Fix cpu performance debug builds #651
Merged
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
The OS detection code was bothering me as it wasn't properly doing cross compilation (some places were and some weren't). Additionally, the OS detection was a bit haphazard. This is a pure cleanup that parses the information in TARGET up-front into an enum that is then checked instead of working with strings.
MarcusDunn
approved these changes
Feb 13, 2025
This was referenced Feb 20, 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Outdated suggestions cannot be applied.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.
Fixes #649 but does not fix the 30% perf reduction from stock CPU llama.cpp cli as I haven't tracked that down.
I first did a cleanup commit that should be identical behavior as before but made the OS target detection logic a lot more robust in cross-compilation environments through the use of an enum instead of ad-hoc places that accidentally used
cfg!(windows)/cfg!(target_os =)which pick up the host not the target. Hopefully that's OK. Couldn't find a crate that did this out of the box unfortunately but I didn't look that hard. The second commit that has the fix is a lot smaller.