mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-25 09:09:07 -04:00
379fa3e525
- llama-cpp: x86 AND arm64 now use the single llama-cpp-cpu-all build (only hipblas keeps the fallback build). ggml's arm64 variant table (armv8.x / armv9.x, plus apple_m* on darwin) is selected at runtime. - turboquant: same recipe via a turboquant-cpu-all target. turboquant copies backend/cpp/llama-cpp's CMakeLists.txt + Makefile per flavor, so the hw_grpc_proto STATIC fix and the SHARED_LIBS / EXTRA_CMAKE_ARGS make-vars are inherited; the target just passes SHARED_LIBS=ON, the DL flags and --target ggml through, then collects the .so set. run.sh and package.sh updated to ship/select turboquant-cpu-all. - Makefile lib-collection find now also matches *.dylib (for the darwin build, which emits dylibs rather than .so). ik-llama-cpp is intentionally left unchanged: its pinned ggml has no CPU_ALL_VARIANTS support and its IQK kernels require AVX2, so the per-microarch dynamic backend set does not apply. Scope still excludes the darwin packaging wiring (separate change). Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Assisted-by: Claude:claude-opus-4-8 [Claude Code]
51 lines
1.4 KiB
Bash
Executable File
51 lines
1.4 KiB
Bash
Executable File
#!/bin/bash
|
|
set -ex
|
|
|
|
# Get the absolute current dir where the script is located
|
|
CURDIR=$(dirname "$(realpath $0)")
|
|
|
|
cd /
|
|
|
|
echo "CPU info:"
|
|
grep -e "model\sname" /proc/cpuinfo | head -1
|
|
grep -e "flags" /proc/cpuinfo | head -1
|
|
|
|
BINARY=turboquant-fallback
|
|
|
|
# x86/arm64 ship a single turboquant-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
|
|
# probing. ROCm ships only turboquant-fallback, so fall back to it when cpu-all is absent.
|
|
if [ -e $CURDIR/turboquant-cpu-all ]; then
|
|
BINARY=turboquant-cpu-all
|
|
fi
|
|
|
|
if [ -n "$LLAMACPP_GRPC_SERVERS" ]; then
|
|
if [ -e $CURDIR/turboquant-grpc ]; then
|
|
BINARY=turboquant-grpc
|
|
fi
|
|
fi
|
|
|
|
# Extend ld library path with the dir where this script is located/lib
|
|
if [ "$(uname)" == "Darwin" ]; then
|
|
export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
|
|
else
|
|
export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
|
|
# Tell rocBLAS where to find TensileLibrary data (GPU kernel tuning files)
|
|
if [ -d "$CURDIR/lib/rocblas/library" ]; then
|
|
export ROCBLAS_TENSILE_LIBPATH=$CURDIR/lib/rocblas/library
|
|
fi
|
|
fi
|
|
|
|
# If there is a lib/ld.so, use it
|
|
if [ -f $CURDIR/lib/ld.so ]; then
|
|
echo "Using lib/ld.so"
|
|
echo "Using binary: $BINARY"
|
|
exec $CURDIR/lib/ld.so $CURDIR/$BINARY "$@"
|
|
fi
|
|
|
|
echo "Using binary: $BINARY"
|
|
exec $CURDIR/$BINARY "$@"
|
|
|
|
# We should never reach this point, however just in case we do, run fallback
|
|
exec $CURDIR/turboquant-fallback "$@"
|