-
Notifications
You must be signed in to change notification settings - Fork 319
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Summary: It's been on the to-do list for a while to clean that up. It's only used in `export_program` to properly put the model in eval mode. Now that we only allow `nn.Module`, there are only two cases: `nn.Module`, which will have `eval()`, and `GraphModule`, which can use `torch.ao.quantization.move_exported_model_to_eval`, which we already called before with the `pt2_quant` flag. Now that the flag is not needed, remove it everywhere! We also promote the `quantize_and_export_program` function to `__init__.py` as a compiler API, because it can be quite useful. Differential Revision: D57491621
- Loading branch information
1 parent
0f21c66
commit 553b669
Showing
2 changed files
with
8 additions
and
10 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters