Merge https://github.com/ollama/ollama

Signed-off-by: baalajimaestro <baalajimaestro@ptr.moe>

.github/workflows/test.yaml

@@ -333,4 +333,4 @@ jobs:
           submodules: recursive
       - name: Verify patches carry all the changes
         run: |
-          cd llama && ./sync.sh && git diff --compact-summary --exit-code .
+          cd llama && make apply-patches sync && git diff --compact-summary --exit-code .

.gitignore

@@ -14,4 +14,5 @@ llm/build
 build/*/*/*
 !build/**/placeholder
 llama/build
-__debug_bin*
+__debug_bin*
+llama/vendor

Dockerfile

@@ -1,6 +1,3 @@
-
-2 KiB
-Docker
 # Build stage
 FROM golang:1.22-bookworm as build
 

README.md

@@ -330,6 +330,7 @@ See the [API documentation](./docs/api.md) for all endpoints.
 - [LLMChat](https://github.com/trendy-design/llmchat) (Privacy focused, 100% local, intuitive all-in-one chat interface)
 - [ARGO](https://github.com/xark-argo/argo) (Locally download and run Ollama and Huggingface models with RAG on Mac/Windows/Linux)
 - [G1](https://github.com/bklieger-groq/g1) (Prototype of using prompting strategies to improve the LLM's reasoning through o1-like reasoning chains.)
+- [Ollama App](https://github.com/JHubi1/ollama-app) (Modern and easy-to-use multi-platform client for Ollama)
 
 ### Terminal
 
@@ -411,11 +412,13 @@ See the [API documentation](./docs/api.md) for all endpoints.
 - [High-level function abstraction in Go](https://gitlab.com/tozd/go/fun)
 - [Ollama PHP](https://github.com/ArdaGnsrn/ollama-php)
 - [Agents-Flex for Java](https://github.com/agents-flex/agents-flex) with [example](https://github.com/agents-flex/agents-flex/tree/main/agents-flex-llm/agents-flex-llm-ollama/src/test/java/com/agentsflex/llm/ollama)
+- [Ollama for Swift](https://github.com/mattt/ollama-swift)
 
 ### Mobile
 
 - [Enchanted](https://github.com/AugustDev/enchanted)
 - [Maid](https://github.com/Mobile-Artificial-Intelligence/maid)
+- [Ollama App](https://github.com/JHubi1/ollama-app) (Modern and easy-to-use multi-platform client for Ollama)
 - [ConfiChat](https://github.com/1runeberg/confichat) (Lightweight, standalone, multi-platform, and privacy focused LLM chat interface with optional encryption)
 
 ### Extensions & Plugins

cmd/cmd.go

@@ -21,7 +21,6 @@ import (
 	"path/filepath"
 	"regexp"
 	"runtime"
-	"slices"
 	"strconv"
 	"strings"
 	"sync/atomic"
@@ -47,28 +46,58 @@ import (
 	"github.com/ollama/ollama/version"
 )
 
+var (
+	errModelNotFound     = errors.New("no Modelfile or safetensors files found")
+	errModelfileNotFound = errors.New("specified Modelfile wasn't found")
+)
+
+func getModelfileName(cmd *cobra.Command) (string, error) {
+	fn, _ := cmd.Flags().GetString("file")
+
+	filename := fn
+	if filename == "" {
+		filename = "Modelfile"
+	}
+
+	absName, err := filepath.Abs(filename)
+	if err != nil {
+		return "", err
+	}
+
+	_, err = os.Stat(absName)
+	if err != nil {
+		return fn, err
+	}
+
+	return absName, nil
+}
+
 func CreateHandler(cmd *cobra.Command, args []string) error {
-	filename, _ := cmd.Flags().GetString("file")
-	filename, err := filepath.Abs(filename)
-	if err != nil {
-		return err
-	}
-
-	client, err := api.ClientFromEnvironment()
-	if err != nil {
-		return err
-	}
-
 	p := progress.NewProgress(os.Stderr)
 	defer p.Stop()
 
-	f, err := os.Open(filename)
-	if err != nil {
-		return err
-	}
-	defer f.Close()
+	var reader io.Reader
 
-	modelfile, err := parser.ParseFile(f)
+	filename, err := getModelfileName(cmd)
+	if os.IsNotExist(err) {
+		if filename == "" {
+			reader = strings.NewReader("FROM .\n")
+		} else {
+			return errModelfileNotFound
+		}
+	} else if err != nil {
+		return err
+	} else {
+		f, err := os.Open(filename)
+		if err != nil {
+			return err
+		}
+
+		reader = f
+		defer f.Close()
+	}
+
+	modelfile, err := parser.ParseFile(reader)
 	if err != nil {
 		return err
 	}
@@ -83,6 +112,11 @@ func CreateHandler(cmd *cobra.Command, args []string) error {
 	p.Add(status, spinner)
 	defer p.Stop()
 
+	client, err := api.ClientFromEnvironment()
+	if err != nil {
+		return err
+	}
+
 	for i := range modelfile.Commands {
 		switch modelfile.Commands[i].Name {
 		case "model", "adapter":
@@ -221,7 +255,7 @@ func tempZipFiles(path string) (string, error) {
 		// covers consolidated.x.pth, consolidated.pth
 		files = append(files, pt...)
 	} else {
-		return "", errors.New("no safetensors or torch files found")
+		return "", errModelNotFound
 	}
 
 	// add configuration files, json files are detected as text/plain
@@ -453,7 +487,7 @@ func RunHandler(cmd *cobra.Command, args []string) error {
 		return err
 	}
 
-	opts.MultiModal = slices.Contains(info.Details.Families, "clip")
+	opts.MultiModal = len(info.ProjectorInfo) != 0
 	opts.ParentModel = info.Details.ParentModel
 
 	if interactive {
@@ -1284,7 +1318,7 @@ func NewCLI() *cobra.Command {
 	log.SetFlags(log.LstdFlags | log.Lshortfile)
 	cobra.EnableCommandSorting = false
 
-	if runtime.GOOS == "windows" {
+	if runtime.GOOS == "windows" && term.IsTerminal(int(os.Stdout.Fd())) {
 		console.ConsoleFromFile(os.Stdin) //nolint:errcheck
 	}
 
@@ -1316,7 +1350,7 @@ func NewCLI() *cobra.Command {
 		RunE:    CreateHandler,
 	}
 
-	createCmd.Flags().StringP("file", "f", "Modelfile", "Name of the Modelfile")
+	createCmd.Flags().StringP("file", "f", "", "Name of the Modelfile (default \"Modelfile\"")
 	createCmd.Flags().StringP("quantize", "q", "", "Quantize model to this level (e.g. q4_0)")
 
 	showCmd := &cobra.Command{

cmd/cmd_test.go

@@ -270,3 +270,102 @@ func TestDeleteHandler(t *testing.T) {
 		t.Fatalf("DeleteHandler failed: expected error about stopping non-existent model, got %v", err)
 	}
 }
+
+func TestGetModelfileName(t *testing.T) {
+	tests := []struct {
+		name          string
+		modelfileName string
+		fileExists    bool
+		expectedName  string
+		expectedErr   error
+	}{
+		{
+			name:          "no modelfile specified, no modelfile exists",
+			modelfileName: "",
+			fileExists:    false,
+			expectedName:  "",
+			expectedErr:   os.ErrNotExist,
+		},
+		{
+			name:          "no modelfile specified, modelfile exists",
+			modelfileName: "",
+			fileExists:    true,
+			expectedName:  "Modelfile",
+			expectedErr:   nil,
+		},
+		{
+			name:          "modelfile specified, no modelfile exists",
+			modelfileName: "crazyfile",
+			fileExists:    false,
+			expectedName:  "crazyfile",
+			expectedErr:   os.ErrNotExist,
+		},
+		{
+			name:          "modelfile specified, modelfile exists",
+			modelfileName: "anotherfile",
+			fileExists:    true,
+			expectedName:  "anotherfile",
+			expectedErr:   nil,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			cmd := &cobra.Command{
+				Use: "fakecmd",
+			}
+			cmd.Flags().String("file", "", "path to modelfile")
+
+			var expectedFilename string
+
+			if tt.fileExists {
+				tempDir, err := os.MkdirTemp("", "modelfiledir")
+				defer os.RemoveAll(tempDir)
+				if err != nil {
+					t.Fatalf("temp modelfile dir creation failed: %v", err)
+				}
+				var fn string
+				if tt.modelfileName != "" {
+					fn = tt.modelfileName
+				} else {
+					fn = "Modelfile"
+				}
+
+				tempFile, err := os.CreateTemp(tempDir, fn)
+				if err != nil {
+					t.Fatalf("temp modelfile creation failed: %v", err)
+				}
+
+				expectedFilename = tempFile.Name()
+				err = cmd.Flags().Set("file", expectedFilename)
+				if err != nil {
+					t.Fatalf("couldn't set file flag: %v", err)
+				}
+			} else {
+				if tt.modelfileName != "" {
+					expectedFilename = tt.modelfileName
+					err := cmd.Flags().Set("file", tt.modelfileName)
+					if err != nil {
+						t.Fatalf("couldn't set file flag: %v", err)
+					}
+				}
+			}
+
+			actualFilename, actualErr := getModelfileName(cmd)
+
+			if actualFilename != expectedFilename {
+				t.Errorf("expected filename: '%s' actual filename: '%s'", expectedFilename, actualFilename)
+			}
+
+			if tt.expectedErr != os.ErrNotExist {
+				if actualErr != tt.expectedErr {
+					t.Errorf("expected err: %v actual err: %v", tt.expectedErr, actualErr)
+				}
+			} else {
+				if !os.IsNotExist(actualErr) {
+					t.Errorf("expected err: %v actual err: %v", tt.expectedErr, actualErr)
+				}
+			}
+		})
+	}
+}

cmd/interactive.go

@@ -494,28 +494,22 @@ func buildModelfile(opts runOptions) string {
 }
 
 func normalizeFilePath(fp string) string {
-	// Define a map of escaped characters and their replacements
-	replacements := map[string]string{
-		"\\ ":  " ",  // Escaped space
-		"\\(":  "(",  // Escaped left parenthesis
-		"\\)":  ")",  // Escaped right parenthesis
-		"\\[":  "[",  // Escaped left square bracket
-		"\\]":  "]",  // Escaped right square bracket
-		"\\{":  "{",  // Escaped left curly brace
-		"\\}":  "}",  // Escaped right curly brace
-		"\\$":  "$",  // Escaped dollar sign
-		"\\&":  "&",  // Escaped ampersand
-		"\\;":  ";",  // Escaped semicolon
-		"\\'":  "'",  // Escaped single quote
-		"\\\\": "\\", // Escaped backslash
-		"\\*":  "*",  // Escaped asterisk
-		"\\?":  "?",  // Escaped question mark
-	}
-
-	for escaped, actual := range replacements {
-		fp = strings.ReplaceAll(fp, escaped, actual)
-	}
-	return fp
+	return strings.NewReplacer(
+		"\\ ", " ", // Escaped space
+		"\\(", "(", // Escaped left parenthesis
+		"\\)", ")", // Escaped right parenthesis
+		"\\[", "[", // Escaped left square bracket
+		"\\]", "]", // Escaped right square bracket
+		"\\{", "{", // Escaped left curly brace
+		"\\}", "}", // Escaped right curly brace
+		"\\$", "$", // Escaped dollar sign
+		"\\&", "&", // Escaped ampersand
+		"\\;", ";", // Escaped semicolon
+		"\\'", "'", // Escaped single quote
+		"\\\\", "\\", // Escaped backslash
+		"\\*", "*", // Escaped asterisk
+		"\\?", "?", // Escaped question mark
+	).Replace(fp)
 }
 
 func extractFileNames(input string) []string {
@@ -535,10 +529,9 @@ func extractFileData(input string) (string, []api.ImageData, error) {
 	for _, fp := range filePaths {
 		nfp := normalizeFilePath(fp)
 		data, err := getImageData(nfp)
-		if err != nil {
-			if os.IsNotExist(err) {
-				continue
-			}
+		if errors.Is(err, os.ErrNotExist) {
+			continue
+		} else if err != nil {
 			fmt.Fprintf(os.Stderr, "Couldn't process image: %q\n", err)
 			return "", imgs, err
 		}
@@ -546,7 +539,7 @@ func extractFileData(input string) (string, []api.ImageData, error) {
 		input = strings.ReplaceAll(input, fp, "")
 		imgs = append(imgs, data)
 	}
-	return input, imgs, nil
+	return strings.TrimSpace(input), imgs, nil
 }
 
 func getImageData(filePath string) ([]byte, error) {

convert/convert_test.go

@@ -29,7 +29,7 @@ type tensorData struct {
 	Shape   []int  `json:"shape"`
 }
 
-func convertFull(t *testing.T, fsys fs.FS) (*os.File, llm.KV, llm.Tensors) {
+func convertFull(t *testing.T, fsys fs.FS) (*os.File, llm.KV, *llm.Tensors) {
 	t.Helper()
 
 	f, err := os.CreateTemp(t.TempDir(), "f16")
@@ -60,7 +60,7 @@ func convertFull(t *testing.T, fsys fs.FS) (*os.File, llm.KV, llm.Tensors) {
 	return r, m.KV(), m.Tensors()
 }
 
-func generateResultsJSON(t *testing.T, f *os.File, kv llm.KV, tensors llm.Tensors) map[string]string {
+func generateResultsJSON(t *testing.T, f *os.File, kv llm.KV, tensors *llm.Tensors) map[string]string {
 	actual := make(map[string]string)
 	for k, v := range kv {
 		if s, ok := v.(json.Marshaler); !ok {

discover/amd_common.go

@@ -1,6 +1,6 @@
 //go:build linux || windows
 
-package gpu
+package discover
 
 import (
 	"errors"
@@ -37,19 +37,6 @@ func GetSupportedGFX(libDir string) ([]string, error) {
 	return ret, nil
 }
 
-func rocmGetVisibleDevicesEnv(gpuInfo []GpuInfo) (string, string) {
-	ids := []string{}
-	for _, info := range gpuInfo {
-		if info.Library != "rocm" {
-			// TODO shouldn't happen if things are wired correctly...
-			slog.Debug("rocmGetVisibleDevicesEnv skipping over non-rocm device", "library", info.Library)
-			continue
-		}
-		ids = append(ids, info.ID)
-	}
-	return "HIP_VISIBLE_DEVICES", strings.Join(ids, ",")
-}
-
 func commonAMDValidateLibDir() (string, error) {
 	// Favor our bundled version
 

discover/amd_hip_windows.go

@@ -1,4 +1,4 @@
-package gpu
+package discover
 
 import (
 	"errors"
@@ -64,7 +64,7 @@ func NewHipLib() (*HipLib, error) {
 	return hl, nil
 }
 
-// The hip library only evaluates the HIP_VISIBLE_DEVICES variable at startup
+// The hip library only evaluates the ROCR_VISIBLE_DEVICES variable at startup
 // so we have to unload/reset the library after we do our initial discovery
 // to make sure our updates to that variable are processed by llama.cpp
 func (hl *HipLib) Release() {

discover/amd_linux.go

@@ -1,4 +1,4 @@
-package gpu
+package discover
 
 import (
 	"bufio"
@@ -64,16 +64,13 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 	// Determine if the user has already pre-selected which GPUs to look at, then ignore the others
 	var visibleDevices []string
 	hipVD := envconfig.HipVisibleDevices()   // zero based index only
-	rocrVD := envconfig.RocrVisibleDevices() // zero based index or UUID, but consumer cards seem to not support UUID
+	rocrVD := envconfig.RocrVisibleDevices() // zero based index or UUID
 	gpuDO := envconfig.GpuDeviceOrdinal()    // zero based index
 	switch {
-	// TODO is this priorty order right?
-	case hipVD != "":
-		visibleDevices = strings.Split(hipVD, ",")
 	case rocrVD != "":
 		visibleDevices = strings.Split(rocrVD, ",")
-		// TODO - since we don't yet support UUIDs, consider detecting and reporting here
-		// all our test systems show GPU-XX indicating UUID is not supported
+	case hipVD != "":
+		visibleDevices = strings.Split(hipVD, ",")
 	case gpuDO != "":
 		visibleDevices = strings.Split(gpuDO, ",")
 	}
@@ -99,7 +96,7 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 		}
 		return a < b
 	})
-	cpuCount := 0
+	gpuCount := 0
 	for _, match := range matches {
 		slog.Debug("evaluating amdgpu node " + match)
 		fp, err := os.Open(match)
@@ -108,11 +105,6 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 			continue
 		}
 		defer fp.Close()
-		nodeID, err := strconv.Atoi(filepath.Base(filepath.Dir(match)))
-		if err != nil {
-			slog.Debug("failed to parse node ID", "error", err)
-			continue
-		}
 
 		scanner := bufio.NewScanner(fp)
 		isCPU := false
@@ -186,20 +178,19 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 		// do reliably report VRAM usage.
 
 		if isCPU {
-			cpuCount++
 			continue
 		}
 
-		// CPUs are always first in the list
-		gpuID := nodeID - cpuCount
-
-		// Shouldn't happen, but just in case...
-		if gpuID < 0 {
-			err := fmt.Errorf("unexpected amdgpu sysfs data resulted in negative GPU ID, please set OLLAMA_DEBUG=1 and report an issue")
-			slog.Error(err.Error())
-			return nil, err
+		// Skip over any GPUs that are masked
+		if major == 0 && minor == 0 && patch == 0 {
+			slog.Debug("skipping gpu with gfx000")
+			continue
 		}
 
+		// Keep track of numeric IDs based on valid GPUs
+		gpuID := gpuCount
+		gpuCount += 1
+
 		// Look up the memory for the current node
 		totalMemory := uint64(0)
 		usedMemory := uint64(0)
@@ -273,6 +264,14 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 			name = fmt.Sprintf("%04x:%04x", vendor, device)
 		}
 
+		// Favor UUIDs if available to reduce possibility of getting the numeric IDs wrong
+		var ID string
+		if uniqueID != 0 {
+			ID = fmt.Sprintf("GPU-%016x", uniqueID)
+		} else {
+			ID = strconv.Itoa(gpuID)
+		}
+
 		gpuInfo := RocmGPUInfo{
 			GpuInfo: GpuInfo{
 				Library: "rocm",
@@ -280,7 +279,7 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 					TotalMemory: totalMemory,
 					FreeMemory:  (totalMemory - usedMemory),
 				},
-				ID:            strconv.Itoa(gpuID),
+				ID:            ID,
 				Name:          name,
 				Compute:       fmt.Sprintf("gfx%d%x%x", major, minor, patch),
 				MinimumMemory: rocmMinimumMemory,
@@ -288,6 +287,7 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 				DriverMinor:   driverMinor,
 			},
 			usedFilepath: usedFile,
+			index:        gpuID,
 		}
 
 		// iGPU detection, remove this check once we can support an iGPU variant of the rocm library
@@ -319,7 +319,7 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 		if len(visibleDevices) > 0 {
 			include := false
 			for _, visible := range visibleDevices {
-				if visible == gpuInfo.ID {
+				if visible == gpuInfo.ID || visible == strconv.Itoa(gpuInfo.index) {
 					include = true
 					break
 				}
@@ -516,3 +516,20 @@ func verifyKFDDriverAccess() error {
 	fd.Close()
 	return nil
 }
+
+func rocmGetVisibleDevicesEnv(gpuInfo []GpuInfo) (string, string) {
+	ids := []string{}
+	for _, info := range gpuInfo {
+		if info.Library != "rocm" {
+			// TODO shouldn't happen if things are wired correctly...
+			slog.Debug("rocmGetVisibleDevicesEnv skipping over non-rocm device", "library", info.Library)
+			continue
+		}
+		ids = append(ids, info.ID)
+	}
+	// There are 3 potential env vars to use to select GPUs.
+	// ROCR_VISIBLE_DEVICES supports UUID or numeric so is our preferred on linux
+	// GPU_DEVICE_ORDINAL supports numeric IDs only
+	// HIP_VISIBLE_DEVICES supports numeric IDs only
+	return "ROCR_VISIBLE_DEVICES", strings.Join(ids, ",")
+}

discover/amd_windows.go

@@ -1,4 +1,4 @@
-package gpu
+package discover
 
 import (
 	"bytes"
@@ -43,7 +43,7 @@ func AMDGetGPUInfo() ([]RocmGPUInfo, error) {
 		slog.Debug("error looking up amd driver version", "error", err)
 	}
 
-	// Note: the HIP library automatically handles subsetting to any HIP_VISIBLE_DEVICES the user specified
+	// Note: the HIP library automatically handles subsetting to any *_VISIBLE_DEVICES the user specified
 	count := hl.HipGetDeviceCount()
 	if count == 0 {
 		err := fmt.Errorf("no compatible amdgpu devices detected")
@@ -201,3 +201,20 @@ func (gpus RocmGPUInfoList) RefreshFreeMemory() error {
 	}
 	return nil
 }
+
+func rocmGetVisibleDevicesEnv(gpuInfo []GpuInfo) (string, string) {
+	ids := []string{}
+	for _, info := range gpuInfo {
+		if info.Library != "rocm" {
+			// TODO shouldn't happen if things are wired correctly...
+			slog.Debug("rocmGetVisibleDevicesEnv skipping over non-rocm device", "library", info.Library)
+			continue
+		}
+		ids = append(ids, info.ID)
+	}
+	// There are 3 potential env vars to use to select GPUs.
+	// ROCR_VISIBLE_DEVICES supports UUID or numeric but does not work on Windows
+	// HIP_VISIBLE_DEVICES supports numeric IDs only
+	// GPU_DEVICE_ORDINAL supports numeric IDs only
+	return "HIP_VISIBLE_DEVICES", strings.Join(ids, ",")
+}

discover/cpu_common.go

@@ -1,4 +1,4 @@
-package gpu
+package discover
 
 import (
 	"os"

discover/cuda_common.go

@@ -1,6 +1,6 @@
 //go:build linux || windows
 
-package gpu
+package discover
 
 import (
 	"log/slog"

discover/gpu.go

@@ -1,6 +1,6 @@
 //go:build linux || windows
 
-package gpu
+package discover
 
 /*
 #cgo linux LDFLAGS: -lrt -lpthread -ldl -lstdc++ -lm
@@ -229,7 +229,10 @@ func GetGPUInfo() GpuInfoList {
 			slog.Warn("error looking up system memory", "error", err)
 		}
 		depPath := LibraryDir()
-
+		details, err := GetCPUDetails()
+		if err != nil {
+			slog.Warn("failed to lookup CPU details", "error", err)
+		}
 		cpus = []CPUInfo{
 			{
 				GpuInfo: GpuInfo{
@@ -239,6 +242,7 @@ func GetGPUInfo() GpuInfoList {
 					ID:             "0",
 					DependencyPath: depPath,
 				},
+				CPUs: details,
 			},
 		}
 

discover/gpu_darwin.go

@@ -1,6 +1,6 @@
 //go:build darwin
 
-package gpu
+package discover
 
 /*
 #cgo CFLAGS: -x objective-c
@@ -10,7 +10,9 @@ package gpu
 import "C"
 
 import (
+	"log/slog"
 	"runtime"
+	"syscall"
 
 	"github.com/ollama/ollama/format"
 )
@@ -69,11 +71,30 @@ func (l GpuInfoList) GetVisibleDevicesEnv() (string, string) {
 
 func GetSystemInfo() SystemInfo {
 	mem, _ := GetCPUMem()
+	query := "hw.perflevel0.physicalcpu"
+	perfCores, err := syscall.SysctlUint32(query)
+	if err != nil {
+		slog.Warn("failed to discover physical CPU details", "query", query, "error", err)
+	}
+	query = "hw.perflevel1.physicalcpu"
+	efficiencyCores, _ := syscall.SysctlUint32(query) // On x86 xeon this wont return data
+
+	// Determine thread count
+	query = "hw.logicalcpu"
+	logicalCores, _ := syscall.SysctlUint32(query)
+
 	return SystemInfo{
 		System: CPUInfo{
 			GpuInfo: GpuInfo{
 				memInfo: mem,
 			},
+			CPUs: []CPU{
+				{
+					CoreCount:           int(perfCores + efficiencyCores),
+					EfficiencyCoreCount: int(efficiencyCores),
+					ThreadCount:         int(logicalCores),
+				},
+			},
 		},
 		GPUs: GetGPUInfo(),
 	}

discover/gpu_linux.go

@@ -0,0 +1,186 @@
+package discover
+
+import (
+	"bufio"
+	"fmt"
+	"os"
+	"reflect"
+	"regexp"
+	"strings"
+
+	"github.com/ollama/ollama/format"
+)
+
+var CudartGlobs = []string{
+	"/usr/local/cuda/lib64/libcudart.so*",
+	"/usr/lib/x86_64-linux-gnu/nvidia/current/libcudart.so*",
+	"/usr/lib/x86_64-linux-gnu/libcudart.so*",
+	"/usr/lib/wsl/lib/libcudart.so*",
+	"/usr/lib/wsl/drivers/*/libcudart.so*",
+	"/opt/cuda/lib64/libcudart.so*",
+	"/usr/local/cuda*/targets/aarch64-linux/lib/libcudart.so*",
+	"/usr/lib/aarch64-linux-gnu/nvidia/current/libcudart.so*",
+	"/usr/lib/aarch64-linux-gnu/libcudart.so*",
+	"/usr/local/cuda/lib*/libcudart.so*",
+	"/usr/lib*/libcudart.so*",
+	"/usr/local/lib*/libcudart.so*",
+}
+
+var NvmlGlobs = []string{}
+
+var NvcudaGlobs = []string{
+	"/usr/local/cuda*/targets/*/lib/libcuda.so*",
+	"/usr/lib/*-linux-gnu/nvidia/current/libcuda.so*",
+	"/usr/lib/*-linux-gnu/libcuda.so*",
+	"/usr/lib/wsl/lib/libcuda.so*",
+	"/usr/lib/wsl/drivers/*/libcuda.so*",
+	"/opt/cuda/lib*/libcuda.so*",
+	"/usr/local/cuda/lib*/libcuda.so*",
+	"/usr/lib*/libcuda.so*",
+	"/usr/local/lib*/libcuda.so*",
+}
+
+var OneapiGlobs = []string{
+	"/usr/lib/x86_64-linux-gnu/libze_intel_gpu.so*",
+	"/usr/lib*/libze_intel_gpu.so*",
+}
+
+var (
+	CudartMgmtName = "libcudart.so*"
+	NvcudaMgmtName = "libcuda.so*"
+	NvmlMgmtName   = "" // not currently wired on linux
+	OneapiMgmtName = "libze_intel_gpu.so*"
+)
+
+func GetCPUMem() (memInfo, error) {
+	var mem memInfo
+	var total, available, free, buffers, cached, freeSwap uint64
+	f, err := os.Open("/proc/meminfo")
+	if err != nil {
+		return mem, err
+	}
+	defer f.Close()
+	s := bufio.NewScanner(f)
+	for s.Scan() {
+		line := s.Text()
+		switch {
+		case strings.HasPrefix(line, "MemTotal:"):
+			_, err = fmt.Sscanf(line, "MemTotal:%d", &total)
+		case strings.HasPrefix(line, "MemAvailable:"):
+			_, err = fmt.Sscanf(line, "MemAvailable:%d", &available)
+		case strings.HasPrefix(line, "MemFree:"):
+			_, err = fmt.Sscanf(line, "MemFree:%d", &free)
+		case strings.HasPrefix(line, "Buffers:"):
+			_, err = fmt.Sscanf(line, "Buffers:%d", &buffers)
+		case strings.HasPrefix(line, "Cached:"):
+			_, err = fmt.Sscanf(line, "Cached:%d", &cached)
+		case strings.HasPrefix(line, "SwapFree:"):
+			_, err = fmt.Sscanf(line, "SwapFree:%d", &freeSwap)
+		default:
+			continue
+		}
+		if err != nil {
+			return mem, err
+		}
+	}
+	mem.TotalMemory = total * format.KibiByte
+	mem.FreeSwap = freeSwap * format.KibiByte
+	if available > 0 {
+		mem.FreeMemory = available * format.KibiByte
+	} else {
+		mem.FreeMemory = (free + buffers + cached) * format.KibiByte
+	}
+	return mem, nil
+}
+
+const CpuInfoFilename = "/proc/cpuinfo"
+
+type linuxCpuInfo struct {
+	ID         string `cpuinfo:"processor"`
+	VendorID   string `cpuinfo:"vendor_id"`
+	ModelName  string `cpuinfo:"model name"`
+	PhysicalID string `cpuinfo:"physical id"`
+	Siblings   string `cpuinfo:"siblings"`
+	CoreID     string `cpuinfo:"core id"`
+}
+
+func GetCPUDetails() ([]CPU, error) {
+	file, err := os.Open(CpuInfoFilename)
+	if err != nil {
+		return nil, err
+	}
+	reColumns := regexp.MustCompile("\t+: ")
+	scanner := bufio.NewScanner(file)
+	cpuInfos := []linuxCpuInfo{}
+	cpu := &linuxCpuInfo{}
+	for scanner.Scan() {
+		line := scanner.Text()
+		if sl := reColumns.Split(line, 2); len(sl) > 1 {
+			t := reflect.TypeOf(cpu).Elem()
+			s := reflect.ValueOf(cpu).Elem()
+			for i := range t.NumField() {
+				field := t.Field(i)
+				tag := field.Tag.Get("cpuinfo")
+				if tag == sl[0] {
+					s.FieldByName(field.Name).SetString(sl[1])
+					break
+				}
+			}
+		} else if strings.TrimSpace(line) == "" && cpu.ID != "" {
+			cpuInfos = append(cpuInfos, *cpu)
+			cpu = &linuxCpuInfo{}
+		}
+	}
+
+	// Process the sockets/cores/threads
+	socketByID := map[string]*CPU{}
+	coreBySocket := map[string]map[string]struct{}{}
+	threadsByCoreBySocket := map[string]map[string]int{}
+	for _, c := range cpuInfos {
+		if _, found := socketByID[c.PhysicalID]; !found {
+			socketByID[c.PhysicalID] = &CPU{
+				ID:        c.PhysicalID,
+				VendorID:  c.VendorID,
+				ModelName: c.ModelName,
+			}
+			coreBySocket[c.PhysicalID] = map[string]struct{}{}
+			threadsByCoreBySocket[c.PhysicalID] = map[string]int{}
+		}
+		if c.CoreID != "" {
+			coreBySocket[c.PhysicalID][c.PhysicalID+":"+c.CoreID] = struct{}{}
+			threadsByCoreBySocket[c.PhysicalID][c.PhysicalID+":"+c.CoreID]++
+		} else {
+			coreBySocket[c.PhysicalID][c.PhysicalID+":"+c.ID] = struct{}{}
+			threadsByCoreBySocket[c.PhysicalID][c.PhysicalID+":"+c.ID]++
+		}
+	}
+
+	// Tally up the values from the tracking maps
+	for id, s := range socketByID {
+		s.CoreCount = len(coreBySocket[id])
+		s.ThreadCount = 0
+		for _, tc := range threadsByCoreBySocket[id] {
+			s.ThreadCount += tc
+		}
+
+		// This only works if HT is enabled, consider a more reliable model, maybe cache size comparisons?
+		efficiencyCoreCount := 0
+		for _, threads := range threadsByCoreBySocket[id] {
+			if threads == 1 {
+				efficiencyCoreCount++
+			}
+		}
+		if efficiencyCoreCount == s.CoreCount {
+			// 1:1 mapping means they're not actually efficiency cores, but regular cores
+			s.EfficiencyCoreCount = 0
+		} else {
+			s.EfficiencyCoreCount = efficiencyCoreCount
+		}
+	}
+
+	result := []CPU{}
+	for _, c := range socketByID {
+		result = append(result, *c)
+	}
+	return result, nil
+}

discover/gpu_oneapi.go

@@ -1,6 +1,6 @@
 //go:build linux || windows
 
-package gpu
+package discover
 
 import (
 	"log/slog"

discover/gpu_test.go

@@ -1,4 +1,4 @@
-package gpu
+package discover
 
 import (
 	"runtime"

discover/gpu_windows.go

@@ -0,0 +1,234 @@
+package discover
+
+import (
+	"fmt"
+	"log/slog"
+	"syscall"
+	"unsafe"
+)
+
+type MEMORYSTATUSEX struct {
+	length               uint32
+	MemoryLoad           uint32
+	TotalPhys            uint64
+	AvailPhys            uint64
+	TotalPageFile        uint64
+	AvailPageFile        uint64
+	TotalVirtual         uint64
+	AvailVirtual         uint64
+	AvailExtendedVirtual uint64
+}
+
+var (
+	k32                              = syscall.NewLazyDLL("kernel32.dll")
+	globalMemoryStatusExProc         = k32.NewProc("GlobalMemoryStatusEx")
+	sizeofMemoryStatusEx             = uint32(unsafe.Sizeof(MEMORYSTATUSEX{}))
+	GetLogicalProcessorInformationEx = k32.NewProc("GetLogicalProcessorInformationEx")
+)
+
+var CudartGlobs = []string{
+	"c:\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v*\\bin\\cudart64_*.dll",
+}
+
+var NvmlGlobs = []string{
+	"c:\\Windows\\System32\\nvml.dll",
+}
+
+var NvcudaGlobs = []string{
+	"c:\\windows\\system*\\nvcuda.dll",
+}
+
+var OneapiGlobs = []string{
+	"c:\\Windows\\System32\\DriverStore\\FileRepository\\*\\ze_intel_gpu64.dll",
+}
+
+var (
+	CudartMgmtName = "cudart64_*.dll"
+	NvcudaMgmtName = "nvcuda.dll"
+	NvmlMgmtName   = "nvml.dll"
+	OneapiMgmtName = "ze_intel_gpu64.dll"
+)
+
+func GetCPUMem() (memInfo, error) {
+	memStatus := MEMORYSTATUSEX{length: sizeofMemoryStatusEx}
+	r1, _, err := globalMemoryStatusExProc.Call(uintptr(unsafe.Pointer(&memStatus)))
+	if r1 == 0 {
+		return memInfo{}, fmt.Errorf("GlobalMemoryStatusEx failed: %w", err)
+	}
+	return memInfo{TotalMemory: memStatus.TotalPhys, FreeMemory: memStatus.AvailPhys, FreeSwap: memStatus.AvailPageFile}, nil
+}
+
+type LOGICAL_PROCESSOR_RELATIONSHIP uint32
+
+const (
+	RelationProcessorCore LOGICAL_PROCESSOR_RELATIONSHIP = iota
+	RelationNumaNode
+	RelationCache
+	RelationProcessorPackage
+	RelationGroup
+	RelationProcessorDie
+	RelationNumaNodeEx
+	RelationProcessorModule
+)
+const RelationAll LOGICAL_PROCESSOR_RELATIONSHIP = 0xffff
+
+type GROUP_AFFINITY struct {
+	Mask     uintptr // KAFFINITY
+	Group    uint16
+	Reserved [3]uint16
+}
+
+type PROCESSOR_RELATIONSHIP struct {
+	Flags           byte
+	EfficiencyClass byte
+	Reserved        [20]byte
+	GroupCount      uint16
+	GroupMask       [1]GROUP_AFFINITY // len GroupCount
+}
+
+// Omitted unused structs: NUMA_NODE_RELATIONSHIP CACHE_RELATIONSHIP GROUP_RELATIONSHIP
+
+type SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX struct {
+	Relationship LOGICAL_PROCESSOR_RELATIONSHIP
+	Size         uint32
+	U            [1]byte // Union len Size
+	// PROCESSOR_RELATIONSHIP
+	// NUMA_NODE_RELATIONSHIP
+	// CACHE_RELATIONSHIP
+	// GROUP_RELATIONSHIP
+}
+
+func (group *GROUP_AFFINITY) IsMember(target *GROUP_AFFINITY) bool {
+	if group == nil || target == nil {
+		return false
+	}
+	return group.Mask&target.Mask != 0
+}
+
+type winPackage struct {
+	groups              []*GROUP_AFFINITY
+	coreCount           int // performance cores = coreCount - efficiencyCoreCount
+	efficiencyCoreCount int
+	threadCount         int
+}
+
+func (pkg *winPackage) IsMember(target *GROUP_AFFINITY) bool {
+	for _, group := range pkg.groups {
+		if group.IsMember(target) {
+			return true
+		}
+	}
+	return false
+}
+
+func getLogicalProcessorInformationEx() ([]byte, error) {
+	buf := make([]byte, 1)
+	bufSize := len(buf)
+	ret, _, err := GetLogicalProcessorInformationEx.Call(
+		uintptr(RelationAll),
+		uintptr(unsafe.Pointer(&buf[0])),
+		uintptr(unsafe.Pointer(&bufSize)),
+	)
+	if ret != 0 {
+		return nil, fmt.Errorf("failed to determine size info ret:%d %w", ret, err)
+	}
+
+	buf = make([]byte, bufSize)
+	ret, _, err = GetLogicalProcessorInformationEx.Call(
+		uintptr(RelationAll),
+		uintptr(unsafe.Pointer(&buf[0])),
+		uintptr(unsafe.Pointer(&bufSize)),
+	)
+	if ret == 0 {
+		return nil, fmt.Errorf("failed to gather processor information ret:%d buflen:%d %w", ret, bufSize, err)
+	}
+	return buf, nil
+}
+
+func processSystemLogicalProcessorInforationList(buf []byte) []*winPackage {
+	var slpi *SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX
+	// Find all the packages first
+	packages := []*winPackage{}
+	for bufOffset := 0; bufOffset < len(buf); bufOffset += int(slpi.Size) {
+		slpi = (*SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX)(unsafe.Pointer(&buf[bufOffset]))
+		if slpi.Relationship != RelationProcessorPackage {
+			continue
+		}
+		pr := (*PROCESSOR_RELATIONSHIP)(unsafe.Pointer(&slpi.U[0]))
+		pkg := &winPackage{}
+		ga0 := unsafe.Pointer(&pr.GroupMask[0])
+		for j := range pr.GroupCount {
+			gm := (*GROUP_AFFINITY)(unsafe.Pointer(uintptr(ga0) + uintptr(j)*unsafe.Sizeof(GROUP_AFFINITY{})))
+			pkg.groups = append(pkg.groups, gm)
+		}
+		packages = append(packages, pkg)
+	}
+
+	slog.Info("packages", "count", len(packages))
+
+	// To identify efficiency cores we have to compare the relative values
+	// Larger values are "less efficient" (aka, more performant)
+	var maxEfficiencyClass byte
+	for bufOffset := 0; bufOffset < len(buf); bufOffset += int(slpi.Size) {
+		slpi = (*SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX)(unsafe.Pointer(&buf[bufOffset]))
+		if slpi.Relationship != RelationProcessorCore {
+			continue
+		}
+		pr := (*PROCESSOR_RELATIONSHIP)(unsafe.Pointer(&slpi.U[0]))
+		if pr.EfficiencyClass > maxEfficiencyClass {
+			maxEfficiencyClass = pr.EfficiencyClass
+		}
+	}
+	if maxEfficiencyClass > 0 {
+		slog.Info("efficiency cores detected", "maxEfficiencyClass", maxEfficiencyClass)
+	}
+
+	// then match up the Cores to the Packages, count up cores, threads and efficiency cores
+	for bufOffset := 0; bufOffset < len(buf); bufOffset += int(slpi.Size) {
+		slpi = (*SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX)(unsafe.Pointer(&buf[bufOffset]))
+		if slpi.Relationship != RelationProcessorCore {
+			continue
+		}
+		pr := (*PROCESSOR_RELATIONSHIP)(unsafe.Pointer(&slpi.U[0]))
+		ga0 := unsafe.Pointer(&pr.GroupMask[0])
+		for j := range pr.GroupCount {
+			gm := (*GROUP_AFFINITY)(unsafe.Pointer(uintptr(ga0) + uintptr(j)*unsafe.Sizeof(GROUP_AFFINITY{})))
+			for _, pkg := range packages {
+				if pkg.IsMember(gm) {
+					pkg.coreCount++
+					if pr.Flags == 0 {
+						pkg.threadCount++
+					} else {
+						pkg.threadCount += 2
+					}
+					if pr.EfficiencyClass < maxEfficiencyClass {
+						pkg.efficiencyCoreCount++
+					}
+				}
+			}
+		}
+	}
+
+	// Sumarize the results
+	for i, pkg := range packages {
+		slog.Info("", "package", i, "cores", pkg.coreCount, "efficiency", pkg.efficiencyCoreCount, "threads", pkg.threadCount)
+	}
+
+	return packages
+}
+
+func GetCPUDetails() ([]CPU, error) {
+	buf, err := getLogicalProcessorInformationEx()
+	if err != nil {
+		return nil, err
+	}
+	packages := processSystemLogicalProcessorInforationList(buf)
+	cpus := make([]CPU, len(packages))
+
+	for i, pkg := range packages {
+		cpus[i].CoreCount = pkg.coreCount
+		cpus[i].EfficiencyCoreCount = pkg.efficiencyCoreCount
+		cpus[i].ThreadCount = pkg.threadCount
+	}
+	return cpus, nil
+}

discover/types.go

@@ -1,4 +1,4 @@
-package gpu
+package discover
 
 import (
 	"fmt"
@@ -10,11 +10,11 @@ import (
 type memInfo struct {
 	TotalMemory uint64 `json:"total_memory,omitempty"`
 	FreeMemory  uint64 `json:"free_memory,omitempty"`
-	FreeSwap    uint64 `json:"free_swap,omitempty"`
+	FreeSwap    uint64 `json:"free_swap,omitempty"` // TODO split this out for system only
 }
 
 // Beginning of an `ollama info` command
-type GpuInfo struct {
+type GpuInfo struct { // TODO better name maybe "InferenceProcessor"?
 	memInfo
 	Library string `json:"library,omitempty"`