mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-06-25 09:09:07 -04:00
Code Issues Packages Projects Releases Wiki Activity

docs(llama-cpp): correct run.sh comment for arm64/darwin cpu-all

Browse Source 
arm64 and darwin CPU images now also ship llama-cpp-cpu-all (not fallback-only);
only GPU images ship fallback-only. Fix the stale comment to match.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]
This commit is contained in:
Ettore Di Giacinto
2026-06-25 07:05:06 +00:00
parent 292c1cab94
commit c23fc5fb42
1 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
backend/cpp/llama-cpp/run.sh
View File

@@ -12,9 +12,10 @@ grep -e "flags" /proc/cpuinfo | head -1
BINARY=llama-cpp-fallback
# x86 ships a single llama-cpp-cpu-all built with ggml CPU_ALL_VARIANTS: ggml's backend
# registry dlopens the best libggml-cpu-*.so for this host, so no shell-side AVX probing.
# arm64/darwin builds ship only llama-cpp-fallback, so fall back to it when cpu-all absent.
# CPU images (x86, arm64, darwin) ship a single llama-cpp-cpu-all built with ggml
# CPU_ALL_VARIANTS: ggml's backend registry dlopens the best libggml-cpu-*.so for this
# host, so no shell-side AVX probing. GPU images (cublas/sycl/vulkan/hipblas) ship only
# llama-cpp-fallback (the accelerator does the compute), so fall back to it when absent.
if [ -e $CURDIR/llama-cpp-cpu-all ]; then
BINARY=llama-cpp-cpu-all
fi