mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-30 18:09:05 -04:00
feat: materialize Hugging Face model artifacts (#10825)
* feat(config): add model artifact source contract Assisted-by: Codex:GPT-5 [Codex] * feat(downloader): add authenticated raw-byte progress Assisted-by: Codex:GPT-5 [Codex] * feat(huggingface): resolve immutable snapshot manifests Assisted-by: Codex:GPT-5 [Codex] * feat(models): add artifact storage primitives Assisted-by: Codex:GPT-5 [Codex] * feat(models): materialize pinned Hugging Face snapshots Assisted-by: Codex:GPT-5 [Codex] * feat(models): bind managed snapshots at runtime Assisted-by: Codex:GPT-5 [Codex] * feat(gallery): materialize model artifacts during install Assisted-by: Codex:GPT-5 [Codex] * feat(gallery): declare managed Hugging Face artifacts Assisted-by: Codex:GPT-5 [Codex] * feat(models): preload managed model artifacts Assisted-by: Codex:GPT-5 [Codex] * fix(gallery): retain shared artifact caches on delete Assisted-by: Codex:GPT-5 [Codex] * feat(models): report artifact acquisition progress Assisted-by: Codex:GPT-5 [Codex] * refactor(backends): load managed models from ModelFile Assisted-by: Codex:GPT-5 [Codex] * refactor(backends): load staged speech model snapshots Assisted-by: Codex:GPT-5 [Codex] * refactor(backends): use staged snapshots in engine backends Assisted-by: Codex:GPT-5 [Codex] * test(distributed): cover staged artifact snapshots Assisted-by: Codex:GPT-5 [Codex] * docs: explain managed model artifacts Assisted-by: Codex:GPT-5 [Codex] * docs: add product design context Assisted-by: Codex:GPT-5 [Codex] * feat(ui): show model artifact download progress Assisted-by: Codex:GPT-5 [Codex] * Eagerly materialize Hugging Face artifacts Materialize HF-backed model references as managed GGUF artifacts during load, with lazy download retained only as fallback. Assisted-by: Codex:GPT-5 [shell] * Refactor HF downloads through a shared executor Assisted-by: Codex:GPT-5 [shell] * drop Signed-off-by: Ettore Di Giacinto <mudler@localai.io> --------- Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
LocalAI [bot]
@@ -116,7 +116,11 @@ func newApplication(appConfig *config.ApplicationConfig) *Application {
|
||||
ml.SetLoadObserver(corebackend.ModelLoadTraceObserver(appConfig))
|
||||
|
||||
app := &Application{
|
||||
backendLoader: config.NewModelConfigLoader(appConfig.SystemState.Model.ModelsPath),
|
||||
backendLoader: config.NewModelConfigLoader(
|
||||
appConfig.SystemState.Model.ModelsPath,
|
||||
config.WithArtifactMaterializer(appConfig.ModelArtifactMaterializer),
|
||||
config.WithPreloadDisplay(appConfig.ModelPreloadRenderMode, appConfig.DisableModelPreloadColor),
|
||||
),
|
||||
modelLoader: ml,
|
||||
applicationConfig: appConfig,
|
||||
templatesEvaluator: templates.NewEvaluator(appConfig.SystemState.Model.ModelsPath),
|
||||
|
||||
55
core/application/model_artifact_materializer_test.go
Normal file
55
core/application/model_artifact_materializer_test.go
Normal file
@@ -0,0 +1,55 @@
|
||||
package application
|
||||
|
||||
import (
|
||||
"context"
|
||||
"os"
|
||||
"path/filepath"
|
||||
|
||||
. "github.com/onsi/ginkgo/v2"
|
||||
. "github.com/onsi/gomega"
|
||||
|
||||
"github.com/mudler/LocalAI/core/config"
|
||||
"github.com/mudler/LocalAI/pkg/modelartifacts"
|
||||
"github.com/mudler/LocalAI/pkg/system"
|
||||
)
|
||||
|
||||
type applicationLoaderMaterializer struct {
|
||||
seen []modelartifacts.Spec
|
||||
}
|
||||
|
||||
func (f *applicationLoaderMaterializer) Ensure(_ context.Context, _ string, spec modelartifacts.Spec) (modelartifacts.Result, error) {
|
||||
f.seen = append(f.seen, spec)
|
||||
spec.Resolved = &modelartifacts.Resolved{
|
||||
Endpoint: "https://huggingface.co",
|
||||
Revision: "0123456789abcdef0123456789abcdef01234567",
|
||||
CacheKey: "0123456789abcdef0123456789abcdef0123456789abcdef0123456789abcdef",
|
||||
}
|
||||
return modelartifacts.Result{Spec: spec}, nil
|
||||
}
|
||||
|
||||
var _ = Describe("application model artifact wiring", func() {
|
||||
It("injects the controller materializer into the model config loader", func() {
|
||||
modelsPath := GinkgoT().TempDir()
|
||||
state, err := system.GetSystemState(
|
||||
system.WithModelPath(modelsPath),
|
||||
system.WithBackendPath(GinkgoT().TempDir()),
|
||||
)
|
||||
Expect(err).NotTo(HaveOccurred())
|
||||
materializer := &applicationLoaderMaterializer{}
|
||||
app := newApplication(&config.ApplicationConfig{
|
||||
Context: context.Background(),
|
||||
SystemState: state,
|
||||
ModelArtifactMaterializer: materializer,
|
||||
})
|
||||
Expect(os.WriteFile(filepath.Join(modelsPath, "managed.yaml"), []byte(`
|
||||
name: managed
|
||||
backend: transformers
|
||||
artifacts:
|
||||
- source: {type: huggingface, repo: owner/repo}
|
||||
parameters: {model: owner/repo}
|
||||
`), 0644)).To(Succeed())
|
||||
Expect(app.ModelConfigLoader().LoadModelConfigsFromPath(modelsPath)).To(Succeed())
|
||||
Expect(app.ModelConfigLoader().PreloadWithContext(context.Background(), modelsPath)).To(Succeed())
|
||||
Expect(materializer.seen).To(HaveLen(1))
|
||||
})
|
||||
})
|
||||
@@ -414,18 +414,18 @@ func New(opts ...config.AppOption) (*Application, error) {
|
||||
}
|
||||
}
|
||||
|
||||
if err := application.ModelConfigLoader().Preload(options.SystemState.Model.ModelsPath); err != nil {
|
||||
if err := application.ModelConfigLoader().PreloadWithContext(options.Context, options.SystemState.Model.ModelsPath); err != nil {
|
||||
xlog.Error("error downloading models", "error", err)
|
||||
}
|
||||
|
||||
if options.PreloadJSONModels != "" {
|
||||
if err := galleryop.ApplyGalleryFromString(options.SystemState, application.ModelLoader(), options.EnforcePredownloadScans, options.AutoloadBackendGalleries, options.Galleries, options.BackendGalleries, options.PreloadJSONModels, options.RequireBackendIntegrity); err != nil {
|
||||
if err := galleryop.ApplyGalleryFromString(options.SystemState, application.ModelLoader(), options.EnforcePredownloadScans, options.AutoloadBackendGalleries, options.Galleries, options.BackendGalleries, options.PreloadJSONModels, options.RequireBackendIntegrity, gallery.WithArtifactMaterializer(options.ModelArtifactMaterializer)); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
|
||||
if options.PreloadModelsFromPath != "" {
|
||||
if err := galleryop.ApplyGalleryFromFile(options.SystemState, application.ModelLoader(), options.EnforcePredownloadScans, options.AutoloadBackendGalleries, options.Galleries, options.BackendGalleries, options.PreloadModelsFromPath, options.RequireBackendIntegrity); err != nil {
|
||||
if err := galleryop.ApplyGalleryFromFile(options.SystemState, application.ModelLoader(), options.EnforcePredownloadScans, options.AutoloadBackendGalleries, options.Galleries, options.BackendGalleries, options.PreloadModelsFromPath, options.RequireBackendIntegrity, gallery.WithArtifactMaterializer(options.ModelArtifactMaterializer)); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user