Zero-Shot Dynamic Quantization for Transformer Inference
We introduce a novel run-time method for significantly reducing the accuracy loss associated with quantizing BERT-like models to 8-bit integers. Existing methods for quantizing models either modify the training procedure,or they require an additional calibration step to adjust parameters that also requires a selected held-out dataset. Our method permits taking advantage of quantization without the need for these adjustments. We present results on several NLP tasks demonstrating the usefulness of this technique.
Code (4)
Tasks
QuantizationSimilar Papers 제목 키워드 기반
ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers
Quantization techniques are pivotal in reducing the memory and computational demands of deep neural network inference. Existing solutions, such as ZeroQuant, offer dynamic quantization for models like BERT and GPT but ov…
QuantizationZero-Shot Sharpness-Aware Quantization for Pre-trained Language Models
Quantization is a promising approach for reducing memory overhead and accelerating inference, especially in large pre-trained language model (PLM) scenarios. While having no access to original training data due to securi…
Language ModelingLanguage ModellingQuantizationThe case for 4-bit precision: k-bit Inference Scaling Laws
Quantization methods reduce the number of bits required to represent each parameter in a model, trading accuracy for smaller memory footprints and inference latencies. However, the final model size depends on both the nu…
QuantizationZeroQ: A Novel Zero Shot Quantization Framework
Quantization is a promising approach for reducing the inference time and memory footprint of neural networks. However, most existing quantization methods require access to the original training dataset for retraining dur…
Data Free QuantizationModel CompressionNeural Network CompressionQuantizationA Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics
Quantizing the floating-point weights and activations of deep convolutional neural networks to fixed-point representation yields reduced memory footprints and inference time. Recently, efforts have been afoot towards zer…
Quantization