Conversation
…nchmark detection) Three fixes for Metal deployment experience: - Default GPU vendor to "apple" when accelerator is metal instead of showing "nvidia" in the deploy summary (#249) - Add exponential backoff retry to the Metal agent watcher so it recovers when started before CRDs are installed (#250) - Auto-detect Metal deployments in the benchmark command and skip port-forward, using the direct localhost endpoint instead (#251) Signed-off-by: Christopher Maher <chris@mahercode.io>
Signed-off-by: Christopher Maher <chris@mahercode.io>
The GPU vendor CRD enum only allows nvidia/amd/intel. The previous fix wrote "apple" to opts.gpuVendor which was then used in the CRD, causing validation failure. Now the vendor display is overridden only in the summary output, keeping the CRD value valid. Signed-off-by: Christopher Maher <chris@mahercode.io>
Satisfies goconst linter by reusing the existing acceleratorMetal constant from benchmark.go instead of repeating the "metal" string. Signed-off-by: Christopher Maher <chris@mahercode.io>
Merged
This was referenced Apr 1, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Three fixes for Metal deployment experience discovered during TurboQuant benchmarking and demo recording:
Test plan
make testpasses--accelerator metalshowsGPU: 1 x applehelm install, verify it recovers after CRDs installedllmkube benchmarkagainst Metal deployment without--port-forward=falseFixes #249, #250, #251