SHARD: A Compatibility Framework for Deploying Transformer Models on Edge NPUs
| Title: | SHARD: A Compatibility Framework for Deploying Transformer Models on Edge NPUs |
|---|---|
| Authors: | Mohan, Adhitya; Thompson, Richard; Keller, Eric; Zhao, Mark |
| Source: | Proceedings of the Sixth European Workshop on Machine Learning and Systems. :200-207 |
| Availability: | http://dl.acm.org/doi/10.1145/3805621.3807618 |
| Database: | ACM Full-Text Collection |