Post-Training Quantization

Also known as PTQ

Ask about this topic

Overview

Post-training quantization (PTQ) converts a trained model to lower-precision numbers without retraining it, reducing memory use and enabling inference on constrained hardware. Methods range from rounding and calibration-based scaling to Hessian-aware reconstruction such as GPTQ, rotations and outlier handling, codebooks, and mixed-precision allocation across layers, experts, or caches. Calibration usually uses a small set of representative inputs, while evaluation spans language-model perplexity and reasoning, vision accuracy, multimodal tasks, and real-device latency and memory. The central tension is that moderate precision often retains task quality, while very low bit widths can amplify errors and alter behavior; calibration and hardware-aware kernels help, but accuracy, behavioral fidelity, and deployment speed do not always move together.

Latest papers

CardsList

360 papers70 papers in the last four weeks, up 46% on the four weeks before. 0.4% of all new papers.

May 26, 2026

Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression

We propose Hurwitz Quaternion Multiplicative Quantization (HQMQ), a calibration-free method for KV cache compression of large language models. HQMQ treats each 4-element chunk of K or V as a quaternion and quantizes its unit direction to the product qp⋅qsq_p \cdot q_s, where qpq_p ranges over the 24-element Hurwitz group 2T2T (the 24 vertices of the 24-cell on S3S^3, pairwise angle 60∘60^\circ) and qsq_s ranges over a per-(layer, head) secondary codebook of SS random unit quaternions. The multiplicative composition yields 24S24S effective codewords at SS stored parameters; random initialization suffices because left-multiplication is an S3S^3 isometry, so seeded codebooks vary in end-task ppl by <1.5%<1.5\%. A per-batch median-multiplier outlier extraction step (C=3C{=}3, no calibration) handles modern outlier-heavy architectures. We evaluate on five modern open models: Mistral-7B (dense MHA), Llama-3-8B and Qwen2.5-7B and Qwen3-8B (dense GQA), and gpt-oss-20b (sparse MoE). On Mistral-7B and Qwen3-8B, HQMQ matches fp16 within 0.020.02--0.030.03 ppl points at ∼\sim5 bits. On Qwen2.5-7B and Qwen3-8B, where naive int4 collapses to 104+10^4{+} ppl, HQMQ + Med3×\times recovers fp16 quality within 0.020.02--0.100.10 ppl points at ∼\sim5 bits. HQMQ Pareto-dominates naive int by 33--1900×1900\times at matched bits across all five models, and downstream zero-shot accuracy matches fp16 at 3.793.79 bits on Mistral. Against the strongest calibrated KV-quantization baseline, HQMQ at 3.793.79 bits matches KIVI-4 (∼4.5\sim 4.5 bits) within ∼1{\sim}1 pt on CoQA, 0.60.6 pts on TruthfulQA, and 2.32.3 pts on GSM8K, at 16%16\% fewer bits and without a calibration pass. At the storage level, HQMQ delivers up to 5.05×5.05\times KV compression, shrinking a Llama-3-70B 128k-context cache from 43 GB to 8.5 GB.

Kabir Swain, Sijie Han, Daniel Karl I. Weidele +3

Massachusetts Institute of Technology, Cambridge, MA, USA · University of Toronto, Toronto, Canada · IBM Research, Cambridge, MA, USA.

KV-Cache CompressionLLM QuantizationKV CachingNeural Network QuantizationKV-Cache QuantizationPost-Training Quantization+1
AskPDF
May 26, 2026

Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V

W4A4 quantization of large video diffusion Transformers offers substantial memory savings but is hindered by two main challenges: sparse large-magnitude activation outliers, and strongly timestep-dependent activation distributions across the multi-step denoising trajectory. These difficulties are compounded by Wan2.2-I2V's two-expert Mixture-of-Experts DiT design, whose high-noise and low-noise experts exhibit distinct quantization sensitivities that a single global calibration policy cannot capture. We propose a post-training quantization framework combining SVDQuant-based low-rank outlier compensation, GPTQ-based reconstruction-aware residual weight quantization, and timestep-bin-wise per-layer activation clipping-ratio search conducted independently for each expert. On the OpenS2V-Eval benchmark, our method reduces peak GPU memory by 59.3% relative to the BF16 baseline while incurring only a 0.9% drop in VBench average score and a 2.3% drop in Imaging Quality, demonstrating that expert- and timestep-aware calibration is essential for high-fidelity W4A4 inference on MoE video DiTs.

Junhao Wu, Dezhong Yao, Hai Jin

School of Computer Science and Technology, Huazhong University of Science and Technology Wuhan, Hubei, China 430074

Video Diffusion ModelsDiffusion TransformerDiffusion Model Quantization4-Bit QuantizationActivation QuantizationPost-Training Quantization+1
AskPDF
May 26, 2026

WINDQuant: Weight-Informed Neural Decision-Making for Global Mixed-Precision LLM Quantization

Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in the ultra-low-bit regime remains challenging. Existing post-training methods often suffer from severe accuracy degradation, while quantization-aware training requires costly retraining and additional resources. Moreover, most mixed-precision strategies rely on coarse-grained or heuristic sensitivity analysis that overlooks fine-grained variations within weight matrices. We propose WINDQuant, a reinforcement-learning-based allocation controller for ultra-low-bit LLM quantization. Rather than introducing another low-level quantization operator, WINDQuant learns how to assign bit-widths and quantization treatments to fine-grained column chunks under a global storage budget. By operating at the column-chunk level, WINDQuant enables flexible and fine-grained precision assignment within layers under a global target bit-width. The implementation combines PPO with activation-aware calibration, lightweight per-unit quantizer fitting, and explicit effective-bit accounting of the learned mixed-precision plan. Experiments on LLaMA models demonstrate that WINDQuant achieves competitive performance in ultra-low-bit settings while reducing optimization overhead relative to retraining-based approaches, highlighting reinforcement learning as a practical controller for adaptive mixed-precision quantization.

Phong Nam Huu Nguyen, Khoi M. Le, Cong-Duy T Nguyen +3

CAIR, VinUniversity, Vietnam

Mixed-Precision QuantizationLLM QuantizationPost-Training QuantizationNeural Network Quantization
AskPDF
May 26, 2026

Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2

This report describes Tail-Aware HiFloat4, our submission to the low-bit text-to-video generation quantization challenge. Our method adapts the public ViDiT-Q post-training quantization pipeline to Wan2.2 under the HiFloat4 numerical format. We quantize the main linear layers in both Wan2.2 transformer modules with W4A4 HiFloat4 fake quantization, keep numerically sensitive boundary modules in high precision, and introduce an activation-tail-aware percentile calibration module for channel-mask construction. Together with compact PTQ-state restoration, this design reduces the influence of rare calibration outliers while keeping the runtime HiFloat4 arithmetic and sampling pipeline unchanged.

Zhanfeng Feng, Shuai Guo, Xin Di +3

University of Science and Technology of China Hefei, China

Video Diffusion Models4-Bit QuantizationActivation QuantizationPost-Training Quantization
AskPDF
May 25, 2026

QAM-W: Joint 2D Codebook Quantization for LLM Weights via Hadamard Rotation and Activation-Aware Scaling

Scalar post-training quantizers discard pairwise coordinate structure within weight rows. We introduce QAM-W (Quadrature Amplitude Modulation for Weights), a codec that recovers this structure: each row is L2-normalized, block-Hadamard rotated, paired into 2D coordinates, and quantized against a single Lloyd-Max codebook trained on the unit circular Gaussian, with activation-aware per-channel scaling. In a cross-model study spanning five LLMs from four families (1.1B--13B parameters) and eight quantized configurations, the activation-aware variant at ≈5.5\approx 5.5 bpw stays within ±0.4%\pm 0.4\% of BF16 WikiText-2 perplexity on every model, matching the SmoothQuant W8A8 quality envelope at 32%32\% fewer weight bits. Joint 2D coding outperforms polar (amplitude ×\times phase) coding by 2--15pp ΔΔPPL at equal bitrate, and paired KL against BF16 tracks ΔΔPPL% at Spearman ρ=0.99ρ= 0.99 across 37 (method, model) rows, consistent with a monotone composite bound from codec distortion to KL divergence. A 3.5bpw variant is competitive on quantization-tolerant architectures. At strict 4bpw, the rotated-codebook frontier method QTIP outperforms QAM-W; the contribution is the quality-preserving 5--6bpw band.

Preetam Sharma, Kacper Dobek

Independent Research · Institute of Computing Science Poznan University of Technology, Poznan, Poland

LLM QuantizationRotation-Based QuantizationVector QuantizationWeight-Only QuantizationPost-Training Quantization
AskPDF
May 25, 2026

GoQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Transformer Quantization

The deployment of Large Language Models (LLMs) and Vision Transformers (ViTs) on edge devices is significantly constrained by memory limitations and the critical timing bottlenecks introduced by dense Multiply-Accumulate (MAC) arrays. In the ultra-low bit regime, logarithmic Power-of-Two (PoT) quantization provides a hardware-efficient alternative by replacing MAC operations with bit-shifts. However, the non-uniform exponential lattice is inherently limited by a Low Angular Resolution Regime, a structural flaw that becomes particularly pronounced at sub-4-bit thresholds, leading to a notable degradation of high-dimensional feature manifolds. To address this geometric limitation, we propose Geometric Orthogonal Residual Projection Quantization (GoQuant), an algorithm-hardware co-design framework. By formulating quantization as a dual-basis geometric projection, GoQuant adaptively synthesizes a higher-resolution residual lattice using strictly shift-and-add operations. Furthermore, its analytical solver offers a practical alternative to computationally intensive gradient-based optimization, reducing the full-model calibration time for LLaMA-2-7B to approximately 15 minutes. Extensive evaluations demonstrate GoQuant's applicability across modalities and its hardware efficiency. Under the 3-bit (W3/A16) constraint, it achieves a perplexity of 6.10 on LLaMA-2-7B, comparing favorably to conventional MAC-intensive baselines like AWQ without relying on asymmetric scaling, while maintaining competitive accuracy in 4-bit scenarios. At the silicon level, standard-cell RTL synthesis at a 28nm node indicates that GoQuant effectively mitigates the timing bottlenecks associated with dense multiplier trees. By flattening the combinational logic depth, our parallel shift-and-add datapath reduces the critical path delay to 0.35 ns.

Maoyang Xiang, Tao Luo, Bo Wang

Information Systems Technology and Design Singapore University of Technology and Design Singapore · Institute of High Performance Computing (IHPC) Agency for Science, Technology and Research (A*STAR) Singapore

LLM QuantizationEfficient Neural Network InferencePost-Training QuantizationLow-Bit QuantizationNeural Network Quantization
AskPDF
May 25, 2026

InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization

Low-bit activation quantization remains a major bottleneck in efficient large language model (LLM) deployment. The difficulty is not only that activations contain outliers, but that their distributions are often poorly matched to a low-bit uniform quantizer. Existing post-training quantization (PTQ) methods suppress peaks, balance channels, or minimize reconstruction error, yet they rarely specify what activation distribution is actually easy to discretize. As a result, activations may appear numerically smoother while still incurring large quantization error because the quantization range remains wide or most values collapse into a few levels near the mean. We recast activation transformation as quantizer-facing distribution design and analyze quantization error from an information-theoretic perspective. Our analysis shows that quantization-friendly activations should jointly have a smaller numerical range and sufficient dispersion within that range. Guided by this analysis, we propose InfoQuant, a train-free method that employs Peak Suppression Orthogonal Transformation (PSOT) to shape activations into more quantization-friendly distributions. We further introduce adaptive outlier-token selection to improve the robustness of PSOT during optimization. Across multiple LLM families, InfoQuant consistently outperforms prior PTQ and end-to-end training baselines. Under W4A4KV4, it preserves 97% of floating-point accuracy on average and reduces the LLaMA-2 13B performance gap by 42% over the previous state of the art. Code is available at https://github.com/LLIKKE/InfoQuant

Ke Li, Dong An, Xiaoling Zang +6

School of Software Technology, Zhejiang University · Ant Group · College of Computer Science and Technology, Zhejiang University of Technology +3

LLM QuantizationActivation QuantizationPost-Training QuantizationLow-Bit QuantizationNeural Network Quantization
AskPDF
May 21, 2026

GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs

Mixture-of-Experts Large Language Models (MoE-LLMs) achieve strong performance but incur substantial memory overhead due to massive expert parameters. Mixed-precision quantization mitigates this cost by allocating expert-wise bit-widths based on their importance, approaching the accuracy-memory Pareto frontier and enabling extreme low-bit quantization. However, existing methods rely on layer-wise importance estimation and overlook router shifts induced by quantization, resulting in suboptimal allocation and routing. In this work, we propose Global Expert-level Mixed-precision Quantization (GEMQ) to overcome these limitations via (1) a global linear-programming formulation that captures model-wide expert importance based on quantization error analysis, and (2) efficient router fine-tuning to adapt routing to quantized experts. These components are integrated into a progressive quantization framework that iteratively refines importance estimation and allocation. Experiments demonstrate that GEMQ significantly reduces memory and accelerates inference with minimal accuracy degradation. Source code is available at https://github.com/jndeng/GEMQ .

Jianing Deng, Song Wang, Dongwei Wang +4

University of Pittsburgh · University of Central Florida · University of Arizona +1

Mixed-Precision QuantizationLLM QuantizationMixture-of-Experts Language ModelsLLM Inference AccelerationMixture-of-Experts QuantizationPost-Training Quantization+1
AskPDF
May 20, 2026

MGVQ: Synergizing Multi-dimensional Sensitivity-Aware and Gradient-Hessian Fusion for Vector Quantization

Vision-Language Models (VLMs) achieve outstanding performance, yet their huge model size severely hinders deployment on edge devices with limited resources. As an efficient model compression technique, vector quantization (VQ) excels in ultra-low-bit representation, which maps model weights to discrete codewords in a compact codebook to cut memory consumption and transmission overhead while preserving model capability. Direct VQ application to VLMs still has two core limitations. First, cross-modality weight distribution differences brought by visual and textual inputs cannot be well fitted by a single unified codebook. Second, current second-order error compensation ignores first-order gradient information, causing weight deviation from pre-trained optimal states, gradient drift and biased compensation results. This work proposes MGVQ, a novel vector quantization framework integrating multi-dimensional sensitivity perception and gradient-Hessian fusion. It consists of two core modules: sensitivity-guided structured mixed-precision quantization dynamically assigns different bit-widths according to channel sensitivity via combined global and local sensitivity analysis for refined resource allocation; gradient-aware second-order error compensation embeds first-order gradients into error correction, and adopts Kronecker and Block-LDL decomposition to ensure low computational cost. Extensive experiments on mainstream VLMs including LLaVA-onevision, InternVL2 and Qwen2-VL verify the effectiveness of MGVQ. In 2-bit quantization settings, MGVQ surpasses existing advanced post-training quantization methods significantly, achieving a maximum accuracy improvement of 4.9 points (71.4% vs 67.0% on InternVL2-26B). The proposed method realizes stable and efficient ultra-low-bit VLM quantization, greatly promoting the practical deployment of multimodal large models in resource-limited environments.

Zhong Wang, Zukang Xu, Xing Hu +1

Bauman Moscow State Technical University · Houmo AI

Mixed-Precision QuantizationVision-Language ModelsVLM QuantizationVector QuantizationGradient QuantizationPost-Training Quantization+1
AskPDF
May 19, 2026

ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models

Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical. Aggressive, sub-4-bit weight quantization is the natural solution, yet existing post-training quantization (PTQ) methods suffer severe performance degradation in this regime. To address this, we introduce ActQuant, an action-guided mixed-precision PTQ framework that operates in two stages: (1) an inter-tensor bit allocator that assigns each weight matrix a single bit-width based on how much it contributes to predicting the agent's actions; (2) an intra-tensor scale optimizer tunes per-block quantization scales using action-aware curvature, so that dynamic range is concentrated on the weights most influential for control. To deliver the on-device benefits of our aggressive quantization, we further introduce OmniModel.cpp, an agentic conversion pipeline that ports architectures into a native C/C++ runtime with efficient low-bit kernels. We evaluate ActQuant both in simulation and on a real-world 6-DoF UR3 arm, with all models deployed through OmniModel.cpp. On the LIBERO benchmark, ActQuant is the only method that operates at or below 3 bits-per-weight, retaining 95.0% on OpenVLA-OFT and 94.8% on π0.5π_{0.5}. Pushed further, ActQuant reaches 2.5 bpw at 90.1% on OpenVLA-OFT, compressing the backbone from 14.3 GB to 2.7 GB (5.3×\times). On the physical UR3 arm, π0.5π_{0.5} quantized with ActQuant retains the baseline's success rate while reducing the memory footprint by 2.5×\times.

Arash Akbari, Arman Akbari, Masih Eskandar +11

1Northeastern University · University of Georgia · 3Cisco Systems

Neural Network QuantizationVLM QuantizationEfficient VLA Model InferenceLow-Bit QuantizationMixed-Precision QuantizationEfficient VLA Models+4
AskPDF
May 19, 2026

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor

MXFP4 arithmetic can dramatically accelerate reinforcement learning (RL) post-training of large language models (LLMs), yet the quantization error introduces severe accuracy degradation. Existing work treats the quantization error as a monolithic noise term, missing the distinct mechanisms upon interpreting how quantization error damages training. We prove an exact three-way decomposition of quantization error and show how each component dominates a distinct RL training pathway. Our theoretical and empirical analysis decomposes the MXFP4 quantization error into three additive components: "scale bias" from power-of-two rounding, "deadzone truncation" from zeroing small values, and "grid noise" from rounding to the nearest 4-bit grid. Each component dominates a distinct RL failure mode: scale bias accumulates multiplicatively through the backward pass, affecting gradient accuracy; deadzone truncation degrades rollout quality; and grid noise raises the policy's entropy. We combine corrections that are RL failure mode-targeted but not component-exclusive: Macro-block scaling to reduce scale bias, Outlier Fallback recovers deadzone entries, but also partially reduces scale bias induced error, and Adaptive Quantization Noise (AQN) for controlling the policy entropy. On Qwen2.5-3B dense and Qwen3-30B-A3B-Base mixture-of-experts model, the targeted corrections recover BF16 accuracy to within 0.7% and exceed BF16 by +1.0% respectively.

Xiaocan Li, Shiliang Wu, Zheng Shen

Huawei Canada

LLM Quantization4-Bit QuantizationRL Post-TrainingPost-Training QuantizationNeural Network QuantizationQuantization Error Compensation
AskPDF
May 19, 2026

Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models

Low-bit post-training quantization (PTQ) is a pivotal technique for deploying Vision-Language Models (VLMs) on resource-constrained devices. However, existing PTQ methods often degrade VLMs' accuracy due to the heterogeneous activation distributions of text and vision modalities during quantization. We find that this cross-modal heterogeneity is distributed unevenly across channels: a small subset of channels contains most modality-specific outliers, and these outliers typically reside in different channels for each modality. Motivated by this, we propose SplitQ, a channel-Splitting-driven post-training Quantization framework. At its core, SplitQ introduces a novel Modality-specific Outlier Channel Decoupling (MOCD) module that effectively isolates salient modality-specific outlier channels with minimal overhead. To further address the remaining cross-modal distribution discrepancies, we design an Adaptive Cross-Modal Calibration (ACC) module that employs dual lightweight learnable branches to dynamically mitigate modality-induced quantization errors. Extensive experiments on popular VLMs demonstrate that SplitQ significantly outperforms existing approaches across 6 popular multi-modal datasets under all evaluated quantization settings, including W4A8, W4A4, W3A3, and W3A2. Notably, SplitQ preserves 93.5% of FP16 performance under the challenging W3A3 setting (69.5 vs. 74.3), pushing the efficiency frontier for deploying advanced VLMs. Our code is available at https://github.com/EMVision-NK/SplitQ

Yi Zhong, Haotong Qin, Xindong Zhang +2

VCIP, College of Computer Science, Nankai University · D-ITET, ETH Zürich · OPPO Research Institute +1

Vision-Language ModelsVLM QuantizationLarge Vision-Language ModelsPost-Training QuantizationLow-Bit Quantization
AskPDF
May 19, 2026

Quant.npu: Enabling Efficient Mobile NPU Inference for on-device LLMs via Fully Static Quantization

Large language models (LLMs) are increasingly deployed on mobile devices, where Neural Processing Units (NPUs) necessitate fully static quantization for optimal inference efficiency. However, existing post-training quantization (PTQ) methods predominantly rely on dynamic activation quantization, rendering them incompatible with NPU hardware constraints. To bridge the gap between high-fidelity PTQ and NPU-constrained inference, we propose Quant.npu, a integer-only fully static quantization framework. It incorporates learnable quantization parameters and rotation matrices, enabling low-bit activation-weight quantization without runtime quantization parameters re-computation. Crucially, we identify that initialization and selective optimization of quantization parameters is pivotal for optimization stability, as improper initialization and naive joint optimization induce gradient instability that disrupts the optimization of rotation matrices. To address this, we propose a rotation-and-bit-width-aware initialization tailored to diverse activation profiles and a distribution-aware selective optimization (two-stage quantization pipeline) tailored to rotated and unrotated tensors. Furthermore, we introduce a sensitivity-guided adaptive mixed-precision scheme to balance accuracy with inference efficiency. Extensive experiments on real-world mobile NPUs demonstrate that Quant.npu achieves comparable accuracy to state-of-the-art methods, while reducing inference latency by up to 15.1%.

Jinghe Zhang, Daliang Xu, Chenghua Wang +5

Mixed-Precision QuantizationLLM QuantizationAI Accelerator InferenceOn-Device Language Model InferencePost-Training QuantizationNeural Network Quantization
AskPDF
May 19, 2026

TORQ: Two-Level Orthogonal Rotation for MXFP4 Quantization

As Large Language Models (LLMs) advance toward practical deployment, the Microscaling FP4 (MXFP4) format has emerged as a cornerstone for next-generation low-bit inference, owing to its ability to balance high dynamic range with hardware efficiency. However, directly applying MXFP4 to LLM activation quantization inevitably leads to significant accuracy degradation. In this paper, we theoretically analyze the error structure of MXFP4 activation quantization, revealing that the root cause of this performance drop lies in two structural imbalances between activation distributions and the MXFP4 block floating-point format: (1) extreme inter-block variance imbalance and (2) intra-block codebook utilization imbalance. To address these challenges, we propose TORQ (Two-level Orthogonal Rotation for MXFP4 Quantization), a training-free Post-Training Quantization (PTQ) framework designed to reshape the geometric properties of the activation space through optimal coordinate transformations. At the macroscopic level, TORQ leverages the Schur-Horn theorem to redistribute activation energy via inter-block orthogonal rotation, preventing high-variance blocks from driving up shared scaling factors and thereby preserving the precision of small-magnitude elements. At the microscopic level, TORQ employs maximum-entropy-guided intra-block rotation to alleviate codebook collapse and maximize the MXFP4 codebook's information capacity. Experiments on mainstream LLMs such as LLaMA3 and Qwen3 show that TORQ significantly improves the accuracy of MXFP4 activation quantization compared to existing methods: on Qwen3-32B, the perplexity on WikiText is reduced to 8.43 (vs. 7.61 for BF16), and the average accuracy increases from 38.40% with direct RTN to 73.63% (vs. 74.82% for BF16), substantially narrowing the gap between 4-bit floating-point quantization and full-precision inference.

Zukang Xu, Xing Hu, Dawei Yang

1Houmo AI.

LLM QuantizationRotation-Based QuantizationActivation QuantizationPost-Training QuantizationNeural Network Quantization
AskPDF
May 19, 2026

Quantized Machine Learning Models for Medical Imaging in Low-Resource Healthcare Settings

Deep learning models have shown strong performance in medical image analysis, but deploying them in low-resource clinical environments remains difficult due to computational, memory, and power constraints. This paper presents a multi-strategy compression framework for brain tumor classification from MRI, encompassing quantization-aware training, knowledge distillation from a DenseNet-101 teacher to a compact DenseNet-32 student with low-bit post-training quantization, and Float16 post-training quantization on a lightweight MobileNetV2 backbone. Using a multi-class brain tumor MRI dataset containing glioma, meningioma, pituitary tumors, and healthy controls, we provide full experimental validation of the MobileNetV2-based pipeline, training the classifier through a three-stage transfer learning process and applying Float16 quantization via TensorFlow Lite. The DenseNet-based distillation and quantization-aware training strategies are described as complementary compression approaches within the framework, with their complete empirical evaluation reserved for future work. Experimental results on the MobileNetV2 pipeline show that the quantized model achieves 82.37 percent validation accuracy compared to the 82.20 percent full-precision baseline, reducing model size from 35.34 MB to 5.76 MB, a 6.14x compression ratio with no meaningful accuracy loss. Per-class evaluation confirms that quantization preserves diagnostic performance uniformly across all four tumor categories. These findings demonstrate that lightweight quantized models can deliver clinically viable brain tumor screening in resource-constrained healthcare settings.

Sumanth Meenan Kanneti, Aryan Shah

Georgia State University · University of Southern California

Efficient Neural Network InferenceMedical Image ClassificationBrain Tumor ClassificationPost-Training QuantizationNeural Network Compression
AskPDF
May 18, 2026

GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets

Mixed-precision quantization improves the budget--accuracy trade-off for large language models (LLMs) by allocating more bits to sensitive modules. However, automating this allocation at LLM scale faces a unique combination of constraints: learnable approaches require quantization-aware training, which is infeasible for billion-parameter models; training-free alternatives rely on static proxy metrics that miss cross-module interactions and must be recomputed per target budget; and search-based methods are expensive without guaranteeing exact budget compliance. We propose GAMMA, a quantizer-agnostic framework that learns module-wise precision preferences entirely within a post-training pipeline. GAMMA optimizes a teacher-forced hidden-state reconstruction objective under an augmented Lagrangian constraint, and projects the learned preferences into exact budget-feasible discrete assignments via integer programming. A key property is score reuse: because the learned preferences encode a stable sensitivity ranking rather than budget-specific weights, a single training run serves arbitrary deployment targets by re-solving only the integer program, reducing per-budget adaptation from hours to a few minutes. Across Llama and Qwen models (8B--32B), GAMMA outperforms both fixed-precision baselines (up to +12.99 Avg.) and search-based mixed-precision methods (up to +7.00 Avg.), and can match fixed 3-bit quality at 2.5-bit average precision, enabling deployment at substantially smaller memory footprints.

Zhangyang Yao, Haiyan Zhao, Haoyu Wang +3

Beihang University · Tsinghua University · ByteDance Inc

Mixed-Precision QuantizationLLM QuantizationPost-Training Quantization
AskPDF
May 18, 2026

MARR: Module-Adaptive Residual Reconstruction for Low-Bit Post-Training Quantization

Recently, residual reconstruction-based model quantization methods have achieved promising performance in low-bit post-training quantization (PTQ) by introducing cross-layer residuals to reduce error accumulated from previous layers.However, these residuals may also introduce additional bias arising from the Hessian-approximation (HA) assumption underlying reconstruction-based PTQ, leading to suboptimal quantization performance.In this work, we analyze that multiplying the residual term by a scaling coefficient provides a direct way to mitigate the HA bias associated with residual strength, while preserving accumulated-error correction. More importantly, we observe that this trade-off is module-dependent, making a single global residual strength insufficient to balance effective correction and residual-related bias across modules.Based on these observations, we propose Module-Adaptive Residual Reconstruction (MARR), which assigns a module-specific scaling coefficient to adaptively balance accumulated-error correction and residual-related HA bias for each module.To avoid expensive per-module coefficient search and obtain a stable coefficient estimate, we design a Proportional-Integral-Derivative (PID)-based adaptive update strategy that uses reconstruction error as feedback to progressively refine this coefficient. Experiments on several typical large language models (LLMs) and vision transformers (ViTs) demonstrate the effectiveness of MARR under low-bit quantization (less than or equal to 4-bit), achieving up to 20.2% performance gains on LLMs and up to 4.6% relative gains on ViTs over the residual reconstruction state-of-the-art methods.Code will be made publicly available upon acceptance.

Le Su, Xing Luo, Zhi Jin

School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University Shenzhen, Guangdong 518107, China · Department of Frontier Research Peng Cheng Laboratory Shenzhen, Guangdong 518055, China

LLM QuantizationPost-Training QuantizationPID ControlLow-Bit QuantizationNeural Network QuantizationQuantization Error Compensation
AskPDF
May 18, 2026

OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization

INT2 KV-cache quantization is attractive for long-context LLM serving, but it remains difficult to make both accurate and deployable. Simple rotations such as Hadamard transforms reduce outliers, but still degrade at INT2 because they are not aligned with downstream attention. We propose OSCAR, an Ultra-low-bit KV Cache quantization method that estimates attention-aware covariance structures offline and uses them to derive fixed rotations and clipping thresholds for quantization. In this way, it aligns KV quantization with the covariance structures that attention actually consumes. More importantly, we not only provide theoretical justification but also develop a fully deployable OSCAR system with a custom INT2 attention kernel that remains compatible with paged KV-cache serving and fused kernel pipelines, enabling seamless integration into modern LLM serving frameworks such as SGLang and vLLM. We evaluate our methods on recent reasoning models with reasoning traces of up to 32k tokens across 5 tasks. On Qwen3-4B-Thinking-2507 and Qwen3-8B, OSCAR reduces the BF16 accuracy gap to 3.78 and 1.42 points, respectively, while naive rotation INT2 collapses to nearly zero. We further scale OSCAR to Qwen3-32B and GLM-4.7 (358B params), where it remains effectively on par with BF16. On long context - RULER-NIAH up to 128K, OSCAR remains robust on both Qwen3 models, while naive rotation INT2 collapses. System-wise, OSCAR reduces KV-cache memory by approximately 8x, improves throughput by up to 7x at large batch sizes under the same memory budget, and accelerates batch-size-1 decoding by up to 3x over BF16 due to reduced memory bandwidth overhead.

Zhongzhu Zhou, Donglin Zhuang, Jisen Li +4

Together AI · University of Sydney · University of Illinois Urbana-Champaign

Rotation-Based QuantizationLLM Inference AccelerationKV-Cache QuantizationPost-Training QuantizationLow-Bit QuantizationNeural Network Quantization
AskPDF
May 16, 2026

CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model

Segment Anything Models (SAMs) are extensively used in computer vision for universal image segmentation, but deploying them on resource-constrained devices is challenging due to their high computational and memory demands. Post-Training Quantization (PTQ) is a widely used technique for model compression and acceleration. However, existing PTQ methods fail to consider the cross-attention architecture in the SAM decoder. This degradation primarily stems from the unique challenges posed by SAMs: (1) Attention dissipation, where the attention information in the decoder, which is crucial for representing segmentation masks, collapses into a diffuse and non-semantic form under low-bit quantization; and (2) Reconstruction oscillation, where bidirectional coupling within the two-way transformer introduces cross-branch error interference and destabilizes convergence. To tackle these issues, we propose CAR-SAM, a unified quantization framework tailored for SAMs. Firstly, to mitigate attention dissipation, we introduce MatMul-Aware Compensation (MAC) mechanism that transfers activation-induced quantization errors from MatMul to preceding linear weights. Secondly, to mitigate oscillation in decoder optimization, we develop a Joint Cross-Attention Reconstruction (JCAR) strategy that jointly reconstructs coupled attention branches, suppressing oscillatory behavior and promoting stable convergence. Extensive experiments show that CAR-SAM robustly quantizes SAM models down to 4-bit precision, surpassing existing methods by 14.6% and 6.6% mAP on SAM-B and SAM-L respectively.

Houji Wen, Jiangyong Yu, Jun Li +1

1Nanjing University of Science and Technology · 2Houmo AI

Cross-Attention4-Bit QuantizationPost-Training QuantizationNeural Network Quantization
AskPDF
May 16, 2026

E-PMQ: Expert-Guided Post-Merge Quantization with Merged-Weight Anchoring

Low-resource deployment constraints have made model quantization essential for deploying neural networks while preserving performance. Meanwhile, model merging has become an increasingly practical low-resource strategy for integrating multiple task- or domain-specialized experts into a single model without joint training or multi-model serving. Together, quantization and model merging enable an efficient low-resource deployment pipeline by integrating multiple experts into one low-bit model. We formulate this setting as Post-Merge Quantization (PMQ). We show that directly applying post-training quantization (PTQ) to a merged model is unreliable because two distinct deviations are coupled: the quantization deviation introduced by low-bit reconstruction and the expert-relative merging deviation inherited from model merging. To mitigate these deviations, we propose E-PMQ, an expert-guided PMQ framework that uses source expert weights to provide expert- guided output targets during layer-wise calibration, together with merged-weight anchoring to stabilize the calibration and preserve the integrated behavior of the merged model. On CLIP-ViT-B/32 eight-task merging, E-PMQ improves 4-bit GPTQ from 65.0% to 73.6% under Task Arithmetic and from 69.1% to 74.8% under TIES-Merging. On harder settings, E-PMQ improves GPTQ from 34.8% to 76.7% on 20-task CLIP-ViT-L/14 and from 78.26% to 83.34% on FLAN-T5- base GLUE. These results demonstrate that E-PMQ enables effective post-merge quantization and low-bit deployment.

Wenjun Wang, Yanggan Gu, Shuo Cai +4

The Hong Kong Polytechnic University · PolyU-Daya Bay Technology and Innovation Research Institute

4-Bit QuantizationPost-Training QuantizationNeural Network Quantization
AskPDF
May 16, 2026

DiRotQ: Rotation-Aware Quantization for 4-bit Diffusion Transformers

Diffusion Transformers (DiTs) achieve state-of-the-art image generation quality but incur substantial memory and computational costs at inference. While aggressive Post-Training Quantization (PTQ) to 4-bit precision offers significant efficiency gains, it typically results in severe quality degradation. Existing approaches, including smoothing-based methods, mixed-precision schemes, rotation techniques, and low-rank residual methods, partially mitigate this issue but still leave a noticeable gap to FP16/BF16 performance. In this work, we introduce DiRotQ, a W4A4 PTQ framework that mitigates this degradation through rotation-aware activation quantization. DiRotQ identifies a low-rank subspace capturing dominant activation variance via Principal Component Analysis (PCA), preserving coefficients in this subspace at higher precision while quantizing the remaining components to 4-bit. Activations are rotated into the PCA basis at inference time using calibration-derived orthogonal transformations, while the inverse rotation is fused into the layer weights offline. Combined with GPTQ-based weight quantization, DiRotQ achieves an FID (lower is better) of 15.9 and PSNR (higher is better) of 19.1 dB on PixArt-Σ over the MJHQ-30K dataset, outperforming the prior state-of-the-art SVDQuant (FID 18.9, PSNR 17.6) under the same INT W4A4 setting. Beyond standard metrics, we introduce a VLM-as-a-Judge evaluation protocol for diffusion model quantization, the first such evaluation in this setting, providing a more holistic assessment of perceptual quality and prompt alignment under aggressive compression. On the systems side, we implement a Triton-based custom kernel to enable efficient end-to-end inference, reducing memory usage of the 12B FLUX.1-dev model by 2.1x and delivering 2.3x speedup over the BF16 baseline, on a 24 GB RTX 4090 GPU.

Sayeh Sharify, Mahsa Salmani, Hesham Mostafa

d-Matrix Santa Clara, CA 95054

Diffusion TransformerDiffusion Model Quantization4-Bit QuantizationRotation-Based QuantizationActivation QuantizationPost-Training Quantization+2
AskPDF
May 15, 2026

Not All Tasks Quantize Equally: Fisher-Guided Quantization for Visual Geometry Transformer

Feed-forward 3D reconstruction models, represented by Visual Geometry Grounded Transformer (VGGT), jointly predict multiple visual geometry tasks such as depth estimation, camera pose prediction, and point cloud reconstruction in a single forward pass. They have been widely adopted in 3D vision applications, but their billion-scale parameters bring substantial memory and computation overhead, posing challenges for on-device deployment. Post-Training Quantization (PTQ) is an effective technique to reduce this overhead. Existing PTQ methods for feed-forward 3D models mainly focus on handling heavy-tailed activation distributions and constructing diverse calibration datasets. However, we observe that feed-forward 3D models predict multiple geometric attributes through a shared backbone, where different transformer blocks and hidden channels contribute distinctly to each task, resulting in substantially different sensitivities to quantization errors across tasks, blocks, and channels. Consequently, treating all tasks equally over-emphasizes insensitive tasks and causes significant accuracy loss on the sensitive ones. To address this issue, we propose Fisher-Guided Quantization (FGQ) for feed-forward 3D reconstruction models. Specifically, FGQ uses the diagonal Fisher information matrix to quantify the different sensitivities across tasks, blocks, and channels, and incorporates these sensitivities into the Learnable Affine Transformation during calibration to better preserve the channels and blocks most critical to each task. Extensive experiments across camera pose estimation, point map reconstruction, and depth estimation show that FGQ consistently outperforms state-of-the-art quantization baselines on VGGT, achieving up to 39% relative improvement under the 4-bit quantization. Code is available at https://github.com/ypzhng/FGQ.

Yipu Zhang, Jintao Cheng, Weilun Feng +5

Department of Electronic and Computer Engineering, HKUST · State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences +2

Feed-Forward 3D ReconstructionPost-Training QuantizationNeural Network Quantization
AskPDF
May 14, 2026

Widening the Gap: Exploiting LLM Quantization via Outlier Injection

LLM quantization has become essential for memory-efficient deployment. Recent work has shown that quantization schemes can pose critical security risks: an adversary may release a model that appears benign in full precision but exhibits malicious behavior once quantized by users. However, existing quantization-conditioned attacks have been limited to relatively simple quantization methods, where the attacker can estimate weight regions that remain invariant under the target quantization. Notably, prior attacks have consistently failed to compromise more popular and sophisticated schemes, limiting their practical impact. In this work, we introduce the first quantization-conditioned attack that consistently induces malicious behavior that can be triggered by a broad range of advanced quantization techniques, including AWQ, GPTQ, and GGUF I-quants. Our attack exploits a simple property shared by many modern quantization methods: large outliers can cause other weights to be rounded to zero. Consequently, by injecting outliers into specific weight blocks, an adversary can induce a targeted, predictable weight collapse in the model. This effect can be used to craft seemingly benign full-precision models that exhibit a wide range of malicious behaviors after quantization. Through extensive evaluation across three attack scenarios and LLMs, we show that our attack achieves high success rates against a broad range of quantization methods on which prior attacks fail. Our results demonstrate, for the first time, that the security risks of quantization are not restricted to simpler schemes but are broadly relevant across complex, widely-used quantization methods.

Xiaohua Zhan, Kazuki Egashira, Robin Staab +2

ETH Zurich

LLM QuantizationLLM Backdoor AttacksAdversarial Attacks on LLMsPost-Training Quantization
AskPDF
May 14, 2026

Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution

Standard unlearning evaluations measure behavioral suppression in full precision, immediately after training, despite every deployed language model being quantized first. Recent work has shown that 4-bit post-training quantization can reverse machine unlearning; we show this is not a tuning artefact but a systematic dual failure: gradient-based methods that achieve meaningful forgetting lose it under compression, while methods that survive quantization barely change the model. Both failures trace to the same root cause: across all baselines, per-parameter updates lie 47-828x below the NF4 quantization bin width; updates diffused across billions of parameters cannot clear quantization bin boundaries, a consequence we formalize as a sparsity-permanence tradeoff. We present MANSU (Mechanistic-Aligned Null-Space Unlearning), which resolves both modes by combining causal circuit attribution to isolate the minimal forget-set subgraph, circuit-restricted null-space projection with a diagonal-Fisher retain bound, and a per-parameter magnitude floor guaranteeing quantization survival by construction. We additionally introduce Circuit Attribution Divergence (CAD), a mechanistic verification metric distinguishing structural erasure from behavioral suppression, a distinction existing metrics cannot make. Across multiple model families and hazard benchmarks, MANSU is the first method to jointly satisfy all four properties with margin on each (meaningful forgetting, retain preservation, non-positive PTQ gap, and structural erasure), while gradient-based baselines recover up to +0.05 accuracy under compression.

Saisab Sadhu, Pratinav Seth, Vinay Kumar Sankarapu

Lexsi Labs

Machine UnlearningPost-Training QuantizationLLM UnlearningMachine Unlearning Evaluation
AskPDF
May 14, 2026

A Hardware-Aware, Per-Layer Methodology for Post-Training Quantization of Large Language Models

Scaled Outer Product (SOP) is a post-training quantization methodology for large language model weights, designed to deliver near-lossless fidelity at 4.5--6 bits per weight on hardware with per-layer LUT decode. The methodology combines per-layer search of fixed and dynamic codebook pairs selected by a per-block selection bit, signed per-block scales, activation-weighted cosine selection, and multiple-choice knapsack promotion of sensitive layers with outlier and sparse-residual correction. Fixed codebooks include NF4, BOF4, Split87, and SH4; per-layer optimized codebooks (DD4) are hosted in LUT SRAM. A new hardware-efficient LUT output format (HIF) is proposed to improve performance, energy, and cost. Across six open model families, the recommended FP6 operating point (E2M3sUE4M4, 6.5 bpw) achieves lower weight reconstruction error than the conventional per-layer-POT FP8 baseline (E4M3, 8.0 bpw) at 1.5 bpw lower storage cost, demonstrating that block-scaled small atoms with carefully chosen scale precision can replace conventionally-deployed FP8. Full evaluation across the 4.5--6 bpw range, including layer promotion and sparse residual correction, is reported in a companion paper.

Earl Killian

Mixed-Precision QuantizationLLM QuantizationWeight-Only QuantizationHardware-Aware QuantizationPost-Training QuantizationLow-Bit Quantization+1
AskPDF
May 14, 2026

Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization

Network quantization has emerged as one of the most practical model compression techniques, which significantly reduces a model's memory and compute consumption by mapping floating-point numbers to low-bit representations. However, existing quantization methods typically suffer from the speed-accuracy tradeoff and limited generalization. To address these issues, recent compensation-based methods offer an efficient yet general solution by introducing additional lightweight linear layers into the quantized network. However, the accuracy of these methods suffers from their limited compensation capability and high sensitivity to outliers. In this paper, we propose Nonlinear Bipolar Compensation (NBC), a post-training quantization approach that introduces nonlinear compensation to reduce the effect of outliers. We further design Bipolar Logarithmic Transformation (BLT), which compresses outliers by mapping both the quantized input and the quantization error into a transformed space. A simple linear layer is then applied for compensation in the transformed space, preserving the efficiency of our method. Extensive experiments across various tasks, models, and quantization methods confirm the effectiveness, efficiency, robustness, and generality of our NBC approach.

Peilin Sun, Jianxin Wu

State Key Laboratory of Novel Software Technology, Nanjing University, China · School of Artificial Intelligence, Nanjing University, China

Activation OutliersQuantization Error CompensationPost-Training QuantizationNeural Network Quantization
AskPDF
May 14, 2026

XFP: Quality-Targeted Adaptive Codebook Quantization with Sparse Outlier Separation for LLM Inference

We introduce XFP, a dynamic weight quantizer for LLM inference that inverts the conventional workflow: the operator specifies reconstruction quality floors on per-channel cosine similarity (one strict floor for attention and shared experts, one lazy floor for routed-expert MoE); XFP determines codebook size, outlier budget, and packing per layer automatically -- no Hessian, no calibration data, no manual bit-width selection. Each weight matrix is decomposed into a sparse fp16 outlier residual and a dense sub-byte index tensor into a per-group learned codebook. Two storage modes share one auto-select frontend and one fused decode kernel: V2 (per-channel Lloyd) and V2a (shared library of L=32 codebooks per layer). On Qwen3.5-122B-A10B under V2, XFP reaches 138 tok/s single-stream decode on workstation hardware (RTX PRO 6000 Blackwell, TP=2) at 94.49% GSM8K strict-match (3 seeds, n=3957), and is 49% faster than Marlin INT4 at TP=1. For models that do not fit in the target memory envelope, we present the H-Process: a quality-driven iteration over the two cosine thresholds that finds the operating point at which the model just fits while still producing sensible output. Three constraints define its search space: the operator-set thresholds, an OOM boundary at quantize-on-load, and a garbage boundary in generation (cosine similarity steers; benches verify). On Qwen3.5-397B-A17B (512 routed experts/layer), the H-Process fits the full expert population into 2x96 GB at ~3.4 effective bits and delivers 100.9 tok/s long-output decode at 66.72% GSM8K strict-match on the full 1319-problem set (single seed at submission; multi-seed evaluation in progress), exceeding INT4 with routed-expert pruning on memory, throughput, and accuracy simultaneously.

Thomas Witt

Gemini Stiftung Leipzig

LLM QuantizationVector QuantizationLLM Inference AccelerationPost-Training QuantizationNeural Network Quantization
AskPDF
May 13, 2026

High-Rate Quantized Matrix Multiplication II

This is the second part of the work investigating quantized matrix multiplication (MatMul). In part I we considered the case of calibration-free quantization, whereas here we discuss the setting where covariance matrix ΣXΣ_X of the columns of the second factor is available. This setting arises in the ubiquitous task of weight-only post-training quantization of LLMs. Weight-only quantization is related to the problem of weighted mean squared error (WMSE) source coding, whose classical (reverse) waterfilling solution dictates how one should distribute rate between coordinates of the vector. We show how waterfilling can be used to improve practical LLM quantization algorithms (GPTQ), which at present allocate rate equally. A recent scheme (known as ``WaterSIC'') that only uses scalar INT quantizers is analyzed and its high-rate performance is shown to be (a) basis free (i.e., characterized by the determinant of ΣXΣ_X and, thus, unlike existing schemes, is immune to applying random rotations); and (b) within a multiplicative factor of 2πe12\frac{2πe}{12} (or 0.25 bit/entry) of the information-theoretic distortion limit. GPTQ's performance, in turn, is affected by the choice of basis, but for a random rotation and actual ΣXΣ_X from Llama-3-8B we find it to be within 0.1 bit (depending on the layer type) of WaterSIC, suggesting that GPTQ with random rotation is also near optimal, at least in the high-rate regime.

Or Ordentlich, Yury Polyanskiy

the Hebrew University of Jerusalem, Israel · MIT, USA

LLM QuantizationRate-Distortion TheoryRate-Distortion OptimizationWeight-Only QuantizationPost-Training QuantizationNeural Network Quantization
AskPDF
May 12, 2026

Search Your Block Floating Point Scales!

Quantization has emerged as a standard technique for accelerating inference for generative models by enabling faster low-precision computations and reduced memory transfers. Recently, GPU accelerators have added first-class support for microscaling Block Floating Point (BFP) formats. Standard BFP algorithms use a fixed scale based on the maximum magnitude of the block. We observe that this scale choice can be suboptimal with respect to quantization errors. In this work, we propose ScaleSearch, an alternative strategy for selecting these scale factors: using a fine-grained search leveraging the mantissa bits in microscaling formats to minimize the quantization error for the given distribution. ScaleSearch can be integrated with existing quantization methods such as Post Training Quantization and low-precision attention, and is shown to improve their performance. Additionally, we introduce ScaleSearchAttention, an accelerated NVFP4-based attention algorithm, which uses ScaleSearch and adapted prior techniques to ensure near-0 performance loss for causal language modeling. Experiments show that ScaleSearch reduces quantization error by 27% for NVFP4 and improves language model PTQ by up to 15 points for MATH500 (Qwen3-8B), while ScaleSearchAttention improves Wikitext-2 PPL by upto 0.77 points for Llama 3.1 70B. The proposed methods closely match baseline performance while providing quantization accuracy improvements.

Tanmaey Gupta, Hayden Prairie, Xiaoxia Wu +10

Cornell University, Ithaca, NY, USA · Together AI, USA · University of California San Diego, La Jolla, CA, USA +1

4-Bit QuantizationLLM Inference AccelerationPost-Training QuantizationNeural Network Quantization
AskPDF
May 12, 2026

Grid Games: The Power of Multiple Grids for Quantizing Large Language Models

A major recent advance in quantization is given by microscaled 4-bit formats such as NVFP4 and MXFP4, quantizing values into small groups sharing a scale, assuming a fixed floating-point grid. In this paper, we study the following natural extension: assume that, for each group of values, we are free to select the "better" among two or more 4-bit grids marked by one or more bits in the scale value. We formalize the power-of-two-grids (PO2) problem, and provide theoretical results showing that practical small-group formats such as MXFP or NVFP can benefit significantly from PO2 grids, while the advantage vanishes for very large groups. On the practical side, we instantiate several grid families, including 1) PO2(NF4), which pairs the standard NF4 normal grid with a learned grid, 2) MPO2, a grid pair that is fully learned over real weights and activations, 3) PO2(Split87), an explicit-zero asymmetric grid and 4) SFP4, a TensorCore-implementable triple which pairs NVFP4 with two shifted variants. Results for post-training quantization of standard open models and pre-training of Llama-like models show that adaptive grids consistently improve accuracy vs single-grid FP4 under both weight-only and weight+activation. Source code is available at https://github.com/IST-DASLab/GridGames.

Vage Egiazarian, Erik Schultheis, Andrei Panferov +3

ISTA · Aril Computer · ETH Zürich +1

LLM Quantization4-Bit QuantizationActivation QuantizationPost-Training Quantization
AskPDF