[CVS-172796] fix bfloat16 conversion when single cast node to bfloat16 #841
+1
−1
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
…use original bf16 outputs tensor
bopeng1234
changed the title
…ansform for OV CPU
mklimenk
approved these changes
Nov 3, 2025
|
@bopeng1234 . This simply ignores BF16-> FP16 for CPU. Why is this conversion needed for GPU and NPU? |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Description
Disable bfloat16 model conversion when the graph's node size <=1.
Motivation and Context
CVS-172796
bfloat16_fix::Transform made changes to the bfloat16 output model, changed the output type to float16.
When single node test, cast_op_test.cc, it only has one node "Cast", the output is changed to float16 by the transformation, but testcase still use it as bfloat16 tensor, which will cause a mismatch;
May need to disable the transformation when unit test runs. OR. Add a cast node before BF16 output node.