fix(agent): filter InferenceServices by Metal accelerator type#157
Merged
fix(agent): filter InferenceServices by Metal accelerator type#157
Conversation
The Metal Agent was claiming all InferenceServices regardless of their Model's accelerator setting. This caused CUDA and CPU models intended for Linux nodes to be intercepted and run on the Mac instead. shouldWatch now looks up the referenced Model resource and only returns true when hardware.accelerator is "metal". Services referencing CUDA, CPU, or missing models are ignored. Signed-off-by: Christopher Maher <chris@defilan.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
hardware.accelerator: metalcuda,cpu, or missing models are ignoredProblem
The
shouldWatchmethod returnedtruefor all InferenceServices. This caused the Metal Agent on a Mac to intercept and run models that should have been scheduled as containers on NVIDIA GPU nodes (CUDA) or CPU nodes.Changes
pkg/agent/watcher.go—shouldWatchnow fetches the referenced Model and checksspec.hardware.accelerator == "metal"pkg/agent/watcher_test.go— Updated tests to cover metal/cuda/cpu/missing model filtering; existing tests updated with Model fixturesTest plan
go test ./pkg/agent/...passes (30/30)accelerator: cudaandaccelerator: cpumodelsaccelerator: metalmodels correctly