TR2024-105
Hardware-Efficient Quantization for Green Custom Foundation Models
-
- , "Hardware-Efficient Quantization for Green Custom Foundation Models", International Conference on Machine Learning (ICML), July 2024.BibTeX TR2024-105 PDF Presentation
- @inproceedings{Koike-Akino2024jul2,
- author = {{Koike-Akino, Toshiaki and Meng Chang and Cevher, Volkan and De Micheli, Giovanni}},
- title = {Hardware-Efficient Quantization for Green Custom Foundation Models},
- booktitle = {International Conference on Machine Learning (ICML)},
- year = 2024,
- month = jul,
- url = {https://www.merl.com/publications/TR2024-105}
- }
- , "Hardware-Efficient Quantization for Green Custom Foundation Models", International Conference on Machine Learning (ICML), July 2024.
-
MERL Contact:
-
Research Areas:
Abstract:
We propose a new hardware-efficient quantization (HEQ) for low-power full-custom foundation models. The HEQ jointly optimizes multiplier hardware and weight quantization to minimize the total power consumption. Exploiting power profile of custom multipliers, our method achieves a significant power reduction up to 20 folds.