update cmake flags for `amd64` macOS (#1780)

* update cmake flags for intel macOS

* remove `LLAMA_K_QUANTS`

* put back `CMAKE_OSX_DEPLOYMENT_TARGET` and disable `LLAMA_F16C`

llm/llama.cpp/gen_common.sh

@@ -3,14 +3,13 @@
 init_vars() {
     LLAMACPP_DIR=gguf
     PATCHES="0001-Expose-callable-API-for-server.patch"
-    CMAKE_DEFS="-DLLAMA_ACCELERATE=on"
-    # TODO - LLAMA_K_QUANTS is stale and needs to be mapped to newer cmake settings
+    CMAKE_DEFS=""
     CMAKE_TARGETS="--target ggml --target ggml_static --target llama --target build_info --target common --target ext_server --target llava_static"
     if echo "${CGO_CFLAGS}" | grep -- '-g' >/dev/null; then
-        CMAKE_DEFS="-DCMAKE_BUILD_TYPE=RelWithDebInfo -DCMAKE_VERBOSE_MAKEFILE=on -DLLAMA_GPROF=on -DLLAMA_SERVER_VERBOSE=on ${CMAKE_DEFS}"
+        CMAKE_DEFS="-DCMAKE_BUILD_TYPE=RelWithDebInfo -DCMAKE_VERBOSE_MAKEFILE=on -DLLAMA_GPROF=on -DLLAMA_SERVER_VERBOSE=on"
     else
         # TODO - add additional optimization flags...
-        CMAKE_DEFS="-DCMAKE_BUILD_TYPE=Release -DLLAMA_SERVER_VERBOSE=off ${CMAKE_DEFS}"
+        CMAKE_DEFS="-DCMAKE_BUILD_TYPE=Release -DLLAMA_SERVER_VERBOSE=off"
     fi
 }
 

llm/llama.cpp/gen_darwin.sh

@@ -9,11 +9,11 @@ set -o pipefail
 echo "Starting darwin generate script"
 source $(dirname $0)/gen_common.sh
 init_vars
-CMAKE_DEFS="-DCMAKE_OSX_DEPLOYMENT_TARGET=11.0 -DLLAMA_METAL=on ${CMAKE_DEFS}"
+CMAKE_DEFS="-DCMAKE_OSX_DEPLOYMENT_TARGET=11.0 -DLLAMA_METAL=on -DLLAMA_ACCELERATE=on ${CMAKE_DEFS}"
 BUILD_DIR="gguf/build/darwin/metal"
 case "${GOARCH}" in
 "amd64")
-    CMAKE_DEFS="-DCMAKE_SYSTEM_PROCESSOR=x86_64 -DCMAKE_OSX_ARCHITECTURES=x86_64 ${CMAKE_DEFS}"
+    CMAKE_DEFS="-DCMAKE_SYSTEM_PROCESSOR=x86_64 -DCMAKE_OSX_ARCHITECTURES=x86_64 -DLLAMA_NATIVE=off -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off ${CMAKE_DEFS}"
     ;;
 "arm64")
     CMAKE_DEFS="-DCMAKE_SYSTEM_PROCESSOR=arm64 -DCMAKE_OSX_ARCHITECTURES=arm64 ${CMAKE_DEFS}"

llm/llama.cpp/gen_linux.sh

@@ -42,7 +42,7 @@ echo "Starting linux generate script"
 if [ -z "${CUDACXX}" -a -x /usr/local/cuda/bin/nvcc ]; then
     export CUDACXX=/usr/local/cuda/bin/nvcc
 fi
-COMMON_CMAKE_DEFS="-DCMAKE_POSITION_INDEPENDENT_CODE=on -DLLAMA_ACCELERATE=on -DLLAMA_NATIVE=off -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off"
+COMMON_CMAKE_DEFS="-DCMAKE_POSITION_INDEPENDENT_CODE=on -DLLAMA_NATIVE=off -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off"
 source $(dirname $0)/gen_common.sh
 init_vars
 git_module_setup

llm/llama.cpp/gen_windows.ps1

@@ -4,7 +4,7 @@ $ErrorActionPreference = "Stop"
 
 function init_vars {
     $script:patches = @("0001-Expose-callable-API-for-server.patch")
-    $script:cmakeDefs = @("-DBUILD_SHARED_LIBS=on", "-DLLAMA_NATIVE=off", "-DLLAMA_F16C=off", "-DLLAMA_FMA=off", "-DLLAMA_AVX512=off", "-DLLAMA_AVX2=off", "-DLLAMA_AVX=on", "-DLLAMA_K_QUANTS=on", "-DLLAMA_ACCELERATE=on", "-A","x64")
+    $script:cmakeDefs = @("-DBUILD_SHARED_LIBS=on", "-DLLAMA_NATIVE=off", "-DLLAMA_F16C=off", "-DLLAMA_FMA=off", "-DLLAMA_AVX512=off", "-DLLAMA_AVX2=off", "-DLLAMA_AVX=on", "-A","x64")
     $script:cmakeTargets = @("ggml", "ggml_static", "llama", "build_info", "common", "ext_server_shared", "llava_static")
     if ($env:CGO_CFLAGS -contains "-g") {
         $script:cmakeDefs += @("-DCMAKE_VERBOSE_MAKEFILE=on", "-DLLAMA_SERVER_VERBOSE=on")