[OpenVINO backend] OpenVINOQuantizer #15
Merged
Conversation
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
Co-authored-by: Alexander Suslov <[email protected]>
ynimmaga
reviewed
Feb 12, 2025
| preset=preset, model_type=model_type, **kwargs | ||
| ) | ||
|
|
||
| def set_ignored_scope( |
There was a problem hiding this comment.
Is this function be exposed to the user so that they can tune the quantization process? If so, it will be good to mention in the documentation
There was a problem hiding this comment.
Agree! But I'm not sure which documentation to update: we don't have a document with describe the OpenVINOQuantizer yet. Should we perhaps create one?
ynimmaga
reviewed
Feb 12, 2025
ynimmaga
reviewed
Feb 12, 2025
Co-authored-by: Yamini Nimmagadda <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
aot_openvino_compiler.pyis updated with the quantization pipeline (timm and torchvision backends only)openvino_executor_runner.cppis updated to take several inputs / produce several outputs in a row. This allows to validate models converted to the edge (inspired by the qualcom example) (code style is refactored by clang-format)aot_openvino_compiler.pyis updated with a validation pipeline (timm and torchvision backends only)Test plan