Overview

Activation quantization studies how to represent the intermediate values passed between neural-network layers with fewer bits, reducing memory traffic and enabling faster, smaller deployments. Common approaches include calibration-based clipping and scale selection, smoothing or rotating activations to reduce outliers, mixed-precision allocation, and quantization-aware training; methods target formats such as INT8, INT4, and FP4. Work spans language and vision models, diffusion systems, speech models, and interactive policies, with evaluations using measures such as perplexity, ImageNet accuracy, generation quality, and task success. A central tension is preserving quality across changing activation distributions while delivering real speed and memory gains on the hardware and kernels used in deployment.

Latest papers

131 papers10 papers in the last four weeks, down 64% on the four weeks before. 0.1% of all new papers.

Mar 9, 2026

Evolution Strategy-Based Calibration for Low-Bit Quantization of Speech Models

Quantization has become essential for the efficient deployment of speech processing systems. Although widely studied, most existing quantization methods were developed for vision and NLP architectures, while the specific challenges of audio signals remain largely overlooked. In particular, we show that audio activations can exhibit large calibration ranges, leading to significant information loss when standard calibration techniques are applied. To address this, we propose ESC, an Evolution Strategy-based Calibration method that formulates activation scaling as an optimization problem and solves it using a two-step local-global scheme driven by an evolution strategy. ESC enables unaltered performance under full INT8 quantization and is the first calibration method to achieve near-lossless performance for full INT4 quantization across multiple speech tasks. Integrating ESC with PTQ methods further reduces performance loss, achieving a 1% relative accuracy degradation on the AST model.
Mar 9, 2026

DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied Vision-Language-Action Models

Vision-language-action (VLA) models achieve favorable task performance, yet runtime errors in closed-loop execution evolve with alternating updates of actions and observations. Existing VLA quantization methods mainly trade off inference speed and model performance while rarely investigating how quantization alters runtime errors. By comparing error distributions between full-precision and quantized models, we identify distinct evolutionary patterns for the two types of errors: quantization enlarges the variance of translation error distributions and increases their dispersion, whereas the distribution center of rotation errors gradually shifts across execution steps, demonstrating cumulative drift. Motivated by this observation, we rethink the optimal quantization strategy for VLA models and propose DyQ-VLA, a runtime-error-aware quantization framework, which dynamically selects activation precision according to execution steps and tracks as well as compensates rotation errors via accumulated quantization residuals. Corresponding operators and runtime adaptation strategies are devised within the framework to enable dynamic-precision execution. Experiments show that DyQ-VLA achieves a 1.88 to 1.93 inference speedups while maintaining comparable or higher average task success rates. Moreover, it reduces mean execution steps by 17.7% to 19.8%. Our code is here: https://anonymous.4open.science/r/DyQ-VLA-7F51/.
Mar 4, 2026

Activation Outliers in Transformer Quantization: Reproduction, Statistical Analysis, and Deployment Tradeoffs

Post-training quantization (PTQ) of transformers is known to suffer from severe accuracy degradation due to structured activation outliers, as originally analyzed by Bondarenko et al. (EMNLP 2021) in work associated with Qualcomm AI Research. This paper provides a reproducible empirical reproduction and systems-level extension of that phenomenon in BERT-base fine-tuned on QNLI. When global W8A8 quantization is applied, validation accuracy drops sharply from 89.66% (FP32) to 54.33%, a decrease of 35.33 points. Statistical analysis of FP32 activations shows strongly heavy-tailed behavior that intensifies with model depth: kurtosis reaches 271 in the final layers and approximately 55% of activation energy is concentrated in the top 1% of channels. We evaluate several mitigation strategies. Mixed precision PTQ restores accuracy close to the FP32 baseline (89.42%). Per-embedding-group (PEG) quantization shows strong sensitivity to grouping structure, improving accuracy from 66.12% with three groups to 86.18% with four groups. In contrast, percentile-based calibration, even at thresholds between 99.0 and 99.99, fails to recover accuracy (about 50.54%), indicating that large activation channels encode structured signal rather than rare noise. Deployment profiling on an RTX 3050 GPU shows minimal differences in latency and memory usage across methods (median latency about 58-59 ms; VRAM usage about 484-486 MB), highlighting the importance of hardware-aware evaluation. Overall, the results show that PTQ failure in transformers is primarily driven by structured channel dominance amplified through residual connections. Effective mitigation therefore requires channel-aware precision allocation rather than scalar clipping alone.
Mar 3, 2026

SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers

Diffusion Transformers (DiTs) achieve state-of-the-art video generation quality, but their substantial memory and computational footprints hinder edge deployment. Quantization can reduce these costs, yet existing methods often degrade video quality due to high activation variation and the difficulty of preserving semantic and temporal coherence. We propose SemanticDialect, which advances block-wise mixed-format quantization. In this framework, each block selects an optimal format (dialect) from a candidate set (formatbook), which is augmented with lookup tables that store quantization errors and quantized indices, enabling efficient per-block format selection and quantization with minimal online overhead. We further introduce attention-guided activation decomposition, which reduces quantization error via residual quantization, and semantic-aware dialect assignment (SeDA), which reduces cross-token quantization inconsistency by enforcing format uniformity among semantically correlated tokens. Experiments demonstrate that SemanticDialect outperforms prior quantization methods and block-wise formats (MXFP4, NVFP4) while approaching FP16 quality on Open-Sora 2.0. We also validate hardware deployability through RTL design and GPU kernel implementation.
Mar 3, 2026

Practical FP4 Training for Large-Scale MoE Models on Hopper GPUs

Training large-scale Mixture-of-Experts (MoE) models is bottlenecked by activation memory and expert-parallel communication, yet FP4 training remains impractical on Hopper-class GPUs without native MXFP4 or NVFP4 support. In this work, we present a training recipe that enables MXFP4 efficiency for MoE models on Hopper architectures without native 4-bit computation support. A central challenge is to integrate FP4 into an existing BF16/FP8 hybrid training pipeline without incurring costly precision round-trips (e.g., FP4 ↔\leftrightarrow BF16 ↔\leftrightarrow FP8). We address this challenge by introducing direct FP8-to-FP4 quantization and de-quantization, together with scaling-aware FP4 row-wise to column-wise conversion, enabling FP4 activations and expert-parallel communication with minimal overhead. Core MoE computations are executed in FP8, while activations and expert-parallel communication are compressed using MXFP4, achieving substantial memory and bandwidth savings without degrading convergence. At the 671B parameter scale, our method achieves end-to-end training performance comparable to strong FP8 baselines, while reducing peak activation memory by 14.8% (11.8 GB) and improving training throughput by 12.5%, from 1157 to 1302 tokens per GPU per second. These results show that FP4 efficiency can be practically realized for large-scale MoE training through careful software-hardware co-design, even without native FP4 Tensor Core support.
Mar 2, 2026

FreeAct: Freeing Activations for LLM Quantization

Quantization is pivotal for mitigating the significant memory and computational overhead of Large Language Models (LLMs). While emerging transformation-based methods have successfully enhanced quantization by projecting feature spaces onto smoother manifolds using orthogonal matrices, they typically enforce a rigid one-to-one transformation constraint. This static approach fails to account for the dynamic patterns inherent in input activations, particularly within diffusion LLMs (dLLMs) and Multimodal LLMs (MLLMs), where varying token types exhibit distinct distributions. To advance this, we propose FreeAct, a novel quantization framework that relaxes the static one-to-one constraint to accommodate dynamic activation disparities. Theoretically, we leverage the rank-deficient nature of activations to derive a solution space that extends beyond simple inverse matrices, enabling the decoupling of activation transformations from weights. Methodologically, FreeAct identifies token-specific dynamics (i.e., vision v.s. text, or masked tokens) and allocates distinct transformation matrices to the activation side, while maintaining a unified, static transformation for the weights. Extensive experiments across dLLMs and MLLMs demonstrate that FreeAct significantly outperforms baselines, up to 5.3% performance improvement, with in-depth analyses. Our code will be publicly released.
Feb 16, 2026

S2D: Selective Spectral Decay for Quantization-Friendly Conditioning of Neural Activations

Activation outliers in large-scale transformer models pose a fundamental challenge to model quantization, creating excessively large ranges that cause severe accuracy drops during quantization. We empirically observe that outlier severity intensifies with pre-training scale (e.g., progressing from CLIP to the more extensively trained SigLIP and SigLIP2). Through theoretical analysis as well as empirical correlation studies, we establish the direct link between these activation outliers and dominant singular values of the weights. Building on this insight, we propose Selective Spectral Decay (S2DS^2D), a geometrically-principled conditioning method that surgically regularizes only the weight components corresponding to the largest singular values during fine-tuning. Through extensive experiments, we demonstrate that S2DS^2D significantly reduces activation outliers and produces well-conditioned representations that are inherently quantization-friendly. Models trained with S2DS^2D achieve up to 7% improved PTQ accuracy on ImageNet under W4A4 quantization and 4% gains when combined with QAT. These improvements also generalize across downstream tasks and vision-language models, enabling the scaling of increasingly large and rigorously trained models without sacrificing deployment efficiency.
Oct 6, 2025

Activation Quantization of Vision Encoders Needs Prefixing Registers

Large pretrained vision encoders are central to multimodal intelligence, powering applications from on-device vision processing to vision-language models. Since these applications often demand real-time processing of massive visual data, reducing the inference cost of vision encoders is critical. Quantization offers a practical path, but it remains challenging even at 8-bit precision due to so-called outliers. In this work, we propose RegCache\textit{RegCache}, a training-free algorithm that mitigates outliers in large-scale pretrained vision encoders and serves as a plug-in module that can be applied on top of other quantization methods. RegCache introduces outlier-prone yet semantically meaningless prefix tokens to the vision encoder, which prevent other tokens from having outliers. Notably, we observe that outliers in vision encoders behave differently from those in language models, motivating two technical innovations: middle-layer prefixing and token deletion. Experimental results show that our method consistently improves quantized model performance across various vision encoders, particularly in extremely low-bit regimes (e.g., 4-bit).
Jun 13, 2025

GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers

Vision Transformers (ViTs) are essential in computer vision but are computationally intensive, too. Model quantization, particularly to low bit-widths like 4-bit, aims to alleviate this difficulty, yet existing Post-Training Quantization (PTQ) and Quantization-Aware Training (QAT) methods exhibit significant limitations. PTQ often incurs substantial accuracy drop, while QAT achieves high accuracy but suffers from prohibitive computational costs, limited generalization to downstream tasks, training instability, and lacking of open-source codebase. To address these challenges, this paper introduces General, Practical, and Lightning Quantization (GPLQ), a novel framework designed for efficient and effective ViT quantization. GPLQ is founded on two key empirical insights: the paramount importance of activation quantization and the necessity of preserving the model's original optimization basin'' to maintain generalization. Consequently, GPLQ employs a sequential activation-first, weights-later'' strategy. Stage 1 keeps weights in FP32 while quantizing activations with a feature mimicking loss in only 1 epoch to keep it stay in the same ``basin'', thereby preserving generalization. Stage 2 quantizes weights using a PTQ method. As a result, GPLQ is 100x faster than existing QAT methods, lowers memory footprint to levels even below FP32 training, and achieves 4-bit model performance that is highly competitive with FP32 models in terms of both accuracy on ImageNet and generalization to diverse downstream tasks, including fine-grained visual classification and object detection. We will release an easy-to-use open-source toolkit supporting multiple vision tasks.
Jun 5, 2025

FPTQuant: Function-Preserving Transforms for LLM Quantization

Large language models (LLMs) require substantial compute, and thus energy, at inference time. While quantizing weights and activations is effective at improving efficiency, naive quantization of LLMs can significantly degrade performance due to large magnitude outliers. This paper describes FPTQuant, which introduces three novel, lightweight, and expressive function-preserving transforms (FPTs) to facilitate quantization of transformers: (1) a mergeable pre-RoPE transform for queries and keys, (2) a mergeable transform for values, and (3) a cheap, dynamic per-token scaling transform. By leveraging the equivariances and independencies inherent to canonical transformer operation, we designed these FPTs to maintain the model's function while shaping the intermediate activation distributions to be more quantization friendly. FPTQuant requires no custom kernels and adds virtually no overhead during inference. The FPTs are trained both locally to reduce outliers, and end-to-end such that the outputs of the quantized and full-precision models match. FPTQuant enables static INT4 quantization with minimal overhead and shows SOTA speed-up of up to 3.9X over FP. Empirically, FPTQuant has an excellent accuracy-speed trade-off -- it is performing on par or exceeding most prior work and only shows slightly lower accuracy compared to a method that is up to 29% slower.
Feb 5, 2024

On Orthogonal Recurrent Neural Networks Quantization

In recent years, Orthogonal Recurrent Neural Networks (ORNNs) have gained popularity due to their ability to manage tasks involving long-term dependencies, such as the Copy-task, and their linear complexity. However, existing ORNNs utilize full precision weights and activations, which prevents their deployment on compact devices. In this paper, we explore the quantization of the weight matrices in ORNNs, leading to Quantized approximately Orthogonal RNNs (QORNNs). The construction of such networks remained an open problem, acknowledged for its inherent instability. We propose and investigate two strategies to learn QORNN by combining quantization-aware training (QAT) and orthogonal projections. We also study post-training quantization of the activations for pure integer computation of the recurrent loop. The most efficient fully-quantized models are currently the only alternatives for solving the Copy-task with 1000 timesteps. They also surpass existing quantized models on tasks requiring long-term dependencies, such as permuted MNIST as well as some Internet of Things (IoT) tasks. However, they are less effective on tasks where long short-term memory (LSTMs) and other gated RNNs outperform ORNNs.