"Max Retries Reached"
For some reason, I see this error wayy more commonly now than before, is there a reason?
Network is still PAINFULLY slow
This is maybe the 3rd or 4th time I post this here or send a support request about this issue in the past 6 months. I've moved my production workloads to another GPU cloud provider because of this.
Today, I wanted to see if things were better now. They are not. Testing out the new GitHub integration, my build that pulls a model from HuggingFace has been running for almost 10 minutes now because it's downloading a 1GB model weight at 500 kbps....
Once again I ask, are you planning to improve this situation once and for all some day? I moved out to another platform because of this. The fact that it happens on the build, okay, might not be terrible as we're not charged for build time I understand. But I've seen this issue during serverless execution where uploading a 10 MB file would take almost 90 seconds. And these are seconds we're billed for at a GPU price tier....
⚠ Hundreds of unexplained requests coming in
🔴 We have started to experience a sudden influx of requests on all of our production endpoints, first started a month ago, but now its getting more frequent, like every day in the past 2-3 days, around this time. (when i posted this)
These requests are not coming from us, since the jobs that we actually submitted and are in the queue are below a 100 at this timeframe.
I've already rotated the API keys, but its still happening.
Any way to figure this out?...
