-
**What happened**:
Making an HTTP request to the HTTPS port of the controller generates a log containing the sNAT ip of the node serving the request on its NodePort, instead of the real ip coming f…
-
**Deployment**
- [ ] _implement script to load registered model from mlflow server_
- [ ] _containerize the API and host on render_
- [ ] _try uvicorn & gunicorn and compare performace_
- [ ] _e2e ci…
-
recap updated
5 months ago
-
Hi, I have trained a new model but meet errors when testing, I did it as:
1. train a model with:
```
accelerate launch --num_processes 2 --multi_gpu --mixed_precision "fp16" \
tutorial_train.py …
-
## Description
#19489 is the epic for Facility Locator progressive disclosure. We need to write a test plan that:
1. Harnesses the existing [Facility Locator regression test](https://docs.google.com…
-
## Goal
Allow action developers to thoroughly test all parts of their VM.
## Assumptions
* Users want to sanity check their VM with an e2e testing suite that tests their TXs in a VM
* Users want…
-
-
Have you done any load testing to indicate how many messages per second it supports?
The same for number of metrics that can be exposed by a single exporter instance?
-
Load test the website
-
I did some load testing in the past, but it was only on the home page. Before public advertisements, we might want to test the actual application itself to make sure it won't break under high load.