[Draft] Add self-detecting on-the-fly bfloat16->float16 conversion pass #741
+83
−6
Conversation
This file contains hidden or 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
mklimenk
changed the title
sfatimar
reviewed
Jul 15, 2025
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Outdated suggestions cannot be applied.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.
A follow-up to #740 with changed logic. Instead of relying on an external configuration key, perform bfloat16->float16 conversion in case there is at least one tensor in bfloat16 in the model.
Depending on the discussion, one of those PRs will be closed in favor of another. Keeping this one as a draft for now.
https://jira.devtools.intel.com/browse/CVS-170592