hparams : add SWA rope parameters #12374
Merged
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
|
Would this necessitate reconverting Gemma 3 since we no longer have hard coded detection for the Arch? Or is it using already existing metadata? |
Member
Author
|
No, the change is backwards compatible. It's a simple refactoring of the code, to make it less special-cased. |
jpohhhh
pushed a commit
to Telosnex/llama.cpp
that referenced
this pull request
Mar 14, 2025
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Mar 19, 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Outdated suggestions cannot be applied.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.
cont #12373
Add notion of SWA-related rope parameters. Currently, only part of the
hparams, but in the future could be added to thecparamsif we want to be able to control these per-context.Also add debug logs to know which layers use SWA.