llama-stack
llama-stack copied to clipboard
Add a new lifecycle method to providers after the stack has been initialized
🚀 Describe the new functionality needed
As I was writing an inference provider that needs to dynamically register models while starting (not through static declaration in run.yaml), I got help from @bbrowning to inject models API but the registration fails because it has to be done in the provider constructor and thus the provider is not yet registered.
💡 Why is this needed? What if we don't build it?
To support dynamic registration of various resources related to the current provider
Other thoughts
Add a new optional lifecycle method in the provider that get called when the stack if fully initiallized
This issue has been automatically marked as stale because it has not had activity within 60 days. It will be automatically closed if no further activity occurs within 30 days.
Still accurate
This issue has been automatically marked as stale because it has not had activity within 60 days. It will be automatically closed if no further activity occurs within 30 days.
@jeffmaury which inference provider?
Podman AI Lab
@jeffmaury where can i find the code? is the issue that users cannot register models not in the static list? is the issue that users should not need to register models at all?
This issue has been automatically marked as stale because it has not had activity within 60 days. It will be automatically closed if no further activity occurs within 30 days.
This issue has been automatically closed due to inactivity. Please feel free to reopen if you feel it is still relevant!