How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917651230490624 |
|---|---|
| author | You, Jaeseong Park, Minseop Lee, Kyunggeun An, Seokjun Patel, Chirag Nage, Markus |
| author_facet | You, Jaeseong Park, Minseop Lee, Kyunggeun An, Seokjun Patel, Chirag Nage, Markus |
| contents | This paper investigates three different parameterizations of asymmetric uniform quantization for quantization-aware training: (1) scale and offset, (2) minimum and maximum, and (3) beta and gamma. We perform a comprehensive comparative analysis of these parameterizations' influence on quantization-aware training, using both controlled experiments and real-world large language models. Our particular focus is on their changing behavior in response to critical training hyperparameters, bit width and learning rate. Based on our investigation, we propose best practices to stabilize and accelerate quantization-aware training with learnable asymmetric quantization ranges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_16898 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training You, Jaeseong Park, Minseop Lee, Kyunggeun An, Seokjun Patel, Chirag Nage, Markus Machine Learning Artificial Intelligence This paper investigates three different parameterizations of asymmetric uniform quantization for quantization-aware training: (1) scale and offset, (2) minimum and maximum, and (3) beta and gamma. We perform a comprehensive comparative analysis of these parameterizations' influence on quantization-aware training, using both controlled experiments and real-world large language models. Our particular focus is on their changing behavior in response to critical training hyperparameters, bit width and learning rate. Based on our investigation, we propose best practices to stabilize and accelerate quantization-aware training with learnable asymmetric quantization ranges. |
| title | How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2404.16898 |