forked from intel/ai-reference-models
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* Changed the attention part so that it can utilize the existing fusion of batchmatmul+mul+addv2, and also use static varibles to reduce redundant compution * fixed a minor bug for a static variable * Changed the model so that the reshape can be moved out of dense layer so that we can fuse the ops in the dense layers * Changed the depth of attention to a static variable
- Loading branch information
Showing
2 changed files
with
17 additions
and
8 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