Merge branch 'ollama:main' into main

llm/generate/gen_common.sh

@@ -133,13 +133,5 @@ install() {
 
 # Keep the local tree clean after we're done with the build
 cleanup() {
-    (cd ${LLAMACPP_DIR}/ && git checkout CMakeLists.txt)
-
-    if [ -n "$(ls -A ../patches/*.diff)" ]; then
-        for patch in ../patches/*.diff; do
-            for file in $(grep "^+++ " ${patch} | cut -f2 -d' ' | cut -f2- -d/); do
-                (cd ${LLAMACPP_DIR}; git checkout ${file})
-            done
-        done
-    fi
+    git submodule update --force ${LLAMACPP_DIR}
 }

llm/generate/gen_darwin.sh

@@ -25,14 +25,6 @@ case "${GOARCH}" in
 "amd64")
     COMMON_CPU_DEFS="${COMMON_DARWIN_DEFS} -DCMAKE_SYSTEM_PROCESSOR=${ARCH} -DCMAKE_OSX_ARCHITECTURES=${ARCH} -DGGML_METAL=off -DGGML_NATIVE=off"
 
-    # Static build for linking into the Go binary
-    init_vars
-    CMAKE_TARGETS="--target llama --target ggml"
-    CMAKE_DEFS="${COMMON_CPU_DEFS} -DGGML_BLAS=off -DGGML_ACCELERATE=off -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off ${CMAKE_DEFS}"
-    BUILD_DIR="../build/darwin/${ARCH}_static"
-    echo "Building static library"
-    build
-
     if [ -z "$OLLAMA_SKIP_CPU_GENERATE" ]; then
         #
         # CPU first for the default library, set up as lowest common denominator for maximum compatibility (including Rosetta)
@@ -76,14 +68,6 @@ case "${GOARCH}" in
     ;;
 "arm64")
 
-    # Static build for linking into the Go binary
-    init_vars
-    CMAKE_TARGETS="--target llama --target ggml"
-    CMAKE_DEFS="${COMMON_DARWIN_DEFS} -DCMAKE_OSX_DEPLOYMENT_TARGET=11.3 -DCMAKE_SYSTEM_NAME=Darwin -DCMAKE_SYSTEM_PROCESSOR=${ARCH} -DCMAKE_OSX_ARCHITECTURES=${ARCH} ${CMAKE_DEFS}"
-    BUILD_DIR="../build/darwin/${ARCH}_static"
-    echo "Building static library"
-    build
-
     if [ -z "$OLLAMA_SKIP_METAL_GENERATE" ]; then
         init_vars
         CMAKE_DEFS="${COMMON_DARWIN_DEFS} -DCMAKE_SYSTEM_PROCESSOR=${ARCH} -DCMAKE_OSX_ARCHITECTURES=${ARCH} ${CMAKE_DEFS}"

llm/generate/gen_linux.sh

@@ -67,19 +67,6 @@ init_vars
 git_module_setup
 apply_patches
 
-init_vars
-if [ -z "${OLLAMA_SKIP_STATIC_GENERATE}" -o "${OLLAMA_CPU_TARGET}" = "static" ]; then
-    # Builds by default, allows skipping, forces build if OLLAMA_CPU_TARGET="static"
-    # Enables optimized Dockerfile builds using a blanket skip and targeted overrides
-    # Static build for linking into the Go binary
-    init_vars
-    CMAKE_TARGETS="--target llama --target ggml"
-    CMAKE_DEFS="-DBUILD_SHARED_LIBS=off -DGGML_NATIVE=off -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_OPENMP=off ${CMAKE_DEFS}"
-    BUILD_DIR="../build/linux/${ARCH}_static"
-    echo "Building static library"
-    build
-fi
-
 init_vars
 if [ -z "${OLLAMA_SKIP_CPU_GENERATE}" ]; then
     # Users building from source can tune the exact flags we pass to cmake for configuring
@@ -273,7 +260,7 @@ if [ -z "${OLLAMA_SKIP_ROCM_GENERATE}" -a -d "${ROCM_PATH}" ]; then
         ROCM_VARIANT=_v$(ls ${ROCM_PATH}/lib/librocblas.so.*.*.????? | cut -f5 -d. || true)
     fi
     init_vars
-    CMAKE_DEFS="${COMMON_CMAKE_DEFS} ${CMAKE_DEFS} -DGGML_HIPBLAS=on -DGGML_CUDA_NO_PEER_COPY=on -DCMAKE_C_COMPILER=$ROCM_PATH/llvm/bin/clang -DCMAKE_CXX_COMPILER=$ROCM_PATH/llvm/bin/clang++ -DAMDGPU_TARGETS=$(amdGPUs) -DGPU_TARGETS=$(amdGPUs)"
+    CMAKE_DEFS="${COMMON_CMAKE_DEFS} ${CMAKE_DEFS} -DGGML_HIPBLAS=on -DCMAKE_C_COMPILER=$ROCM_PATH/llvm/bin/clang -DCMAKE_CXX_COMPILER=$ROCM_PATH/llvm/bin/clang++ -DAMDGPU_TARGETS=$(amdGPUs) -DGPU_TARGETS=$(amdGPUs)"
     # Users building from source can tune the exact flags we pass to cmake for configuring llama.cpp
     if [ -n "${OLLAMA_CUSTOM_ROCM_DEFS}" ]; then
         echo "OLLAMA_CUSTOM_ROCM_DEFS=\"${OLLAMA_CUSTOM_ROCM_DEFS}\""

llm/generate/gen_windows.ps1

@@ -189,39 +189,6 @@ function cleanup {
 # -DGGML_FMA (FMA3) -- 2013 Intel Haswell & 2012 AMD Piledriver
 
 
-function build_static() {
-    if ((-not "${env:OLLAMA_SKIP_STATIC_GENERATE}") -and ((-not "${env:OLLAMA_CPU_TARGET}") -or ("${env:OLLAMA_CPU_TARGET}" -eq "static"))) {
-        # GCC build for direct linking into the Go binary
-        init_vars
-
-        # cmake will silently fallback to msvc compilers if gcc isn't in the path, so detect and fail fast
-        # as we need this to be compiled by gcc for golang to be able to link with it
-        write-host "Checking for gcc..."
-        get-command  gcc
-        get-command  mingw32-make
-        $oldTargets = $script:cmakeTargets
-        $script:cmakeTargets = @("llama", "ggml")
-        $script:cmakeDefs = @(
-            "-G", "MinGW Makefiles"
-            "-DCMAKE_C_COMPILER=gcc.exe",
-            "-DCMAKE_CXX_COMPILER=g++.exe",
-            "-DBUILD_SHARED_LIBS=off",
-            "-DGGML_NATIVE=off",
-            "-DGGML_AVX=off",
-            "-DGGML_AVX2=off",
-            "-DGGML_AVX512=off",
-            "-DGGML_F16C=off",
-            "-DGGML_FMA=off",
-            "-DGGML_OPENMP=off")
-        $script:buildDir="../build/windows/${script:ARCH}_static"
-        write-host "Building static library"
-        build
-        $script:cmakeTargets = $oldTargets
-    } else {
-        write-host "Skipping CPU generation step as requested"
-    }
-}
-
 function build_cpu_x64 {
     if ((-not "${env:OLLAMA_SKIP_CPU_GENERATE}" ) -and ((-not "${env:OLLAMA_CPU_TARGET}") -or ("${env:OLLAMA_CPU_TARGET}" -eq "cpu"))) {
         init_vars
@@ -391,7 +358,6 @@ function build_rocm() {
             "-DCMAKE_C_COMPILER=clang.exe",
             "-DCMAKE_CXX_COMPILER=clang++.exe",
             "-DGGML_HIPBLAS=on",
-            "-DGGML_CUDA_NO_PEER_COPY=on",
             "-DHIP_PLATFORM=amd",
             "-DGGML_AVX=on",
             "-DGGML_AVX2=off",
@@ -434,7 +400,6 @@ init_vars
 if ($($args.count) -eq 0) {
     git_module_setup
     apply_patches
-    build_static
     if ($script:ARCH -eq "arm64") {
         build_cpu_arm64
     } else { # amd64