mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 10:26:53 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

build: Make target improvements (#7499)

Browse source 
* 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.
This commit is contained in:
Daniel Hiltgen 2024-12-10 09:47:19 -08:00 • committed by GitHub
parent 63269668c0
commit 4879a234c4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
58 changed files with 877 additions and 1168 deletions
Download patch file Download diff file Expand all files Collapse all files

45
llm/server.go
View file

@ -25,7 +25,6 @@ import (
"golang.org/x/sync/semaphore"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/build"
"github.com/ollama/ollama/discover"
"github.com/ollama/ollama/envconfig"
"github.com/ollama/ollama/format"
@ -144,20 +143,13 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
// Loop through potential servers
finalErr := errors.New("no suitable llama servers found")
rDir, err := runners.Refresh(build.EmbedFS)
if err != nil {
return nil, err
}
availableServers := runners.GetAvailableServers()
availableServers := runners.GetAvailableServers(rDir)
if len(availableServers) == 0 {
return nil, finalErr
}
var servers []string
if cpuRunner != "" {
servers = []string{cpuRunner}
} else {
servers = runners.ServersForGpu(gpus[0]) // All GPUs in the list are matching Library and Variant
servers = runners.ServersForGpu(gpus[0].RunnerName()) // All GPUs in the list are matching Library and Variant
}
demandLib := envconfig.LLMLibrary()
if demandLib != "" {
@ -167,7 +159,7 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
} else {
slog.Info("user override", "OLLAMA_LLM_LIBRARY", demandLib, "path", serverPath)
servers = []string{demandLib}
if strings.HasPrefix(demandLib, "cpu") {
if strings.HasPrefix(demandLib, "cpu") || (!(runtime.GOOS == "darwin" && runtime.GOARCH == "arm64") && demandLib == runners.BuiltinName()) {
// Omit the GPU flag to silence the warning
opts.NumGPU = -1
}
@ -279,15 +271,16 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
}
for i := range servers {
dir := availableServers[servers[i]]
if dir == "" {
builtin := servers[i] == runners.BuiltinName()
server := availableServers[servers[i]]
if server == "" {
// Shouldn't happen
finalErr = fmt.Errorf("[%d] server %s not listed in available servers %v", i, servers[i], availableServers)
slog.Error("server list inconsistent", "error", finalErr)
continue
}
if strings.HasPrefix(servers[i], "cpu") {
if strings.HasPrefix(servers[i], "cpu") || (builtin && !(runtime.GOOS == "darwin" && runtime.GOARCH == "arm64")) {
gpus = discover.GetCPUInfo()
}
@ -304,14 +297,16 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
slog.Debug("ResolveTCPAddr failed ", "error", err)
port = rand.Intn(65535-49152) + 49152 // get a random port in the ephemeral range
}
finalParams := append(params, "--port", strconv.Itoa(port))
finalParams := []string{"runner"}
finalParams = append(finalParams, params...)
finalParams = append(finalParams, "--port", strconv.Itoa(port))
pathEnv := "LD_LIBRARY_PATH"
if runtime.GOOS == "windows" {
pathEnv = "PATH"
}
// Start with the server directory for the LD_LIBRARY_PATH/PATH
libraryPaths := []string{dir}
libraryPaths := []string{filepath.Dir(server)}
if libraryPath, ok := os.LookupEnv(pathEnv); ok {
// favor our bundled library dependencies over system libraries
@ -325,22 +320,6 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
libraryPaths = append(gpus[0].DependencyPath, libraryPaths...)
}
server := filepath.Join(dir, "ollama_llama_server")
if runtime.GOOS == "windows" {
server += ".exe"
}
// Detect tmp cleaners wiping out the file
_, err := os.Stat(server)
if errors.Is(err, os.ErrNotExist) {
slog.Warn("llama server disappeared, reinitializing payloads", "path", server, "error", err)
_, err = runners.Refresh(build.EmbedFS)
if err != nil {
slog.Warn("failed to reinitialize payloads", "error", err)
return nil, err
}
}
// TODO - once fully switched to the Go runner, load the model here for tokenize/detokenize cgo access
s := &llmServer{
port: port,
@ -417,7 +396,7 @@ func NewLlamaServer(gpus discover.GpuInfoList, model string, ggml *GGML, adapter
if err = s.cmd.Start(); err != nil {
// Detect permission denied and augment the message about noexec
if errors.Is(err, os.ErrPermission) {
finalErr = fmt.Errorf("unable to start server %w. %s may have noexec set. Set OLLAMA_TMPDIR for server to a writable executable directory", err, dir)
finalErr = fmt.Errorf("unable to start server %w. %s may have noexec set. Set OLLAMA_TMPDIR for server to a writable executable directory", err, server)
continue
}
msg := ""