build: Make target improvements (#7499)

* llama: wire up builtin runner

This adds a new entrypoint into the ollama CLI to run the cgo built runner.
On Mac arm64, this will have GPU support, but on all other platforms it will
be the lowest common denominator CPU build.  After we fully transition
to the new Go runners more tech-debt can be removed and we can stop building
the "default" runner via make and rely on the builtin always.

* build: Make target improvements

Add a few new targets and help for building locally.
This also adjusts the runner lookup to favor local builds, then
runners relative to the executable, and finally payloads.

* Support customized CPU flags for runners

This implements a simplified custom CPU flags pattern for the runners.
When built without overrides, the runner name contains the vector flag
we check for (AVX) to ensure we don't try to run on unsupported systems
and crash.  If the user builds a customized set, we omit the naming
scheme and don't check for compatibility.  This avoids checking
requirements at runtime, so that logic has been removed as well.  This
can be used to build GPU runners with no vector flags, or CPU/GPU
runners with additional flags (e.g. AVX512) enabled.

* Use relative paths

If the user checks out the repo in a path that contains spaces, make gets
really confused so use relative paths for everything in-repo to avoid breakage.

* Remove payloads from main binary

* install: clean up prior libraries

This removes support for v0.3.6 and older versions (before the tar bundle)
and ensures we clean up prior libraries before extracting the bundle(s).
Without this change, runners and dependent libraries could leak when we
update and lead to subtle runtime errors.

scripts/build_darwin.sh

@@ -14,16 +14,14 @@ export CGO_CFLAGS=-mmacosx-version-min=11.3
 export CGO_CXXFLAGS=-mmacosx-version-min=11.3
 export CGO_LDFLAGS=-mmacosx-version-min=11.3
 
-for TARGETARCH in arm64 amd64; do
-    echo "Building Go runner darwin $TARGETARCH"
-    rm -rf llama/build
-    GOOS=darwin ARCH=$TARGETARCH GOARCH=$TARGETARCH make -C llama -j 8
-    CGO_ENABLED=1 GOOS=darwin GOARCH=$TARGETARCH go build -trimpath -o dist/ollama-darwin-$TARGETARCH
-    CGO_ENABLED=1 GOOS=darwin GOARCH=$TARGETARCH go build -trimpath -cover -o dist/ollama-darwin-$TARGETARCH-cov
-done
+rm -rf llama/build dist/darwin-*
+echo "Building darwin arm64"
+GOOS=darwin ARCH=arm64 GOARCH=arm64 make -j 8 dist
+echo "Building darwin amd64 with AVX enabled"
+GOOS=darwin ARCH=amd64 GOARCH=amd64 CUSTOM_CPU_FLAGS="avx" make -j 8 dist
 
-lipo -create -output dist/ollama dist/ollama-darwin-arm64 dist/ollama-darwin-amd64
-rm -f dist/ollama-darwin-arm64 dist/ollama-darwin-amd64
+
+lipo -create -output dist/ollama dist/darwin-arm64/bin/ollama dist/darwin-amd64/bin/ollama
 if [ -n "$APPLE_IDENTITY" ]; then
     codesign --deep --force --options=runtime --sign "$APPLE_IDENTITY" --timestamp dist/ollama
 else

scripts/build_windows.ps1

@@ -82,7 +82,7 @@ function buildOllama() {
     if ($null -eq ${env:OLLAMA_SKIP_GENERATE}) {
         write-host "Building ollama runners"
         Remove-Item -ea 0 -recurse -force -path "${script:SRC_DIR}\dist\windows-${script:ARCH}"
-        & make -C llama -j 12
+        & make -j 12 dist
         if ($LASTEXITCODE -ne 0) { exit($LASTEXITCODE)}
     } else {
         write-host "Skipping generate step with OLLAMA_SKIP_GENERATE set"

scripts/install.sh

@@ -71,29 +71,20 @@ for BINDIR in /usr/local/bin /usr/bin /bin; do
 done
 OLLAMA_INSTALL_DIR=$(dirname ${BINDIR})
 
+if [ -d "$OLLAMA_INSTALL_DIR/lib/ollama" ] ; then
+    status "Cleaning up old version at $OLLAMA_INSTALL_DIR/lib/ollama"
+    $SUDO rm -rf "$OLLAMA_INSTALL_DIR/lib/ollama"
+fi
 status "Installing ollama to $OLLAMA_INSTALL_DIR"
 $SUDO install -o0 -g0 -m755 -d $BINDIR
 $SUDO install -o0 -g0 -m755 -d "$OLLAMA_INSTALL_DIR"
-if curl -I --silent --fail --location "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" >/dev/null ; then
-    status "Downloading Linux ${ARCH} bundle"
-    curl --fail --show-error --location --progress-bar \
-        "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" | \
-        $SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
-    BUNDLE=1
-    if [ "$OLLAMA_INSTALL_DIR/bin/ollama" != "$BINDIR/ollama" ] ; then
-        status "Making ollama accessible in the PATH in $BINDIR"
-        $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
-    fi
-else
-    status "Downloading Linux ${ARCH} CLI"
-    curl --fail --show-error --location --progress-bar -o "$TEMP_DIR/ollama"\
-    "https://ollama.com/download/ollama-linux-${ARCH}${VER_PARAM}"
-    $SUDO install -o0 -g0 -m755 $TEMP_DIR/ollama $OLLAMA_INSTALL_DIR/ollama
-    BUNDLE=0
-    if [ "$OLLAMA_INSTALL_DIR/ollama" != "$BINDIR/ollama" ] ; then
-        status "Making ollama accessible in the PATH in $BINDIR"
-        $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
-    fi
+status "Downloading Linux ${ARCH} bundle"
+curl --fail --show-error --location --progress-bar \
+    "https://ollama.com/download/ollama-linux-${ARCH}.tgz${VER_PARAM}" | \
+    $SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
+if [ "$OLLAMA_INSTALL_DIR/bin/ollama" != "$BINDIR/ollama" ] ; then
+    status "Making ollama accessible in the PATH in $BINDIR"
+    $SUDO ln -sf "$OLLAMA_INSTALL_DIR/ollama" "$BINDIR/ollama"
 fi
 
 # Check for NVIDIA JetPack systems with additional downloads
@@ -230,31 +221,11 @@ if ! check_gpu lspci nvidia && ! check_gpu lshw nvidia && ! check_gpu lspci amdg
 fi
 
 if check_gpu lspci amdgpu || check_gpu lshw amdgpu; then
-    if [ $BUNDLE -ne 0 ]; then
-        status "Downloading Linux ROCm ${ARCH} bundle"
-        curl --fail --show-error --location --progress-bar \
-            "https://ollama.com/download/ollama-linux-${ARCH}-rocm.tgz${VER_PARAM}" | \
-            $SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
+    status "Downloading Linux ROCm ${ARCH} bundle"
+    curl --fail --show-error --location --progress-bar \
+        "https://ollama.com/download/ollama-linux-${ARCH}-rocm.tgz${VER_PARAM}" | \
+        $SUDO tar -xzf - -C "$OLLAMA_INSTALL_DIR"
 
-        install_success
-        status "AMD GPU ready."
-        exit 0
-    fi
-    # Look for pre-existing ROCm v6 before downloading the dependencies
-    for search in "${HIP_PATH:-''}" "${ROCM_PATH:-''}" "/opt/rocm" "/usr/lib64"; do
-        if [ -n "${search}" ] && [ -e "${search}/libhipblas.so.2" -o -e "${search}/lib/libhipblas.so.2" ]; then
-            status "Compatible AMD GPU ROCm library detected at ${search}"
-            install_success
-            exit 0
-        fi
-    done
-
-    status "Downloading AMD GPU dependencies..."
-    $SUDO rm -rf /usr/share/ollama/lib
-    $SUDO chmod o+x /usr/share/ollama
-    $SUDO install -o ollama -g ollama -m 755 -d /usr/share/ollama/lib/rocm
-    curl --fail --show-error --location --progress-bar "https://ollama.com/download/ollama-linux-amd64-rocm.tgz${VER_PARAM}" \
-        | $SUDO tar zx --owner ollama --group ollama -C /usr/share/ollama/lib/rocm .
     install_success
     status "AMD GPU ready."
     exit 0