Fix support of "inputs_embeds" input of VLMs in SDPAToPA transformation #28674
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
CuriousPanCake
changed the title
github-actions
bot
added
the
category: transformations
itikhono
reviewed
Jan 27, 2025
itikhono
reviewed
Jan 27, 2025
itikhono
reviewed
Feb 3, 2025
| @@ -904,6 +903,551 @@ TEST_P(SDPAToPATest, SDPAToPA_Baichuan2_13b_General) { | |||
| } | |||
| } | |||
|
|
|||
| TEST_P(SDPAToPATest, SDPAToPA_nanoLLaVA_General) { | |||
| { | |||
| auto beam_idx = make_param(PartialShape{DYN}, element::i32, "beam_idx"); | |||
There was a problem hiding this comment.
It looks like, we need to simplify the test
It's better to do in the next PR
itikhono
approved these changes
Feb 3, 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Outdated suggestions cannot be applied.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.
VLMs have tokens and their generation already served as the "inputs_embeds" input, so there's no need to transform the input in the way this is done for "input_ids".
Tickets:
Signed-off-by: Andrii Staikov [email protected]