Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_ai 85% Match Research Paper ML Engineers,AI Researchers,Hardware Designers,Developers deploying AI models 1 week ago

STaMP: Sequence Transformation and Mixed Precision for Low-Precision Activation Quantization

generative-ai › autoregressive
📄 Abstract

Abstract: Quantization is the key method for reducing inference latency, power and memory footprint of generative AI models. However, accuracy often degrades sharply when activations are quantized below eight bits. Recent work suggests that invertible linear transformations (e.g. rotations) can aid quantization, by reparameterizing feature channels and weights. In this paper, we propose \textit{Sequence Transformation and Mixed Precision} (STaMP) quantization, a novel strategy that applies linear transformations along the \textit{sequence} dimension to exploit the strong local correlation in language and visual data. By keeping a small number of tokens in each intermediate activation at higher precision, we can maintain model accuracy at lower (average) activations bit-widths. We evaluate STaMP on recent LVM and LLM architectures, demonstrating that it significantly improves low bit width activation quantization and complements established activation and weight quantization methods including recent feature transformations.
Authors (5)
Marco Federici
Riccardo Del Chiaro
Boris van Breugel
Paul Whatmough
Markus Nagel
Submitted
October 30, 2025
arXiv Category
cs.LG
arXiv PDF

Key Contributions

Proposes STaMP quantization, a novel strategy that applies linear transformations along the sequence dimension for low-precision activation quantization. It maintains accuracy at lower bit-widths by keeping a small number of tokens at higher precision, significantly improving efficiency for LLMs and LVMs.

Business Value

Enables the deployment of large generative AI models on resource-constrained devices and reduces operational costs for cloud-based inference, making advanced AI more accessible and efficient.