mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-14 23:28:23 -04:00
Richard Palethorpe
799cc9f211
feat: bound backend admission and expose running traces Add process-wide backend execution admission without blocking UI or administrative HTTP work. Represent backend operations while they are in flight, surface running traces with immediate log links, and tie streaming admission leases to the gRPC receive lifecycle. Assisted-by: OpenAI Codex: GPT-5 Signed-off-by: Richard Palethorpe <io@richiejp.com>
39 lines
867 B
Go
39 lines
867 B
Go
package backend
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
model "github.com/mudler/LocalAI/pkg/model"
|
|
)
|
|
|
|
func TokenMetrics(
|
|
ctx context.Context,
|
|
modelFile string,
|
|
loader *model.ModelLoader,
|
|
appConfig *config.ApplicationConfig,
|
|
modelConfig config.ModelConfig) (*proto.MetricsResponse, error) {
|
|
|
|
opts := ModelOptions(modelConfig, appConfig, model.WithModel(modelFile))
|
|
model, err := loader.Load(opts...)
|
|
if err != nil {
|
|
recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
|
|
return nil, err
|
|
}
|
|
|
|
if model == nil {
|
|
return nil, fmt.Errorf("could not loadmodel model")
|
|
}
|
|
release, err := AcquireGlobalBackendSlot()
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer release()
|
|
|
|
res, err := model.GetTokenMetrics(ctx, &proto.MetricsRequest{})
|
|
|
|
return res, err
|
|
}
|