fix(local-inference): point at Metal nil-pipeline guard - #11617
Conversation
There was a problem hiding this comment.
Your trial has ended. Reactivate Greptile to resume code reviews.
|
Important Review skippedAuto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
…l-pipeline guard
Build the guarded llama.cpp submodule commit 299d5b78b with the Apple Metal
toolchain (macOS 26.2, M4 Max) and run a real eliza-1 0.8B GGUF fully offloaded
to the Metal GPU (every layer -> device MTL0). Generation completes correctly
("... is **Paris**.", 430/174 tok/s) with no nil-pipeline abort, proving the
two new nil-checks are inert on the healthy Metal path and only fire on a
genuinely nil pipeline. Verifies the regression risk of the submodule bump on
the one platform the original Linux capture host could not.
Refs #11612.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
There was a problem hiding this comment.
Your trial has ended. Reactivate Greptile to resume code reviews.
|
Post-merge review note: I verified the llama.cpp submodule pointer against One parent-repo issue remained after merge: |
|
Claude encountered an error —— View job I'll analyze this and get back to you. |
Summary
nil Metal compute pipelinebackend failure at both pipeline dereference pointsRefs #11612.
Evidence
git diff --checkinsideplugins/plugin-local-inference/native/llama.cppgit diff --checkgit diff --submodule=log -- plugins/plugin-local-inference/native/llama.cppNot captured here
.ipsartifacts.Residual
This is the defensive stop-the-NULL-deref patch. It does not resolve why the A18 Pro
mul_matpipeline is nil; root-cause kernel selection/compilation still needs real-device Metal diagnostics.