dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

feat: track internally started models by ID (#3693)

Browse source 
* chore(refactor): track internally started models by ID

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Just extend options, no need to copy

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Improve debugging for rerankers failures

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Simplify model loading with rerankers

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Be more consistent when generating model options

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Uncommitted code

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Make deleteProcess more idiomatic

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Adapt CLI for sound generation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixup threads definition

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Handle corner case where c.Seed is nil

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Consistently use ModelOptions

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Adapt new code to refactoring

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Dave <dave@gray101.com>
This commit is contained in:
Ettore Di Giacinto 2024-10-02 08:55:58 +02:00 • committed by GitHub
parent db704199dc
commit 0965c6cd68
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
20 changed files with 169 additions and 185 deletions
Download patch file Download diff file Expand all files Collapse all files

13
core/backend/llm.go
View file

@ -33,22 +33,11 @@ type TokenUsage struct {
func ModelInference(ctx context.Context, s string, messages []schema.Message, images, videos, audios []string, loader *model.ModelLoader, c config.BackendConfig, o *config.ApplicationConfig, tokenCallback func(string, TokenUsage) bool) (func() (LLMResponse, error), error) {
modelFile := c.Model
threads := c.Threads
if *threads == 0 && o.Threads != 0 {
threads = &o.Threads
}
grpcOpts := GRPCModelOpts(c)
var inferenceModel grpc.Backend
var err error
opts := modelOpts(c, o, []model.Option{
model.WithLoadGRPCLoadModelOpts(grpcOpts),
model.WithThreads(uint32(*threads)), // some models uses this to allocate threads during startup
model.WithAssetDir(o.AssetsDestination),
model.WithModel(modelFile),
model.WithContext(o.Context),
})
opts := ModelOptions(c, o, []model.Option{})
if c.Backend != "" {
opts = append(opts, model.WithBackendString(c.Backend))