Workaround for Assertion error when embedding with bge-m3 in lazy mode #2093
+16
−45
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
Signed-off-by: slokesha <[email protected]>
slokesha
requested review from
PatrykWo,
afierka-intel,
jikunshang,
kzawora-intel,
madamczyk-intel,
mgawarkiewicz-intel,
michalkuligowski,
mswiniarsk,
vivekgoe and
xuechendi
as code owners
Signed-off-by: slokesha <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Added Workaround for Assertion error when embedding with bge-m3 in lazy mode.
For RoBERTa models, the position_ids are recalculated using the function create_position_ids_from_input_ids_hpu().
However, due to a known issue on HPU where modifying an already allocated tensor in-place can lead to invalid or corrupted values, this workaround precomputes position_ids on the CPU using the corresponding input_ids.
The computed position_ids are then transferred to the HPU within hpu_model_runner to ensure correctness and avoid in-place modification issues.