Jasmine

guess the error is that the proxy address format in the global variable is incorrect, Proxy URL had no scheme, should start with http:// or https://


Very sorry! When writing the Onnx runtime, I specified the CPU inference, please wait https://github.com/LlmKira/VitsServer/blob/c11475105127609ce7a1b8cc62e42ce70982ba9e/event.py#L157

https://github.com/LlmKira/VitsServer/pull/11/commits/954cebaf9a00f0458bc1fcb0ebc21191d48d6798

ok

pls wait a while for svc branch

> > ok > > Have done 50 test inferences for each model with same input text > pytorch avg ~2.5s > onnx avg ~ 2.7s > triton onnx avg...

The ONNX model will perform some initialization operations during the first reasoning after the Session is loaded, and this factor should also be considered

``` PC brands: ThinkBook 16 G4+ IAP OS: Arch Linux x86_64 Kernel Version: 5.18.5-arch1-1 branch: dev Status: Build pass and Wi-Fi Connected ```