feat(loader): enhance single active backend by treating as singleton (#5107)

feat(loader): enhance single active backend by treating at singleton

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-01 20:58:11 +02:00 committed by GitHub
parent c59975ab05
commit 2c425e9c69
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
24 changed files with 92 additions and 71 deletions

View file

@ -53,6 +53,7 @@ func ModelInference(ctx context.Context, s string, messages []schema.Message, im
if err != nil {
return nil, err
}
defer loader.Close()
var protoMessages []*proto.Message
// if we are using the tokenizer template, we need to convert the messages to proto messages