next build (#8539)

* add build to .dockerignore

* test: only build one arch

* add build to .gitignore

* fix ccache path

* filter amdgpu targets

* only filter if autodetecting

* Don't clobber gpu list for default runner

This ensures the GPU specific environment variables are set properly

* explicitly set CXX compiler for HIP

* Update build_windows.ps1

This isn't complete, but is close.  Dependencies are missing, and it only builds the "default" preset.

* build: add ollama subdir

* add .git to .dockerignore

* docs: update development.md

* update build_darwin.sh

* remove unused scripts

* llm: add cwd and build/lib/ollama to library paths

* default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS

* add additional cmake output vars for msvc

* interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12

* remove unncessary filepath.Dir, cleanup

* add hardware-specific directory to path

* use absolute server path

* build: linux arm

* cmake install targets

* remove unused files

* ml: visit each library path once

* build: skip cpu variants on arm

* build: install cpu targets

* build: fix workflow

* shorter names

* fix rocblas install

* docs: clean up development.md

* consistent build dir removal in development.md

* silence -Wimplicit-function-declaration build warnings in ggml-cpu

* update readme

* update development readme

* llm: update library lookup logic now that there is one runner (#8587)

* tweak development.md

* update docs

* add windows cuda/rocm tests

---------

Co-authored-by: jmorganca <jmorganca@gmail.com>
Co-authored-by: Daniel Hiltgen <daniel@ollama.com>

discover/amd_common.go

@@ -9,8 +9,6 @@ import (
 	"path/filepath"
 	"runtime"
 	"strings"
-
-	"github.com/ollama/ollama/envconfig"
 )
 
 // Determine if the given ROCm lib directory is usable by checking for existence of some glob patterns
@@ -41,13 +39,10 @@ func commonAMDValidateLibDir() (string, error) {
 	// Favor our bundled version
 
 	// Installer payload location if we're running the installed binary
-	exe, err := os.Executable()
-	if err == nil {
-		rocmTargetDir := filepath.Join(filepath.Dir(exe), envconfig.LibRelativeToExe(), "lib", "ollama")
-		if rocmLibUsable(rocmTargetDir) {
-			slog.Debug("detected ROCM next to ollama executable " + rocmTargetDir)
-			return rocmTargetDir, nil
-		}
+	rocmTargetDir := filepath.Join(LibOllamaPath, "rocm")
+	if rocmLibUsable(rocmTargetDir) {
+		slog.Debug("detected ROCM next to ollama executable " + rocmTargetDir)
+		return rocmTargetDir, nil
 	}
 
 	// Prefer explicit HIP env var

discover/amd_linux.go

@@ -77,8 +77,7 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 
 	gfxOverride := envconfig.HsaOverrideGfxVersion()
 	var supported []string
-	depPaths := LibraryDirs()
-	libDir := ""
+	var libDir string
 
 	// The amdgpu driver always exposes the host CPU(s) first, but we have to skip them and subtract
 	// from the other IDs to get alignment with the HIP libraries expectations (zero is the first GPU, not the CPU)
@@ -353,9 +352,8 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 				})
 				return nil, err
 			}
-			depPaths = append(depPaths, libDir)
 		}
-		gpuInfo.DependencyPath = depPaths
+		gpuInfo.DependencyPath = []string{libDir}
 
 		if gfxOverride == "" {
 			// Only load supported list once

discover/amd_windows.go

@@ -5,7 +5,6 @@ import (
 	"errors"
 	"fmt"
 	"log/slog"
-	"os"
 	"path/filepath"
 	"slices"
 	"strconv"
@@ -50,14 +49,13 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 		slog.Info(err.Error())
 		return nil, err
 	}
-	depPaths := LibraryDirs()
+
 	libDir, err := AMDValidateLibDir()
 	if err != nil {
 		err = fmt.Errorf("unable to verify rocm library: %w", err)
 		slog.Warn(err.Error())
 		return nil, err
 	}
-	depPaths = append(depPaths, libDir)
 
 	var supported []string
 	gfxOverride := envconfig.HsaOverrideGfxVersion()
@@ -113,7 +111,7 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 				UnreliableFreeMemory: true,
 
 				ID:             strconv.Itoa(i), // TODO this is probably wrong if we specify visible devices
-				DependencyPath: depPaths,
+				DependencyPath: []string{libDir},
 				MinimumMemory:  rocmMinimumMemory,
 				Name:           name,
 				Compute:        gfx,
@@ -164,9 +162,7 @@ func AMDValidateLibDir() (string, error) {
 	}
 
 	// Installer payload (if we're running from some other location)
-	localAppData := os.Getenv("LOCALAPPDATA")
-	appDir := filepath.Join(localAppData, "Programs", "Ollama")
-	rocmTargetDir := filepath.Join(appDir, envconfig.LibRelativeToExe(), "lib", "ollama")
+	rocmTargetDir := filepath.Join(LibOllamaPath, "rocm")
 	if rocmLibUsable(rocmTargetDir) {
 		slog.Debug("detected ollama installed ROCm at " + rocmTargetDir)
 		return rocmTargetDir, nil

discover/gpu.go

@@ -23,7 +23,6 @@ import (
 
 	"github.com/ollama/ollama/envconfig"
 	"github.com/ollama/ollama/format"
-	"github.com/ollama/ollama/runners"
 )
 
 type cudaHandles struct {
@@ -101,15 +100,7 @@ func initCudaHandles() *cudaHandles {
 
 	// Aligned with driver, we can't carry as payloads
 	nvcudaMgmtPatterns := NvcudaGlobs
-
-	if runtime.GOOS == "windows" {
-		localAppData := os.Getenv("LOCALAPPDATA")
-		cudartMgmtPatterns = []string{filepath.Join(localAppData, "Programs", "Ollama", CudartMgmtName)}
-	}
-	libDirs := LibraryDirs()
-	for _, d := range libDirs {
-		cudartMgmtPatterns = append(cudartMgmtPatterns, filepath.Join(d, CudartMgmtName))
-	}
+	cudartMgmtPatterns = append(cudartMgmtPatterns, filepath.Join(LibOllamaPath, "cuda_v*", CudartMgmtName))
 	cudartMgmtPatterns = append(cudartMgmtPatterns, CudartGlobs...)
 
 	if len(NvmlGlobs) > 0 {
@@ -240,7 +231,7 @@ func GetGPUInfo() GpuInfoList {
 		if err != nil {
 			slog.Warn("error looking up system memory", "error", err)
 		}
-		depPaths := LibraryDirs()
+
 		details, err := GetCPUDetails()
 		if err != nil {
 			slog.Warn("failed to lookup CPU details", "error", err)
@@ -248,11 +239,9 @@ func GetGPUInfo() GpuInfoList {
 		cpus = []CPUInfo{
 			{
 				GpuInfo: GpuInfo{
-					memInfo:        mem,
-					Library:        "cpu",
-					Variant:        runners.GetCPUCapability().String(),
-					ID:             "0",
-					DependencyPath: depPaths,
+					memInfo: mem,
+					Library: "cpu",
+					ID:      "0",
 				},
 				CPUs: details,
 			},
@@ -294,17 +283,13 @@ func GetGPUInfo() GpuInfoList {
 				gpuInfo.DriverMajor = driverMajor
 				gpuInfo.DriverMinor = driverMinor
 				variant := cudaVariant(gpuInfo)
-				if depPaths != nil {
-					gpuInfo.DependencyPath = depPaths
-					// Check for variant specific directory
-					if variant != "" {
-						for _, d := range depPaths {
-							if _, err := os.Stat(filepath.Join(d, "cuda_"+variant)); err == nil {
-								// Put the variant directory first in the search path to avoid runtime linking to the wrong library
-								gpuInfo.DependencyPath = append([]string{filepath.Join(d, "cuda_"+variant)}, gpuInfo.DependencyPath...)
-								break
-							}
-						}
+
+				// Start with our bundled libraries
+				if variant != "" {
+					variantPath := filepath.Join(LibOllamaPath, "cuda_"+variant)
+					if _, err := os.Stat(variantPath); err == nil {
+						// Put the variant directory first in the search path to avoid runtime linking to the wrong library
+						gpuInfo.DependencyPath = append([]string{variantPath}, gpuInfo.DependencyPath...)
 					}
 				}
 				gpuInfo.Name = C.GoString(&memInfo.gpu_name[0])
@@ -376,7 +361,7 @@ func GetGPUInfo() GpuInfoList {
 						gpuInfo.FreeMemory = uint64(memInfo.free)
 						gpuInfo.ID = C.GoString(&memInfo.gpu_id[0])
 						gpuInfo.Name = C.GoString(&memInfo.gpu_name[0])
-						gpuInfo.DependencyPath = depPaths
+						gpuInfo.DependencyPath = []string{LibOllamaPath}
 						oneapiGPUs = append(oneapiGPUs, gpuInfo)
 					}
 				}
@@ -512,33 +497,30 @@ func GetGPUInfo() GpuInfoList {
 
 func FindGPULibs(baseLibName string, defaultPatterns []string) []string {
 	// Multiple GPU libraries may exist, and some may not work, so keep trying until we exhaust them
-	var ldPaths []string
 	gpuLibPaths := []string{}
 	slog.Debug("Searching for GPU library", "name", baseLibName)
 
-	// Start with our bundled libraries
-	patterns := []string{}
-	for _, d := range LibraryDirs() {
-		patterns = append(patterns, filepath.Join(d, baseLibName))
-	}
+	// search our bundled libraries first
+	patterns := []string{filepath.Join(LibOllamaPath, baseLibName)}
 
+	var ldPaths []string
 	switch runtime.GOOS {
 	case "windows":
-		ldPaths = strings.Split(os.Getenv("PATH"), ";")
+		ldPaths = strings.Split(os.Getenv("PATH"), string(os.PathListSeparator))
 	case "linux":
-		ldPaths = strings.Split(os.Getenv("LD_LIBRARY_PATH"), ":")
-	default:
-		return gpuLibPaths
+		ldPaths = strings.Split(os.Getenv("LD_LIBRARY_PATH"), string(os.PathListSeparator))
 	}
 
-	// Then with whatever we find in the PATH/LD_LIBRARY_PATH
-	for _, ldPath := range ldPaths {
-		d, err := filepath.Abs(ldPath)
+	// then search the system's LD_LIBRARY_PATH
+	for _, p := range ldPaths {
+		p, err := filepath.Abs(p)
 		if err != nil {
 			continue
 		}
-		patterns = append(patterns, filepath.Join(d, baseLibName))
+		patterns = append(patterns, filepath.Join(p, baseLibName))
 	}
+
+	// finally, search the default patterns provided by the caller
 	patterns = append(patterns, defaultPatterns...)
 	slog.Debug("gpu library search", "globs", patterns)
 	for _, pattern := range patterns {
@@ -715,28 +697,6 @@ func (l GpuInfoList) GetVisibleDevicesEnv() (string, string) {
 	}
 }
 
-func LibraryDirs() []string {
-	// dependencies can exist wherever we found the runners (e.g. build tree for developers) and relative to the executable
-	// This can be simplified once we no longer carry runners as payloads
-	paths := []string{}
-	appExe, err := os.Executable()
-	if err != nil {
-		slog.Warn("failed to lookup executable path", "error", err)
-	} else {
-		appRelative := filepath.Join(filepath.Dir(appExe), envconfig.LibRelativeToExe(), "lib", "ollama")
-		if _, err := os.Stat(appRelative); err == nil {
-			paths = append(paths, appRelative)
-		}
-	}
-	rDir := runners.Locate()
-	if err != nil {
-		slog.Warn("unable to locate gpu dependency libraries", "error", err)
-	} else {
-		paths = append(paths, filepath.Dir(rDir))
-	}
-	return paths
-}
-
 func GetSystemInfo() SystemInfo {
 	gpus := GetGPUInfo()
 	gpuMutex.Lock()

discover/gpu_darwin.go

@@ -15,7 +15,6 @@ import (
 	"syscall"
 
 	"github.com/ollama/ollama/format"
-	"github.com/ollama/ollama/runners"
 )
 
 const (
@@ -28,7 +27,6 @@ func GetGPUInfo() GpuInfoList {
 		return []GpuInfo{
 			{
 				Library: "cpu",
-				Variant: runners.GetCPUCapability().String(),
 				memInfo: mem,
 			},
 		}
@@ -51,7 +49,6 @@ func GetCPUInfo() GpuInfoList {
 	return []GpuInfo{
 		{
 			Library: "cpu",
-			Variant: runners.GetCPUCapability().String(),
 			memInfo: mem,
 		},
 	}

discover/path.go

@@ -0,0 +1,53 @@
+package discover
+
+import (
+	"os"
+	"path/filepath"
+	"runtime"
+)
+
+// LibPath is a path to lookup dynamic libraries
+// in development it's usually 'build/lib/ollama'
+// in distribution builds it's 'lib/ollama' on Windows
+// '../lib/ollama' on Linux and the executable's directory on macOS
+// note: distribution builds, additional GPU-specific libraries are
+// found in subdirectories of the returned path, such as
+// 'cuda_v11', 'cuda_v12', 'rocm', etc.
+var LibOllamaPath string = func() string {
+	exe, err := os.Executable()
+	if err != nil {
+		return ""
+	}
+
+	exe, err = filepath.EvalSymlinks(exe)
+	if err != nil {
+		return ""
+	}
+
+	libPath := filepath.Dir(exe)
+	switch runtime.GOOS {
+	case "windows":
+		libPath = filepath.Join(filepath.Dir(exe), "lib", "ollama")
+	case "linux":
+		libPath = filepath.Join(filepath.Dir(exe), "..", "lib", "ollama")
+	}
+
+	cwd, err := os.Getwd()
+	if err != nil {
+		return ""
+	}
+
+	// build paths for development
+	buildPaths := []string{
+		filepath.Join(filepath.Dir(exe), "build", "lib", "ollama"),
+		filepath.Join(cwd, "build", "lib", "ollama"),
+	}
+
+	for _, p := range buildPaths {
+		if _, err := os.Stat(p); err == nil {
+			return p
+		}
+	}
+
+	return libPath
+}()

discover/types.go

@@ -5,7 +5,6 @@ import (
 	"log/slog"
 
 	"github.com/ollama/ollama/format"
-	"github.com/ollama/ollama/runners"
 )
 
 type memInfo struct {
@@ -107,7 +106,7 @@ func (l GpuInfoList) ByLibrary() []GpuInfoList {
 	for _, info := range l {
 		found := false
 		requested := info.Library
-		if info.Variant != runners.CPUCapabilityNone.String() {
+		if info.Variant != "" {
 			requested += "_" + info.Variant
 		}
 		for i, lib := range libs {