[Snippets][CPU] Added KVCacheMatcher check for LLM in MHATokenization #28812
+36
−38
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
6fedb81 to
6cf3934
Compare
sshlyapn
approved these changes
Feb 17, 2025
itikhono
reviewed
Feb 18, 2025
itikhono
reviewed
Feb 18, 2025
itikhono
reviewed
Feb 18, 2025
6cf3934 to
0c75162
Compare
itikhono
approved these changes
Feb 19, 2025
Comment on lines
1059
to
1060
| ov::op::util::has_op_with_type<intel_cpu::ScaledDotProductAttentionWithKVCache>(model) || | ||
| ov::op::util::has_op_with_type<ov::op::PagedAttentionExtension>(model); |
There was a problem hiding this comment.
Do we still need these checks here?
If we do, can move them inside is_large_language_model? Since we created a dedicated helper for this check, all the logic related should be inside. What do you think?
There was a problem hiding this comment.
At first time I just wanted to align with GPU check - I was not sure that PA should be in the check is_llm in GPU Plugin. But I found that they updated the condition included PA. So I moved PA to common helper leaving only SDPAWithKVCache because it's CPU-specific op.
Thanks!
0c75162 to
3c8a73c
Compare
3c8a73c to
782ed19
Compare
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Outdated suggestions cannot be applied.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:
is_LLMcheck from GPU plugin to common part to reuse in other pluginsis_large_language_modelfunction in check for LLM in MHATokenization in CPU PluginTickets: