From c23fc5fb42c7e09e196a34fa2eb0b3a6a865ad84 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Thu, 25 Jun 2026 07:05:06 +0000 Subject: [PATCH] docs(llama-cpp): correct run.sh comment for arm64/darwin cpu-all 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 Assisted-by: Claude:claude-opus-4-8 [Claude Code] --- backend/cpp/llama-cpp/run.sh | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/backend/cpp/llama-cpp/run.sh b/backend/cpp/llama-cpp/run.sh index f3f289495..db8498f4b 100755 --- a/backend/cpp/llama-cpp/run.sh +++ b/backend/cpp/llama-cpp/run.sh @@ -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