mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-07-30 18:09:05 -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

16
core/cli/models.go
View File

@@ -14,6 +14,7 @@ import (
"github.com/mudler/LocalAI/core/startup"
"github.com/mudler/LocalAI/pkg/downloader"
"github.com/mudler/LocalAI/pkg/model"
"github.com/mudler/LocalAI/pkg/modelartifacts"
"github.com/mudler/LocalAI/pkg/system"
"github.com/mudler/xlog"
"github.com/schollz/progressbar/v3"
@@ -24,6 +25,9 @@ type ModelsCMDFlags struct {
BackendGalleries string `env:"LOCALAI_BACKEND_GALLERIES,BACKEND_GALLERIES" help:"JSON list of backend galleries" group:"backends" default:"${backends}"`
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
BackendsPath string `env:"LOCALAI_BACKENDS_PATH,BACKENDS_PATH" type:"path" default:"${basepath}/backends" help:"Path containing backends used for inferencing" group:"storage"`
Color string `env:"COLOR" hidden:""`
NoColor string `env:"NO_COLOR" hidden:""`
HFToken string `env:"HF_TOKEN" hidden:""`
}
type ModelsList struct {
@@ -80,10 +84,18 @@ func (mi *ModelsInstall) Run(ctx *cliContext.Context) error {
return err
}
artifactMaterializer := modelartifacts.NewDefaultManager(
modelartifacts.WithHuggingFaceToken(mi.HFToken),
)
galleryService := galleryop.NewGalleryService(&config.ApplicationConfig{
SystemState: systemState,
SystemState: systemState,
ModelArtifactMaterializer: artifactMaterializer,
ModelPreloadRenderMode: mi.Color,
DisableModelPreloadColor: mi.NoColor != "",
}, model.NewModelLoader(systemState))
err = galleryService.Start(context.Background(), config.NewModelConfigLoader(mi.ModelsPath), systemState)
err = galleryService.Start(context.Background(), config.NewModelConfigLoader(mi.ModelsPath,
config.WithArtifactMaterializer(artifactMaterializer),
config.WithPreloadDisplay(mi.Color, mi.NoColor != "")), systemState)
if err != nil {
return err
}

8
core/cli/run.go
View File

@@ -16,6 +16,7 @@ import (
"github.com/mudler/LocalAI/core/http"
"github.com/mudler/LocalAI/core/p2p"
"github.com/mudler/LocalAI/internal"
"github.com/mudler/LocalAI/pkg/modelartifacts"
"github.com/mudler/LocalAI/pkg/signals"
"github.com/mudler/LocalAI/pkg/system"
"github.com/mudler/xlog"
@@ -28,6 +29,9 @@ import (
type RunCMD struct {
ModelArgs []string `arg:"" optional:"" name:"models" help:"Model configuration URLs to load"`
Color string `env:"COLOR" hidden:""`
NoColor string `env:"NO_COLOR" hidden:""`
HFToken string `env:"HF_TOKEN" hidden:""`
ExternalBackends []string `env:"LOCALAI_EXTERNAL_BACKENDS,EXTERNAL_BACKENDS" help:"A list of external backends to load from gallery on boot" group:"backends"`
WebRTCNAT1To1IPs []string `env:"LOCALAI_WEBRTC_NAT_1TO1_IPS,WEBRTC_NAT_1TO1_IPS" help:"IPs advertised as the host ICE candidates for /v1/realtime WebRTC instead of every local interface. Set to the reachable host/LAN IP when running under Docker host networking or NAT, where pion otherwise offers unreachable bridge addresses and the connection drops after ICE consent checks fail." group:"api"`
@@ -238,6 +242,10 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
opts := []config.AppOption{
config.WithContext(context.Background()),
config.WithModelArtifactMaterializer(modelartifacts.NewDefaultManager(
modelartifacts.WithHuggingFaceToken(r.HFToken),
)),
config.WithModelPreloadDisplay(r.Color, r.NoColor != ""),
config.WithConfigFile(r.ModelsConfigFile),
config.WithJSONStringPreload(r.PreloadModels),
config.WithYAMLConfigPreload(r.PreloadModelsConfig),