NVIDIA Triton Inference server documentation

[mpietrzy]

Your website advertised NVIDIA's Triton Inference server as one of the supported deployable platforms using the Seldon Core integration within Kubeflow. When I click on the documentation link, it's out of date. The ability to support this deployment scheme is a critical part of our requirements evaluation. Please advise as to any updated documentation.

[tarekabouzeid]

/assign

[tarekabouzeid]

Hi,
I don't see this link in website, can you please share it?
Below are some related links, hope they can help.

• https://medium.com/kubeflow/gpu-accelerated-inference-for-kubernetes-with-the-nvidia-tensorrt-inference-server-and-kubeflow-63061305fff2
• https://kserve.github.io/website/latest/modelserving/v1beta1/transformer/torchserve_image_transformer/#create-inferenceservice

[varodrig]

/close

[google-oss-prow]

@varodrig: Closing this issue.

In response to this:

/close

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository.

[varodrig]

@mpietrzy we are closing this issue given that the information was provided. thanks @tarekabouzeid