-
Notifications
You must be signed in to change notification settings - Fork 2.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Op] Common RMS operation - corrected author #24539
[Op] Common RMS operation - corrected author #24539
Conversation
… before call to_shape
added rms transformations to common space deleted transformations fusion moved fusion tests deleted RMS op defined in gpu_plugin changed op name workgroupsize check in callback, changed opset name fixed formating fix code style -3rd attempt fix code style -4rd attempt moved transformation_callback check to begin of function, added check before call to_shape fixes in rms fusion
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM (This PR is a copy of #24057, with reviewers comments applied)
return std::make_shared<RMS>(new_args.at(0), | ||
new_args.at(1), | ||
m_epsilon); | ||
return std::make_shared<RMS>(new_args.at(0), new_args.at(1), m_epsilon); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The output_type
attribute should be provided to the cloned RMS op (but it was missed in the original file, so can be fixed separately):
return std::make_shared<RMS>(new_args.at(0), new_args.at(1), m_epsilon); | |
return std::make_shared<RMS>(new_args.at(0), new_args.at(1), m_epsilon, m_output_type); |
### Details: - Reference implementation and ref tests for [internal::RMS](https://github.com/openvinotoolkit/openvino/blob/70142121c1c632b6d710026150b0e6deb20b0e68/src/common/transformations/include/ov_ops/rms.hpp) (moved from gpu custom ops) available for common transformations - Enable Accuracy tests for RMSFusion transformation The changes moving RMS from gpu to internal are from PR: - #24539 (to be merged first) Internal RMS op docs: - #24564 ### Tickets: - Related to 136262 --------- Co-authored-by: michal-miotk <michal.miotk@intel.com> Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Details:
-move RMS operation to common internal opset
-move RMS fusion transformation to common part
-based on #24057
Tickets:
138554