-
Notifications
You must be signed in to change notification settings - Fork 244
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Enable BF16 Concat linear for GPTJ/LLAMA models (#2349)
* Add tpp concat linear * refinement * Update linear_fusion.py * refinement * fix woq * enable concat linear with concat rope * code refine and pass ut * flake8 format * code refiement * minor fix --------- Co-authored-by: liangan1 <liangang.zhang@intel.com>
- Loading branch information
Showing
6 changed files
with
194 additions
and
73 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
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
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