roboflow / inference

A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.
https://inference.roboflow.com
Other
1.15k stars 85 forks source link

Added the github runner instead of the custom runner #379

Closed bigbitbus closed 2 months ago

bigbitbus commented 2 months ago

Description

Remove the custom T4 GPU machine.

Add the github-provided T4 machine.

Type of change

Please delete options that are not relevant.

How has this change been tested, please provide a testcase or example of how you tested the change?

To be tested.

Any specific deployment considerations

For example, documentation changes, usability, usage/costs, secrets, etc.

Docs

PawelPeczek-Roboflow commented 2 months ago

for this to be fully tested u probably need to have that merged and run test from GHA, right? if that's the case I am fine with approving, testing and fixing if something is not fine

PawelPeczek-Roboflow commented 2 months ago

I do not understand why tests fails now

PawelPeczek-Roboflow commented 2 months ago

@bigbitbus - I would merge that but I am not sure why unit tests are failing

PawelPeczek-Roboflow commented 2 months ago

Ok, I understand now - just not merged with most recent main :)