feat: add initial AutoGPTQ backend implementation

This commit is contained in:
Ettore Di Giacinto 2023-08-07 22:39:10 +02:00
parent 91d49cfe9f
commit a843e64fc2
37 changed files with 660 additions and 148 deletions

View file

@ -27,7 +27,7 @@ func ModelInference(ctx context.Context, s string, loader *model.ModelLoader, c
model.WithLoadGRPCLLMModelOpts(grpcOpts),
model.WithThreads(uint32(c.Threads)), // some models uses this to allocate threads during startup
model.WithAssetDir(o.AssetsDestination),
model.WithModelFile(modelFile),
model.WithModel(modelFile),
model.WithContext(o.Context),
}