Sami
Sami
@kthui @Tabrizian Any idea if this is an intended behaviour ? I want to make sure that unhealthy processes are restarted correctly , but playing with `kill` it seems that...
Also, after compiling `python_backend` and force a specific model to restart inside `TRITONBACKEND_ModelInstanceExecute` by forcing restart to true inside `ProcessRequest` , a segmentation fault is triggered and killing the whole...
> Also, after compiling `python_backend` and force a specific model to restart inside `TRITONBACKEND_ModelInstanceExecute` by forcing restart to true inside `ProcessRequest` , a segmentation fault is triggered and killing the...
Thanks for the answer @Tabrizian. My model isn't segfaulting, triton server restart logic is. I did some digging and the issue seems to happen consistently in `StubLauncher::ReceiveMessageFromStub`, after recompiling the...
any news @Eywek ?
@zeruniverse how did you manage to get this sorted out ? I think i'm facing the same issue.
You kept Triton Server but instead of calling an ensemble once you're calling your models 1 by 1 in your Client ?
Even if jaroWinkler doesn't support distance by default, maybe you want to provide a coherent interface and just reverse similarity result for `distance` method.