Fix Cuda out of memory issue for eager runner (#6935)
Pull Request resolved: https://github.com/pytorch/executorch/pull/6866 This PR updates the eager runner to disable grad and save memory usage. It also update the prompt format to not include bos. ghstack-source-id: 254139542 Differential Revision: [D65962743](https://our.internmc.facebook.com/intern/diff/D65962743/) Co-authored-by: Lunwen He <lwhecser@gmail.com>
P
pytorchbot committed
7bfe3b9afc9d66eec35cfb6ff8d5c228f6347ce2
Parent: 8013822
Committed by GitHub <noreply@github.com>
on 11/18/2024, 10:31:27 PM