-
Notifications
You must be signed in to change notification settings - Fork 12.8k
Closed
Labels
bug-unconfirmedhigh severityUsed to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)
Description
What happened?
When compiling with Vulkan support on -DGGML_VULKAN=on
and GCC, after running llama-cli
I get a SIGSEGV on the ggml_log_internal_v
function, in particular on the first vsnprintf
line.
Searching online I found a lot of issues with vsnprintf and %s
. I tried removing the statement using that log function with a %s and it works:
Name and Version
Cannot run as it crashes before printing anything useful
./build/bin/llama-cli --version
ggml_vulkan: Found 1 Vulkan devices:
fish: Job 1, './build/bin/llama-cli --version' terminated by signal SIGSEGV (Address boundary error)
Git rev: 75207b3
gcc -v
Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib64/gcc/x86_64-suse-linux/14/lto-wrapper
OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa
OFFLOAD_TARGET_DEFAULT=1
Target: x86_64-suse-linux
Configured with: ../configure CFLAGS=' -O2 -funwind-tables -fasynchronous-unwind-tables -fstack-clash-protection -Werror=return-type -g' CXXFLAGS=' -O2 -funwind-tables -fasynchronous-unwind-tables -fstack-clash-protection -Werror=return-type -g' XCFLAGS=' -O2 -funwind-tables -fasynchronous-unwind-tables -fstack-clash-protection -Werror=return-type -g' TCFLAGS=' -O2 -funwind-tables -fasynchronous-unwind-tables -fstack-clash-protection -Werror=return-type -g' GDCFLAGS=' -O2 -funwind-tables -fasynchronous-unwind-tables -fstack-clash-protection -g' --prefix=/usr --infodir=/usr/share/info --mandir=/usr/share/man --libdir=/usr/lib64 --libexecdir=/usr/lib64 --enable-languages=c,c++,objc,fortran,obj-c++,ada,go,d,jit,rust,m2 --enable-offload-targets=nvptx-none,amdgcn-amdhsa, --enable-offload-defaulted --without-cuda-driver --enable-host-shared --enable-checking=release --disable-werror --with-gxx-include-dir=/usr/include/c++/14 --with-libstdcxx-zoneinfo=/usr/share/zoneinfo --enable-ssp --disable-libssp --disable-libvtv --enable-cet=auto --disable-libcc1 --enable-plugin --with-bugurl=https://bugs.opensuse.org/ --with-pkgversion='SUSE Linux' --with-slibdir=/lib64 --with-system-zlib --enable-libstdcxx-allocator=new --disable-libstdcxx-pch --enable-libphobos --enable-version-specific-runtime-libs --with-gcc-major-version-only --enable-linker-build-id --enable-linux-futex --enable-gnu-indirect-function --program-suffix=-14 --without-system-libunwind --enable-multilib --with-arch-32=x86-64 --with-tune=generic --with-build-config=bootstrap-lto-lean --enable-link-serialization --build=x86_64-suse-linux --host=x86_64-suse-linux
Thread model: posix
Supported LTO compression algorithms: zlib zstd
gcc version 14.2.1 20241007 [revision 4af44f2cf7d281f3e4f3957efce10e8b2ccb2ad3] (SUSE Linux)
What operating system are you seeing the problem on?
Linux
Relevant log output
./build/bin/llama-cli --version
ggml_vulkan: Found 1 Vulkan devices:
fish: Job 1, './build/bin/llama-cli --version' terminated by signal SIGSEGV (Address boundary error)
Metadata
Metadata
Assignees
Labels
bug-unconfirmedhigh severityUsed to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)Used to report high severity bugs in llama.cpp (Malfunctioning hinder important workflow)