mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-08-01 02:49:51 -04:00
Code Issues Packages Projects Releases Wiki Activity

feat: materialize Hugging Face model artifacts (#10825)

Browse Source 
* 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]
2026-07-15 01:09:33 +02:00
committed by GitHub
parent d82c38ee77
commit bcc41219f7
83 changed files with 4315 additions and 339 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
pkg/model/loader.go
View File

@@ -397,14 +397,21 @@ func (ml *ModelLoader) ListLoadedModels() []*Model {
}
func (ml *ModelLoader) LoadModel(modelID, modelName string, loader func(string, string, string) (*Model, error)) (*Model, error) {
return ml.loadModel(modelID, modelName, loader, true)
return ml.LoadModelWithFile(modelID, modelName, modelName, loader)
}
// loadModel is the implementation behind LoadModel. checkCooldown gates fresh,
func (ml *ModelLoader) LoadModelWithFile(modelID, modelName, modelFileName string, loader func(string, string, string) (*Model, error)) (*Model, error) {
if modelFileName == "" {
modelFileName = modelName
}
return ml.loadModel(modelID, modelName, modelFileName, loader, true)
}
// loadModel is the implementation behind LoadModelWithFile. checkCooldown gates fresh,
// independent load triggers behind the per-model failure cooldown; it is set to
// false for the coalesced retry of an in-flight burst (a follower whose leader
// just failed), which is not a new trigger and should still get its one retry.
func (ml *ModelLoader) loadModel(modelID, modelName string, loader func(string, string, string) (*Model, error), checkCooldown bool) (*Model, error) {
func (ml *ModelLoader) loadModel(modelID, modelName, modelFileName string, loader func(string, string, string) (*Model, error), checkCooldown bool) (*Model, error) {
ml.mu.Lock()
distributed := ml.modelRouter != nil
ml.mu.Unlock()
@@ -430,7 +437,7 @@ func (ml *ModelLoader) loadModel(modelID, modelName string, loader func(string,
// per inference. Trade-off: cross-frontend in-flight visibility
// becomes eventually consistent, acceptable for 1-3 frontend
// deployments.
modelFile := filepath.Join(ml.ModelPath, modelName)
modelFile := filepath.Join(ml.ModelPath, modelFileName)
model, err := loader(modelID, modelName, modelFile)
if err != nil {
return nil, fmt.Errorf("failed to route model with internal loader: %s", err)
@@ -484,7 +491,7 @@ func (ml *ModelLoader) loadModel(modelID, modelName string, loader func(string,
}
// If still not loaded, the other goroutine failed. Retry once as part of
// this burst, bypassing the cooldown gate (we are not a new trigger).
return ml.loadModel(modelID, modelName, loader, false)
return ml.loadModel(modelID, modelName, modelFileName, loader, false)
}
// Mark this model as loading (create a channel that will be closed when done)
@@ -501,7 +508,7 @@ func (ml *ModelLoader) loadModel(modelID, modelName string, loader func(string,
}()
// Load the model (this can take a long time, no lock held)
modelFile := filepath.Join(ml.ModelPath, modelName)
modelFile := filepath.Join(ml.ModelPath, modelFileName)
xlog.Debug("Loading model in memory from file", "file", modelFile)
model, err := loader(modelID, modelName, modelFile)