KY

Disabling saving of models to local clearml ie. /opt/clearml/data/fileserver

8

### **Issue** ClearML server crashed and it was caused by ClearML uploading the models into ClearML server (by default). Is it possible to have an overriding config so clients can...

Expose tritonserver args in values.yaml

10

Current k8s_onprem chart has predefined args in deployment.yaml. We could change it from the yaml file though but would be cleaner to customise the args through values.yaml instead.

rbac required to run triton in k8s

4

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] In the [triton secure...

Authorisation for endpoints

10

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] For security reasons, there...

Allow triton to read from multiple cloud model repositories

6

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] Trying to use Triton...

I have used nvidia-dcgm-exporter to expose the nvidia metrics via port 9400. I managed to find some metrics like DCGM_FI_DEV_GPU_TEMP, etc but I am not able to find metrics for...

Issue with pytorch preprocess code

1

Hi, I have encountered error stating that model was expecting input [1 28 28] but given [1 784] when trying out the pytorch example. I think it is due to...

Error when running minikube-gui on fedora

1

./minikube-gui: symbol lookup error: ./minikube-gui: undefined symbol: _ZdlPvm, version Qt_5