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.

llama/runner/cache.go

@@ -1,4 +1,4 @@
-package main
+package runner
 
 import (
 	"errors"

llama/runner/cache_test.go

@@ -1,4 +1,4 @@
-package main
+package runner
 
 import (
 	"testing"

llama/runner/image.go

@@ -1,4 +1,4 @@
-package main
+package runner
 
 import (
 	"errors"

llama/runner/image_test.go

@@ -1,4 +1,4 @@
-package main
+package runner
 
 import (
 	"reflect"

llama/runner/requirements.go

@@ -1,19 +0,0 @@
-package main
-
-import (
-	"encoding/json"
-	"os"
-
-	"github.com/ollama/ollama/llama"
-	"github.com/ollama/ollama/version"
-)
-
-func printRequirements(fp *os.File) {
-	attrs := map[string]string{
-		"system_info":  llama.PrintSystemInfo(),
-		"version":      version.Version,
-		"cpu_features": llama.CpuFeatures,
-	}
-	enc := json.NewEncoder(fp)
-	_ = enc.Encode(attrs)
-}

llama/runner/runner.go

@@ -1,4 +1,4 @@
-package main
+package runner
 
 import (
 	"context"
@@ -895,32 +895,37 @@ func (s *Server) loadModel(
 	s.ready.Done()
 }
 
-func main() {
-	mpath := flag.String("model", "", "Path to model binary file")
-	ppath := flag.String("mmproj", "", "Path to projector binary file")
-	parallel := flag.Int("parallel", 1, "Number of sequences to handle simultaneously")
-	batchSize := flag.Int("batch-size", 512, "Batch size")
-	nGpuLayers := flag.Int("n-gpu-layers", 0, "Number of layers to offload to GPU")
-	mainGpu := flag.Int("main-gpu", 0, "Main GPU")
-	flashAttention := flag.Bool("flash-attn", false, "Enable flash attention")
-	kvSize := flag.Int("ctx-size", 2048, "Context (or KV cache) size")
-	kvCacheType := flag.String("kv-cache-type", "", "quantization type for KV cache (default: f16)")
-	port := flag.Int("port", 8080, "Port to expose the server on")
-	threads := flag.Int("threads", runtime.NumCPU(), "Number of threads to use during generation")
-	verbose := flag.Bool("verbose", false, "verbose output (default: disabled)")
-	noMmap := flag.Bool("no-mmap", false, "do not memory-map model (slower load but may reduce pageouts if not using mlock)")
-	mlock := flag.Bool("mlock", false, "force system to keep model in RAM rather than swapping or compressing")
-	tensorSplit := flag.String("tensor-split", "", "fraction of the model to offload to each GPU, comma-separated list of proportions")
-	multiUserCache := flag.Bool("multiuser-cache", false, "optimize input cache algorithm for multiple users")
-	requirements := flag.Bool("requirements", false, "print json requirement information")
+func Execute(args []string) error {
+	if args[0] == "runner" {
+		args = args[1:]
+	}
+	fs := flag.NewFlagSet("runner", flag.ExitOnError)
+	mpath := fs.String("model", "", "Path to model binary file")
+	ppath := fs.String("mmproj", "", "Path to projector binary file")
+	parallel := fs.Int("parallel", 1, "Number of sequences to handle simultaneously")
+	batchSize := fs.Int("batch-size", 512, "Batch size")
+	nGpuLayers := fs.Int("n-gpu-layers", 0, "Number of layers to offload to GPU")
+	mainGpu := fs.Int("main-gpu", 0, "Main GPU")
+	flashAttention := fs.Bool("flash-attn", false, "Enable flash attention")
+	kvSize := fs.Int("ctx-size", 2048, "Context (or KV cache) size")
+	kvCacheType := fs.String("kv-cache-type", "", "quantization type for KV cache (default: f16)")
+	port := fs.Int("port", 8080, "Port to expose the server on")
+	threads := fs.Int("threads", runtime.NumCPU(), "Number of threads to use during generation")
+	verbose := fs.Bool("verbose", false, "verbose output (default: disabled)")
+	noMmap := fs.Bool("no-mmap", false, "do not memory-map model (slower load but may reduce pageouts if not using mlock)")
+	mlock := fs.Bool("mlock", false, "force system to keep model in RAM rather than swapping or compressing")
+	tensorSplit := fs.String("tensor-split", "", "fraction of the model to offload to each GPU, comma-separated list of proportions")
+	multiUserCache := fs.Bool("multiuser-cache", false, "optimize input cache algorithm for multiple users")
 
 	var lpaths multiLPath
-	flag.Var(&lpaths, "lora", "Path to lora layer file (can be specified multiple times)")
+	fs.Var(&lpaths, "lora", "Path to lora layer file (can be specified multiple times)")
 
-	flag.Parse()
-	if *requirements {
-		printRequirements(os.Stdout)
-		return
+	fs.Usage = func() {
+		fmt.Fprintf(fs.Output(), "Runner usage\n")
+		fs.PrintDefaults()
+	}
+	if err := fs.Parse(args); err != nil {
+		return err
 	}
 	level := slog.LevelInfo
 	if *verbose {
@@ -983,7 +988,8 @@ func main() {
 	listener, err := net.Listen("tcp", addr)
 	if err != nil {
 		fmt.Println("Listen error:", err)
-		return
+		cancel()
+		return err
 	}
 	defer listener.Close()
 
@@ -999,7 +1005,9 @@ func main() {
 	log.Println("Server listening on", addr)
 	if err := httpServer.Serve(listener); err != nil {
 		log.Fatal("server error:", err)
+		return err
 	}
 
 	cancel()
+	return nil
 }

llama/runner/stop.go

@@ -1,4 +1,4 @@
-package main
+package runner
 
 import (
 	"strings"

llama/runner/stop_test.go

@@ -1,4 +1,4 @@
-package main
+package runner
 
 import (
 	"reflect"