ggml: ggml-cpu: force-no-lto-for-cpu-feats#19609
Merged
ggerganov merged 1 commit intoggml-org:masterfrom Feb 17, 2026
Merged
Conversation
When LTO enabled in build environments it forces all builds to have LTO in place. But feature detection logic is fragile, and causing Illegal instruction errors with lto. This disables LTO for the feature detection code to prevent cross-module optimization from inlining architecture-specific instructions into the score function. Without this, LTO can cause SIGILL when loading backends on older CPUs (e.g., loading power10 backend on power9 crashes before feature check runs).
github-actions
Bot
added
the
ggml
Member
|
@shalinib-ibm Maybe you could take a look at this? They have a discussion going on at https://salsa.debian.org/deeplearning-team/ggml/-/merge_requests/6 already. |
Collaborator
|
While I'm not entirely sure what the root cause for the |
ggerganov
approved these changes
Feb 16, 2026
Member
ggerganov
left a comment
ggerganov
left a comment
There was a problem hiding this comment.
Waiting for CI before merge.
Contributor
Hi all, thanks for flagging this. Since LTO is disabled only for the CPU feature-detection code, this change has no impact on performance-critical paths. We verified this by running llama-bench with and without the change and observed no performance regressions. |
taronaeo
approved these changes
Feb 17, 2026
liparetejas
pushed a commit
to liparetejas/llama.cpp
that referenced
this pull request
Feb 23, 2026
When LTO enabled in build environments it forces all builds to have LTO in place. But feature detection logic is fragile, and causing Illegal instruction errors with lto. This disables LTO for the feature detection code to prevent cross-module optimization from inlining architecture-specific instructions into the score function. Without this, LTO can cause SIGILL when loading backends on older CPUs (e.g., loading power10 backend on power9 crashes before feature check runs).
bartowski1182
pushed a commit
to bartowski1182/llama.cpp
that referenced
this pull request
Mar 2, 2026
When LTO enabled in build environments it forces all builds to have LTO in place. But feature detection logic is fragile, and causing Illegal instruction errors with lto. This disables LTO for the feature detection code to prevent cross-module optimization from inlining architecture-specific instructions into the score function. Without this, LTO can cause SIGILL when loading backends on older CPUs (e.g., loading power10 backend on power9 crashes before feature check runs).
ArberSephirotheca
pushed a commit
to ArberSephirotheca/llama.cpp
that referenced
this pull request
Mar 3, 2026
When LTO enabled in build environments it forces all builds to have LTO in place. But feature detection logic is fragile, and causing Illegal instruction errors with lto. This disables LTO for the feature detection code to prevent cross-module optimization from inlining architecture-specific instructions into the score function. Without this, LTO can cause SIGILL when loading backends on older CPUs (e.g., loading power10 backend on power9 crashes before feature check runs).
Seunghhon
pushed a commit
to Seunghhon/llama.cpp
that referenced
this pull request
Apr 26, 2026
When LTO enabled in build environments it forces all builds to have LTO in place. But feature detection logic is fragile, and causing Illegal instruction errors with lto. This disables LTO for the feature detection code to prevent cross-module optimization from inlining architecture-specific instructions into the score function. Without this, LTO can cause SIGILL when loading backends on older CPUs (e.g., loading power10 backend on power9 crashes before feature check runs).
rsenthilkumar6
pushed a commit
to rsenthilkumar6/llama.cpp
that referenced
this pull request
May 1, 2026
When LTO enabled in build environments it forces all builds to have LTO in place. But feature detection logic is fragile, and causing Illegal instruction errors with lto. This disables LTO for the feature detection code to prevent cross-module optimization from inlining architecture-specific instructions into the score function. Without this, LTO can cause SIGILL when loading backends on older CPUs (e.g., loading power10 backend on power9 crashes before feature check runs).
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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.
When LTO enabled in build environments it forces all builds to have LTO in place. But feature detection logic is fragile, and causing Illegal instruction errors with lto. This disables LTO for the feature detection code to prevent cross-module optimization from inlining architecture-specific instructions into the score function. Without this, LTO can cause SIGILL when loading backends on older CPUs (e.g., loading power10 backend on power9 crashes before feature check runs).
Please also see https://salsa.debian.org/deeplearning-team/ggml/-/merge_requests/6 for more information about the issue we saw on ppc64el builds with LTO enabled in ubuntu.
Make sure to read the contributing guidelines before submitting a PR