DeepAI AI Chat
Log In Sign Up

Automated Backend-Aware Post-Training Quantization

by   Ziheng Jiang, et al.

Quantization is a key technique to reduce the resource requirement and improve the performance of neural network deployment. However, different hardware backends such as x86 CPU, NVIDIA GPU, ARM CPU, and accelerators may demand different implementations for quantized networks. This diversity calls for specialized post-training quantization pipelines to built for each hardware target, an engineering effort that is often too large for developers to keep up with. We tackle this problem with an automated post-training quantization framework called HAGO. HAGO provides a set of general quantization graph transformations based on a user-defined hardware specification and implements a search mechanism to find the optimal quantization strategy while satisfying hardware constraints for any model. We observe that HAGO achieves speedups of 2.09x, 1.97x, and 2.48x on Intel Xeon Cascade Lake CPUs, NVIDIA Tesla T4 GPUs, ARM Cortex-A CPUs on Raspberry Pi4 relative to full precision respectively, while maintaining the highest reported post-training quantization accuracy in each case.


page 2

page 8


HPTQ: Hardware-Friendly Post Training Quantization

Neural network quantization enables the deployment of models on edge dev...

QFT: Post-training quantization via fast joint finetuning of all degrees of freedom

The post-training quantization (PTQ) challenge of bringing quantized neu...

RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization

We introduce a Power-of-Two post-training quantization( PTQ) method for ...

MQBench: Towards Reproducible and Deployable Model Quantization Benchmark

Model quantization has emerged as an indispensable technique to accelera...

Improving Neural Network Quantization without Retraining using Outlier Channel Splitting

Quantization can improve the execution latency and energy efficiency of ...

Attention Round for Post-Training Quantization

At present, the quantification methods of neural network models are main...

Improving Neural Network Quantization using Outlier Channel Splitting

Quantization can improve the execution latency and energy efficiency of ...