happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

ggml: ggml-cpu: force-no-lto-for-cpu-feats 

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 commit is contained in:
Talha Can Havadar 2026-02-13 23:22:22 +01:00 committed by Talha Can Havadar
parent 05a6f0e894
commit 9937626f47
No known key found for this signature in database
GPG Key ID: 2574387962FEB0D1
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ggml/src/ggml-cpu/CMakeLists.txt
View File

@ -9,6 +9,11 @@ function(ggml_add_cpu_backend_features cpu_name arch)
target_compile_definitions(${GGML_CPU_FEATS_NAME} PRIVATE ${ARGN})
target_compile_definitions(${GGML_CPU_FEATS_NAME} PRIVATE GGML_BACKEND_DL GGML_BACKEND_BUILD GGML_BACKEND_SHARED)
set_target_properties(${GGML_CPU_FEATS_NAME} PROPERTIES POSITION_INDEPENDENT_CODE ON)
# Disable LTO for the feature detection code to prevent cross-module optimization
# from inlining architecture-specific instructions into the score function.
# Without this, LTO can cause SIGILL when loading backends on older CPUs
# (e.g., loading power10 backend on power9 crashes before feature check runs).
target_compile_options(${GGML_CPU_FEATS_NAME} PRIVATE -fno-lto)
target_link_libraries(${cpu_name} PRIVATE ${GGML_CPU_FEATS_NAME})
endfunction()