cs.LGMar 4, 2026

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

Authors: Pranav Kumar Kaliaperumal

Organizations: M.S. Computer Science, University of Colorado Denver, Aurora, Colorado, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

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.

Figures & tables

MethodAccuracy (%)Δ\Delta vs FP32
FP3289.66–
W8A854.33-35.33
Mixed Precision89.42-0.24
PEG (K=3,P)66.12-23.54
Percentile50.54-39.12
TABLE I: Validation Accuracy on QNLI
Methodp50 (ms)p95 (ms)VRAM (MB)Size (MB)
FP3258.3859.08483.7417.7
W8A858.6159.13485.5418.3
MP-PTQ58.7759.55486.3418.3
PEG58.9759.81486.3419.6
Percentile59.1259.77486.3418.3
TABLE II: Latency, VRAM, and Serialized Model Size
LayerMean VarianceKurtosisTop-1% Energy
Embeddings (0)0.2590.15
Layer 10.32140.21
Layer 20.38410.29
Layer 40.46730.37
Layer 100.551350.49
Layer 110.582710.55
TABLE III: Depth-wise Activation Outlier Statistics (FP32)
More in this topic

Activation Outliers

Activation outliers are unusually large or structured neural-network activations that complicate quantization, training stability, and efficient inference.

See all 17 papers

Explore similar work

CardsList
May 25, 2026

The Quantization Benefits of Residual-Free Transformers

Large-scale transformer training and deployment are increasingly constrained by the transfer of activations, gradients, and optimizer states across accelerators. Low-bit quantization offers a natural remedy, but transformer activations are often heavy-tailed and outlier-dominated, making simple quantization highly lossy. We show that this difficulty is not only a property of the quantizer, but also of the architecture. Specifically, residual connections can drive transformer activations away from Gaussianity during training. Using controlled comparisons between residual and residual-free transformers, we demonstrate that this effect leads to substantially higher quantization error and accuracy degradation at low precision in residual models. We explain the phenomenon through an excess kurtosis analysis, showing that residual mixing can amplify non-Gaussianity, whereas dense mixing in residual-free contracts non-Gaussianity. We then show that residual-free transformers can be made trainable using orthogonal initialization, spectral or second-order optimization, and depth-aware scaling of attention temperature. In language tasks, while there is a small drop in full precision performance, these models retain near-Gaussian activations and exhibit significantly improved robustness to low-bit quantization. Our results identify an accuracy--compressibility trade-off in transformer design and motivate architecture-level approaches to quantization-friendly foundation models.

Yiping Ji, Mahalakshmi Sabanayagam, Peyman Moghadam +2

Australian Institute for Machine Learning, Adelaide University · DATA61, CSIRO

TransformerActivation OutliersActivation QuantizationLow-Bit Quantization
AskPDF
Oct 7, 2026

TR-PTQ: High-Accuracy Integer-Only Transformer Post Training Quantization via Taylor Region Reformulation

Post-training quantization (PTQ) enables efficient deployment, yet transformer architectures remain challenging to quantize due to nonlinear layers. While existing methods attribute accuracy loss to insufficient numerical precision, often necessitating floating-point fallbacks, we demonstrate that degradation is actually driven by specific structural error sources. We find that learned scale parameters in normalization layers and compounded approximations in GELU are the primary error contributors, whereas SoftMax remains inherently robust to aggressive quantization. To address these bottlenecks, we introduce TR-PTQ, a unified integer-only formulation using shared Taylor Region (TR) exponential and logarithm primitives. This approach allows computationally expensive operations, including division and square roots, to be performed entirely in the log-domain via standard integer arithmetic. Combined with a calibration-free, outlier-aware optimization for LayerNorm parameters, our method eliminates the need for floating-point hardware units for nonlinearities, achieving less than 1.5% absolute accuracy degradation across vision and language benchmarks.

Eliyahu Levy, Adam Teman, Yoni Pugachov

Faculty of Engineering, Bar-Ilan University, Ramat Gan, Israel

Post-Training QuantizationNeural Network QuantizationActivation Quantization
AskPDF
Jan 29, 2026

Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models

Post-training quantization (PTQ) is a practical way to reduce the memory footprint of large language models, but low-bit quantization is sensitive to mismatches between the quantization codebook and the empirical weight/activation distributions. We revisit Benford-like leading-digit statistics as a lightweight diagnostic of scale-broad behavior in transformer tensors. Across several model families, we observe a consistent functional dichotomy: transformational nn.Linear weights tend to be Benford-like, whereas LayerNorm parameters systematically deviate. Motivated by this observation, we propose BenQ, a data-free PTQ codebook that uses a simple log-spaced grid as a proxy for scale-broad distributions and applies it selectively to transformational layers while keeping stability-critical parameters in higher precision. In 4-bit group-wise PTQ, BenQ consistently improves over uniform RTN and trades wins with NF4 across architectures and tasks, while remaining substantially simpler than optimization-based methods. We additionally report dynamic activation quantization as an exploratory stress test: the results show that log-spaced grids can reduce RTN failures in some families, but also reveal that outlier handling remains essential for reliable low-bit activation PTQ. Code is available at https://github.com/ufopcsilab/benford-quant.

Arthur Negrão, Pedro Silva, Vander L. S. Freitas +2

Postgraduate Program in Computer Science Federal University of Ouro Preto · Computing Department Federal University of Ouro Preto

LLM Quantization4-Bit QuantizationPost-Training QuantizationNeural Network Quantization
AskPDF