ggml : remove SVE paths #16314
Open
ggml : remove SVE paths #16314
+126
−891
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
github-actions
bot
added
the
ggml
|
To be clear, this is only removing SVE + GGML_SIMD usage, right? Effectively reverting #13843. Other uses of SVE still remain. |
|
Yes, just the GGML_SIMD related modifications - there is some bug there that causes the CI to fail, but it's too difficult to track without hardware. |
|
@vineelabhinav since you were the original author, are you interested in maintaining this code? Otherwise it will have to be removed. |
Hi, This CI Failure is due to SVE Code Implementation of |
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Outdated suggestions cannot be applied.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.
The SVE builds have been broken for quite some time (https://github.com/ggml-org/llama.cpp/actions/runs/18070620247/job/51419855630). Additionally the SVE code as it is introduces a lot of complexity and duplication because it does not fit into the existing
GGML_SIMDpattern. I don't think it is worth having it in this state.It can be reintroduced after good CI coverage is added, the correctness is verified and it is reworked in some better way that is more inline with the existing code.