[CPU] Add gate_up_swapped support for LLM MLP fusion #32683
+124
−27
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
Contributor
Author
|
Hi, @chenhu-wang : could you please help review this pr when you are free? thanks. |
chenhu-wang
reviewed
Nov 5, 2025
Comment on lines
34
to
+35
| bool gate_up_combined; | ||
| bool gate_up_swapped; // true when VariadicSplit output[1] connects to gate instead of up |
Contributor
There was a problem hiding this comment.
let's combine this two flags(gate_up_combined+gate_up_swapped) into one, such as
enum class gate_up_type : uint8_t {
gate_up_separate,
gate_first,
up_first
};
to better indicate how gate up weight provided.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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:
Tickets: