Skip to content

[Bug]: AutoDeploy: avoid aot compilation of auto_deploy kernels unless kernel is needed #9017

@lucaslie

Description

@lucaslie

System Info

see https://nvidia.slack.com/archives/C059LSY62BT/p1762167016530579

Right now, our moe_align extension gets compiled when auto_deploy gets imported. This can affect tooling that imports auto_deploy even if auto_deploy is not used or when the moe_align extension is not used.

Let's minimize the times that the extension gets imported and hence compiled. A couple of suggestion for that:

  • Use local imports inside functions instead of top-level file imports
  • Avoid auto-importing the moe_align or any other extension

Metadata

Metadata

Assignees

Labels

AutoDeploy<NV> AutoDeploy BackendInfra<NV>automated tests, build checks, github actions, system stability & efficiency.bugSomething isn't working

Type

Projects

Status

Done

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions