Fix PositionIdsReplacer for Qwen #28203
Open
+8
−5
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
github-actions
bot
added
the
category: transformations
rkazants
reviewed
Dec 25, 2024
| auto p_neg_const = wrap_type<v0::Constant>(); | ||
| auto p_neg_mul = wrap_type<v1::Multiply>({p_current_len, p_neg_const}); | ||
| // the rotary_emb_cos/rotary_emb_sin are sliced by the total length [1,..4096,1,128] | ||
| auto p_rotary_emb_sincos = wrap_type<v0::Constant>(); | ||
| auto p_slice_1 = wrap_type<v8::Slice>({p_rotary_emb_sincos, _const(), p_opt_reshape, _const(), _const()}); | ||
| auto p_slice_2 = wrap_type<v8::Slice>({p_slice_1, p_neg_mul, _const(), _const(), _const()}); | ||
|
|
There was a problem hiding this comment.
can we cover this case by some test from model_hub_tests?
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Outdated suggestions cannot be applied.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.
Details:
The "current len" pattern might be created in 2 different ways in the Qwen model.
After one of the comments in the review (https://github.com/openvinotoolkit/openvino/pull/28067/files) was resolved, we made the pattern stricter, it stopped covering one of the cases.
Tickets: