Throttling appears on one deployment, while another has spare quota. What can you do?
Why B is the answer
Reassign TPM between the deployments
Quota is shared across deployments and can be reassigned.
In detail
- TPM can be reassigned between deployments.
- Review quota use regularly.
Use case
An illustrative scenario, not a real incident.
One deployment is throttled while another sits idle. Moving TPM from one to the other solves it, with no request for quota.
See it in different ways
mindmap
root((GenAIOps))
Prompts
In Git
Variants
Models
Fit on your data
Gradual rollout
Capacity
Standard
Provisioned
Evaluation
In CI/CD
On production tracesflowchart LR S0["Find spare TPM"] --> S1["Reduce it"] --> S2["Raise the throttled deployment"]
Key point: Reassign TPM between deployments.
Why the other options are wrong
- A. Add more evaluators to the release pipeline
- Evaluators do not change quota.
- C. Delete the Foundry project and create it again
- Deleting the project loses work and fixes nothing.
- D. Raise the temperature on the throttled deployment
- Temperature has no effect on throttling.