failed to update VM: Your organization is not allowed to use GPU machines

,
1

My fly.toml works correctly in the “ord” region, but attempting to set any GPU, such as “a10”, results in the error: “Your organization is not allowed to use GPU machines.”

How can I bypass this error?

Here is my fly.toml

app = 'xxxxxxxxxxx'
primary_region = 'ord'

[build]


[[services]]
  internal_port = 443
  processes = ["app"]
  protocol = "tcp"
  tls_passthrough = true
  auto_stop_machines = 'stop'
  auto_start_machines = true
  min_machines_running = 0

  [[services.ports]]
    port = 443

[[vm]]
  memory = '8gb'
  cpu_kind = 'performance'
  cpus = 1
  gpus = 1
  gpu_kind = 'a10'
3

Hey Freddie,
It looks like you will need to email billing@fly.io. You can read more about it here: Get help with Fly GPUs!.

2 Likes
4

Thanks for your comment, Kaycee. I’ve been stuck for days, and no one is replying to my emails to “billing@fly.io” or “support@fly.io.” I have credit in my account, but I don’t know how to fix this. If this keeps up, I might switch to another serverless provider.

5

When did you send your first email? I don’t think I’ve ever taken longer than ~1 day to get a response from billing.

1 Like
6

Hello Miend. I contacted billing@fly.io three days ago and happily, I got a response just a few hours ago. They told me that the issue is related to an algorithm evaluating my trust score. However, I am still unsure if I will be able to resolve this trust score problem. As of now, I am still unable to deploy my project.

7

An update on this: billing has enabled it for me manually, and I can now deploy. :rocket:

8

This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.