degrees. Within tool use, whether to call a tool is often more sensitive than which tool to call: on 400 BFCL tasks, three of five models lose more completed calls than correct tool selections at 3-bit round-to-nearest. Under GPTQ and GGUF far fewer whether-to-call decisions flip than under plain rounding, so there is no single 3-bit failure point. The same relationship predicts how often decisions flip. Across 1,082 combinations of models, quantization settings, bit-widths and decision types, we fit the slope, the offset and the spread around the fitted line on half of the decisions and predict the flip rate on the other half. The predicted flip rate differs from the observed flip rate by a median of 1.0 percentage point, while reusing the flip rate of the first half misses by 1.3.

Zekun Wu, Swati Dhiman, Adriano Koshiyama

Holistic AI · UCL Centre for Artificial Intelligence, University College London

Post-Training Quantization Low-Bit Quantization Neural Network Quantization Tool Use

Aug 4, 2026cs.CV

Low-Dimensional High-Leverage Subspace Optimization: Beyond Full-Parameter Coupled Training for Neural Network Quantization

Low-bit quantization suffers severe accuracy degradation on compact networks, rooted in the dominant full-parameter coupled training paradigm that ignores parameter subspace heterogeneity. Their limited feature redundancy leaves little room to absorb quantization errors. Conventional pipelines adopt monolithic optimization: PTQ reconstructs fixed pretrained models without improving inherent quantization friendliness; QAT updates all parameters jointly, suffering from gradient coupling between backbone weights and calibration parameters. In this paper, we identify normalization affine parameters as a low-dimensional high-leverage subspace dominating quantization robustness, and propose Normalization Affine Preconditioning (NAP) for targeted subspace optimization. For PTQ, NAP freezes backbone weights and fine-tunes only affine parameters under the target fake-quantization graph on full-precision models, proactively boosting quantization friendliness before downstream reconstruction. For QAT, we introduce an alternating QAT-NAP schema that decouples feature learning and numerical calibration, breaking the performance ceiling of saturated joint training. Theoretical analysis confirms BN affine parameters fully cancel the channel-wise affine component of quantization distortion, while nonlinear rounding and clipping residuals form the irreducible error boundary; distillation-guided NAP acts as directional flatness optimization, projecting teacher-student logit mismatch onto the restricted subspace. Experiments on ImageNet and CIFAR-100 show NAP recovers severely collapsed low-bit quantization, consistently boosts reconstruction-based PTQ, and outperforms saturated full-parameter QAT with negligible tuning cost. This work reveals the principle of targeted low-dimensional subspace optimization, offering a new perspective beyond full-parameter coupled training for efficient deep learning.

Peng Xia, Junbiao Pang, Zheng Huang

School of Information Science and Technology, Beijing University of Technology, Beijing, China

Quantization-Aware Training Post-Training Quantization Low-Bit Quantization

Aug 4, 2026cs.LG

Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving Transforms

Long-context LLM decoding reads the key-value (KV) cache at every step. Loading it takes longer than computing attention over it, so throughput is bandwidth-bound. Hence, reducing the cache size can raise both decoding speed and serving capacity. The challenge is to reduce cache size while preserving the attention products, keeping reconstruction cheap, and using a fixed per-token bit count. At two bits per element, the most competitive methods rely on orthogonal transforms. However, existing techniques are either data-oblivious or use the query statistics without deriving the transform from a distortion criterion. Moreover, they rely on transforms built on top of random or Hadamard rotations, which equalize variances across entries rather than compacting energy, and fixed-width scalar quantizers, which are suboptimal at low rates. In this paper, we formulate KV cache quantization as a transform coding problem in which distortion is the error in the attention products. We derive closed-form optimal transforms for keys and values from calibration statistics, under a high-resolution model. We show that the optimal key transform is not orthogonal and satisfies a generalized Parseval relation: the attention-aware distortion becomes mean-squared error (MSE) in the transform domain. Thus, we can use MSE-optimal vector quantizers applied directly to the transformed key coefficients. To meet the fixed-width layout requirement, we show that grouping coefficients into equal-volume partitions makes equal-size codebooks attain the variable-rate optimum under the same high-resolution model. At two bits per element, our method, termed NOVA-KV, recovers most of the long-context retrieval accuracy lost by scalar quantization methods at comparable throughput.

Samuel Fernández-Menduiña, Amir Ziashahabi, Eduardo Pavez +2

Department of Electrical and Computer Engineering, University of Southern California

KV Caching Vector Quantization KV-Cache Quantization Low-Bit Quantization

Aug 4, 2026cs.LG

Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs

Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput. However, conventional quantization methods typically require a separate checkpoint for each target bit-width. We introduce Recurrent Residual Quantization (RRQ), a post-training quantization (PTQ) framework that represents weights as a low-bit quantized base together with a sequence of quantized residual corrections, enabling multiple effective precisions from a single checkpoint. Starting from a 2-bit model obtained via post-training quantization (PTQ) or round-to-nearest (RTN), RRQ progressively adds lightweight 2-bit residuals generated via RTN to construct 4-, 6-, and 8-bit representations. The method is calibration-free and avoids joint multi-bit optimization. In our Qwen3-8B setup, the full all-RTN 2-/4-/6-/8-bit package is constructed in 1,293 seconds, 3.3 times faster than the measured MatGPTQ construction. Experiments on six recent LLMs show competitive accuracy at 6 and 8 bits, with model-dependent behavior at 4 bits. The code will be made publicly available upon publication.

Yu Luo, Bo Dong, Wenhua Cheng +1

Intel

Mixed-Precision Quantization LLM Quantization Post-Training Quantization Low-Bit Quantization

Aug 3, 2026cs.LG

Output-Aware Rotation for INT2 KV-Cache Quantization

The key-value (KV) cache has become a major memory and bandwidth bottleneck in long-context large language model inference, making ultra-low-bit quantization increasingly important. However, existing rotation-based INT2 methods optimize cache statistics or proxy errors before the complete attention readout, even though the model is ultimately affected by the error propagated through attention and the output projection

W_O

. To address this mismatch, we propose \textit{OptR}, an output-aware rotation method that minimizes post-

W_O

attention-output error. OptR decomposes the post-

W_O

attention-output error into key- and value-induced terms and learns per-head orthogonal corrections through the full INT2 quantization and attention path. OptR further applies an attention-equivalent key reparameterization to reduce large channel-wise offsets without changing the softmax distribution. Across three models and five reasoning and coding benchmarks, OptR consistently improves both QuaRot and OSCAR and strengthens long-context retrieval, while preserving the paged KV-cache format with negligible inference overhead.

Vincent-Daniel Yun, Woosang Lim, Minsoo Cheong +4

University of Southern California · Seoul National University · Inha University

LLM Inference KV Caching Rotation-Based Quantization Attention Quantization KV-Cache Quantization Low-Bit Quantization+1

Jul 30, 2026cs.AR

LightRot: A Light-Weighted Rotation Scheme and Architecture for Accurate Low-Bit Large Language Model Inference

As large language models (LLMs) continue to demonstrate exceptional capabilities across various domains, the challenge of achieving energy-efficient and accurate inference becomes increasingly critical. This work presents LightRot, a lightweight rotation scheme and dedicated hardware accelerator designed for low-bit LLM inference. The proposed architecture integrates Grouped Local Rotation (GLR) and Outlier Direction Aligning (ODA) algorithms with a hierarchical Fast Hadamard Transform (FHT)-based rotation unit to address key challenges in low-bit quantization, including the energy overhead of rotation operations. The proposed accelerator, implemented in a 28nm CMOS process, achieves a peak energy efficiency of 27.4 TOPS/W for 4-bit inference, surpassing prior state-of-the-art designs. Unlike conventional approaches that rely on higher-precision inference or evaluate on basic language modeling tasks like GPT-2, LightRot is optimized for advanced models such as LLaMA2-13B and LLaMA3-8B. Its performance is further validated on MT-Bench, demonstrating robust applicability to real-world conversational scenarios and redefining benchmarks for chat-based AI systems. By synergizing algorithmic innovations and hardware efficiency, this work sets a new paradigm for scalable, low-bit LLM inference, paving the way for sustainable AI advancements.

Sangjin Kim, Yuseon Choi, Jungjun Oh +2

PIM Semiconductor Design Research Center (AI-PIM), Daejeon 34141, South Korea

LLM Quantization AI Accelerator Inference Rotation-Based Quantization LLM Inference Acceleration Low-Bit Quantization

Jul 30, 2026cs.AR

GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM Inference

Low-bit quantization is essential for efficient LLM inference, and both rotation and fine-grained group quantization have shown individual promise. However, their combination often leads to accuracy degradation or hardware overhead due to a mismatch between the global nature of rotation and the localized behavior of group scaling. We propose GyRot, a quantization framework and hardware accelerator that bridges this gap through algorithm-hardware co-design. GyRot introduces Coarse Rotation, Fine Grouping (CoRFiG) and Harmonic-Aligned Permutation (HAP) to enable cooperative integration of rotation and group quantization, enhancing quantizability while relaxing scaling factor precision. To further reduce hardware cost, we reformulate asymmetric quantization and introduce a zero-point rounding strategy that enables fully integer dequantization. Implemented on an INT4-based tensor PE architecture, GyRot achieves state-of-the-art 4-bit accuracy across LLaMA-family models, while delivering up to 3.4x speedup and 3.6x energy efficiency over baseline LLM accelerators. These results validate GyRot's practical effectiveness for scalable and energy-efficient LLM deployment.

Sangjin Kim, Yuseon Choi, Byeongcheol Kim +2

School of Electrical Engineering, Korea Advanced Institue of Science and Technology (KAIST)

AI Accelerator Inference Rotation-Based Quantization LLM Inference Acceleration Low-Bit Quantization Neural Network Quantization

Jul 28, 2026cs.AI

How Small Can You Go? A Controlled Study of LoRA Rank, Target Modules, and Quantization Trade-offs for Text-to-SQL on a 60M-Parameter Model

Parameter-efficient fine-tuning (PEFT) and low-bit quantization are now standard tools for adapting language models under tight compute budgets, yet their interaction is most often studied on billion-parameter models where the design space is expensive to explore. We ask a complementary question: on a specific, fully reproducible 60M-parameter encoder-decoder model (T5-small) and a single-table text-to-SQL benchmark (WikiSQL), how much task accuracy does each efficiency knob actually cost? We run a controlled, single-variable study over (i) LoRA rank r in {2, 4, 8, 16, 32}, (ii) the set of adapted modules, and (iii) numerical precision. We report task accuracy alongside system-level metrics including trainable parameters, peak training memory, inference latency, and throughput, and frame adaptation as a constrained trade-off rather than an accuracy-only objective. Our results show that LoRA with r=16 recovers within 11.6 percentage points of full fine-tuning accuracy (59.6% vs. 71.2% exact-match) while training fewer than 1% of parameters and consuming 31% less peak GPU memory. Within this setting, rank beyond r=16 yields no measurable accuracy gain. QLoRA with INT8 and NF4 quantization achieves comparable accuracy (52.8% and 53.2%) at dramatically lower memory cost (0.60 GB each), demonstrating a compelling trade-off for memory-constrained deployments. All code, configurations, and logs are released for full reproducibility.

Mahendra Singh Rathor, Anagheem Azzam

Independent Researcher · Jaipur, India · Hamburg, Germany

Memory-Efficient Fine-Tuning Small Language Models Low-Rank Adaptation Text-to-SQL Low-Bit Quantization Parameter-Efficient Fine-Tuning

Jul 26, 2026cs.CL

Research Report on Noise-Shaped One-Bit Coefficients in Discrete Polynomial Fourier Extension

This report studies noise-shaped one-bit coefficients in normalized discrete polynomial Fourier extension. For first-order Sigma-Delta quantization, the error is written as

e_k=u_k-q_k=Δv_k

with a uniformly bounded state. Discrete summation by parts then yields variation estimates for complex weights and an

O(N^{-1})

approximation rate on compact parameter sets. For the parabolic phase

φ_{x,t}(ξ)=xξ+tξ^2

, the bound is expressed through

J(x,t)=\int_0^1 |x+2tξ|dξ

, and the uniform

N^{-1}

rate is shown to be sharp over the admissible input class. Higher-order finite-record identities are derived with all endpoint traces retained. Under endpoint compatibility, or after explicit boundary correction, an

r

th-order noise-shaped error

e=Δ^r v

gives

O(N^{-r})

decay for sufficiently smooth weights and

O(N^{-(r-1+α)})

decay for

C^{r-1,α}

weights. Exact

L^2

orthogonality identities, fourth-moment formulas, local kernel estimates, and oscillatory transfer bounds are also established. Extensions to polynomial phases, multidimensional parameter families, growing observation regions, and correlated state models are included.

Shengquan Wang

[cs.CL]

Low-Bit Quantization

Jul 25, 2026cs.LG

When Can Depth Replace Precision? A Resource Theory of Quantized Neural Computation

When can additional low-bit residual computation replace missing numerical precision for a fixed input-output map? We model a quantized residual system over a fixed horizon as a pure schedule selecting fields from a declared low-bit operation library, and use relaxed controls to characterize its infinite-depth limit. The distance from the target to the closed relaxed reachable set is the exact structural floor: no increase in depth can remove it for that library. Pure schedules approach the relaxed class at rate

O(D^{-1})

under bounded-variation time dependence and

O(D^{-\vartheta}+D^{-1})

under Holder dependence of exponent

\vartheta

. Execution arithmetic can reverse this conclusion: full-state write-back introduces a

Dρ_z

penalty and can freeze residual updates, whereas increment error feedback replaces this growth by a bounded carry term and obeys an exact common-lattice conservation law. A fixed-teacher converse makes this rate sharp: for coherent depth-

L

first-order high-precision comparators, accuracy matching requires

D=Θ(L)

. Learned codebooks add a metadata resource, while state-dependent routing introduces hybrid event conditions. Verified primal and dual bounds yield feasible, impossible, or unresolved decisions before training. Companion software implements the workflow, and Lean 4 machine-checks the exact discrete core. Depth replaces precision only relative to a declared library, horizon, execution semantics, and routing model.

Mojtaba Soltanalian

Department of Electrical and Computer Engineering University of Illinois Chicago 851 S. Morgan St., MC 154 Chicago, IL 60607, USA

Low-Bit Quantization Neural Network Quantization

Jul 25, 2026physics.optics

Approximate reservoir computing with a semiconductor laser for reducing energy consumption

Photonic reservoir computing is a promising physical machine-learning technique for predicting time-series data. The quantization of the response signal from the reservoir is required for the implementation of photonic reservoir computing, and the number of quantization bits and sampling frequency need to be optimized to achieve high performance and low energy consumption. However, few studies have been reported to investigate the effect of bit quantization and sampling frequency. In this study, we introduce a concept of approximate reservoir computing with a semiconductor laser by quantizing the amplitude of node states in the reservoir and output weights. We evaluate the performance of a chaotic time-series prediction task and energy consumption per sample. We achieve significant reduction of energy consumption by optimizing the number of quantization bits, the sampling frequency, and the injection current of the semiconductor laser, while maintaining the prediction performance.

Tatsuki Ito, Kazutaka Kanno, Satoshi Kawakami +1

Department of Information and Computer Sciences, Saitama University, 255 Shimokubo, Sakura-ku, Saitama City, Saitama 338-8570, Japan · Faculty of Information Science and Electrical Engineering, Kyushu University, 744 Motooka, Nishi-ku, Fukuoka 819-0395, Japan

Energy-Efficient ML Reservoir Computing Photonic Computing Low-Bit Quantization

Jul 22, 2026cs.LG

GaugeQuant: Online Learning of Quantization-Optimal Bases from LLM Symmetries

Transformers are known to have internal continuous symmetries that leave outputs invariant, while modifying quantization. GaugeQuant leverages this in-training by introducing a LogSumExp term to the loss that breaks the symmetries, thus selecting a basis that minimizes activation outliers. A stop-gradient operator ensures that only rotation matrices are updated, yielding the language modeling objective completely unaltered. Our requires no specific calibration data, no quantization simulation, and adds negligible training overhead. With the LLaMA-2 7B model under W4A4 quantization with group size 128, perplexity drops from 8.22 to 6.73, competing with post-training methods that require frozen models and calibration datasets. Under W4A16, perplexity drops from 11.16 to 5.45. Code is available at https://github.com/MPedraBento/gauge-quant.

Miguel P. Bento, João F. Seabra

Independent Researcher · Lisbon, Portugal

LLM Quantization Rotation-Based Quantization Activation Quantization Low-Bit Quantization

Jul 21, 2026cs.LG

Contraction-Gauge Preconditioning for Quantized Matrix Multiplication

We study low-precision computation of C=AB with both factors quantized. We derive an exact finite-dimensional identity for the expected squared product error under independent, zero-mean entrywise errors with known variance fields; it holds exactly for non-overloading subtractive dither and for independent stochastic rounding, and we empirically assess deterministic round-to-nearest (RTN). Using the product-preserving equivalence AB=(AT)(T^{-1}B), we formulate contraction-gauge preconditioning: jointly choosing a factor representation and its sharing pattern before quantization. Preconditioning can reduce product error but may require extra transformed, quantized copies of the opposite operand: a shared transform needs one copy, a block-specific transform up to one per block. Within the bounded family of positive diagonal gauges (folds), a geometric program computes a globally optimal shared fold and a linear program decides whether the identity fold is already optimal. For other families we derive computable selection statistics -- tail index for scaling, profile spread for partitioning, coherence and weighted-Gram energy for rotations, slice-energy covariance for hierarchy depth -- with upper bounds for ranking heuristic candidates. Across twelve linear products from a trained three-block image classifier, median within-product rank correlations between dither-model predictions and deterministic-RTN errors are 0.937 at 8 bits and 0.918 at 4 bits. The GP fold cuts held-out product error over the identity fold by 18.0% (8-bit) and 20.5% (4-bit) in geometric mean, beats a SmoothQuant-style grid baseline at both precisions and on ten of twelve products, and lowers composed logit MSE by 15.4% and 26.4%. We thus provide exact stochastic product-error accounting, certified selection within the diagonal family, and a common objective for evaluating reusable transform candidates under RTN.

Piyush Sao, Narasinga Miniskar, Pedro Valero-Lara +2

Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, USA

Post-Training Quantization Low-Bit Quantization Neural Network Quantization

Jul 16, 2026cs.NE

Cross-Layer Error Compensation and Finite-Sample Feature-Statistics Matching for Extreme Low-Bit Quantization of Large Language Models

Layer-wise post-training quantization of large language models minimizes each layer's reconstruction error in isolation, allowing quantization errors to accumulate across depth and causing severe degradation in extreme low-bit regimes. We formulate quantization as a joint optimization over the discrete codes and scales of all layers, driven by two mechanisms: (i) cross-layer error compensation, which maintains the network-level accumulated error through the recursion e_{l+1} = A_l e_l + q_l, with a propagation operator A_l derived from the layer's input differential and a local quantization residual q_l evaluated at teacher features; and (ii) finite-sample feature-statistics matching, which aligns means, projected covariances, and centered empirical kernels between the full-precision and quantized networks under relative normalization. We prove that instantiating the propagation operator as a finite difference of the quantized network makes the recursion exact for arbitrary nonlinear layers, enabling an efficient forward-difference implementation. Binary weights are optimized via a mirror-descent parameterization u = tanh(beta*z) with annealed inverse temperature and group-wise log-scales. On Qwen2.5-1.5B with 1.125-bit group-binary weights, error compensation alone reaches a perplexity ratio of 9.56 +/- 0.15 over the FP16 teacher, outperforming logit distillation (14.09 +/- 0.53; 32 percent relative, more than 8 sigma over 3 seeds) and layer-local reconstruction by two orders of magnitude. The same objective transfers unchanged to 4-bit quantization (1.060 vs. 1.088 for layer-local). Out-of-domain evaluations (C4, CNN/DailyMail) show the advantage of error compensation grows off-domain, while statistics matching keeps feature-statistics discrepancy low off-domain (0.42-0.88 vs. 1.41-2.99 without it), revealing a complementary division of labor between the two mechanisms.

Ryona Noda

Ryo Noda

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

Jul 16, 2026cs.AR

ExaGEMM: Exploration Framework for CPU-Driven ML Inference via Associative In-Register Computing for Low-Bit GEMM

Low-bit GEMM is increasingly central to efficient ML inference, yet very-low-bit execution remains a poor fit for conventional CPUs. Practical deployment spans fragmented regimes-from 1/2/4-bit weights to varying activation precision-whose feasibility, reuse opportunity, and support cost differ under fixed SIMD and register-file budgets, making lightweight CPU support selection a first-class design problem. We present ExaGEMM, a workload-aware codesign and exploration framework for CPU-native low-bit GEMM via register-resident LUT execution. The key insight is that existing SIMD datapaths already cover table generation and accumulation; the only new hardware is an in-register select/feed mechanism with explicitly modeled cost. ExaGEMM co-explores parameterized kernels and lightweight SIMD ISA support using analytical models of register feasibility, compute cost, memory traffic, and hardware overhead, pruning the candidate space by 99.2% before simulation. It then identifies non-dominated support points and generates ISA specs, gem5 patches, and GEMM kernels for validation. Across representative ML models and CPU targets, ExaGEMM improves latency by 13.29x over software-only baselines, while showing that workload-aware frontier selection is especially important for mixed-precision LLM workloads.

Hyunwoo Oh, Suyeon Jang, Hanning Chen +3

University of California, Irvine

Efficient Neural Network Inference Hardware-Software Co-Design Low-Bit Quantization

Jul 13, 2026cs.CV

Efficient Tuning Before Low-Bit Post-Training Quantization for Stochastic Gradient Descent-optimized Models

Post-training quantization (PTQ) compresses deep neural networks for deployment under limited memory and computational budgets. However, low-bit (i.e., 2-bit or 4-bit) PTQ often suffers from substantial performance degradation. Most existing PTQ methods operate on an unconstrained full-precision (FP) model and primarily address quantization errors through post-hoc reconstruction. We argue that low-bit PTQ accuracy is limited not only by post-quantization error minimization, but also by the quantization-error tolerance of a FP model itself. In this paper, we propose Efficient Tuning Before Quantization (ETBQ), a pre-conditioning tuning stage for Stochastic Gradient Descent (SGD)-optimized models before PTQ. During tuning, the FP model is optimized under perturbations sampled from the error distributions of weight and activation quantization, guiding the model toward a loss-landscape region that is less sensitive to the subsequent PTQ. Unlike QAT, ETBQ does not train a fake-quantized deployment model, which is computationally and memory intensive. Instead, ETBQ outputs a FP model that can be used by any PTQ backend. Experiments on CIFAR-100, Tiny-ImageNet, ImageNet, and Cityscapes provide consistent evidence that ETBQ improves low-bit PTQ across diverse tasks. Under W2A4 settings, e.g., ETBQ improves over naive PTQ by 2.14% top-1 accuracy on Tiny-ImageNet and by 5.80% mIoU on Cityscapes. Code is available at https://github.com/xpxpxp2001xpxpxp/ETBQ.

Peng Xia, Junbiao Pang, Muhammad Ayub Sabir

School of Information Science and Technology, Beijing University of Technology, Beijing 100124, China

Activation Quantization Post-Training Quantization Low-Bit Quantization

Jul 9, 2026cs.AI

The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs

Post-training quantization is widely used to deploy large language models in resource-constrained settings, yet its evaluation relies almost exclusively on accuracy and perplexity. We show that these metrics fail to capture behavioral changes induced by quantization. We introduce correctness agreement, a decision-level metric that measures overlap in correct predictions between a base model and its quantized variants, independent of absolute accuracy. Across multiple models and quantization schemes from 8-bit to 2-bit, we find that behavioral divergence emerges under moderate quantization even when task performance appears preserved. To explain this effect, we analyze quantization as a structural operator on attention weights and quantify layer-wise distortions using statistical and distributional measures. Our results reveal non-linear breakpoints at low bit-widths and show that query and key projections are consistently more sensitive than value and output projections. These findings expose an illusion of equivalence between base and quantized models and motivate behavioral evaluation beyond conventional performance metrics.

Baha Rababah, Cuneyt Gurcan Akcora, Carson K. Leung

Department of Computer Science, University of Manitoba, Canada · AI Initiative, University of Central Florida, USA

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