Update SDPA to PagedAttention transformation to support phi3 sliding window #29608
+528
−361
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
category: Core
Is a solution generic or phi3 specific? We have other models with sliding window support like Mistral. |
|
I will check it with the Mistral model |
itikhono
commented
Mar 25, 2025
itikhono
commented
Mar 28, 2025
| {{"variable_id", "varid_1"}, {"variable_type", "f32"}, {"variable_shape", PartialShape{DYN, 32, DYN, 96}}}); | ||
| auto Gather1 = makeOP<opset8::Gather>({ReadValue, Parameter, 0}, {{"batch_dims", 0}}); | ||
| auto Constant7 = makeConst(element::f32, ov::Shape({1, 1, 3072}), MOCK_VALUE); | ||
| auto Constant8 = makeConst(element::u8, ov::Shape({32064, 3072}), MOCK_VALUE); |
There was a problem hiding this comment.
todo: decrease the weights size for this test
|
@sshlyapn could you help to check these changes on GPU? |
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Outdated suggestions cannot be applied.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:
Update SDPA to PagedAttention transformation to support phi3 sliding window
Tickets: