Skip to content

fix(local-inference): point at Metal nil-pipeline guard - #11617

Merged
lalalune merged 2 commits into
developfrom
fix/11612-ios-metal-null-pipeline
Jul 2, 2026
Merged

fix(local-inference): point at Metal nil-pipeline guard#11617
lalalune merged 2 commits into
developfrom
fix/11612-ios-metal-null-pipeline

Conversation

@lalalune

@lalalune lalalune commented Jul 2, 2026

Copy link
Copy Markdown
Member

Summary

  • update the local-inference llama.cpp submodule to fix(metal): guard nil compute pipelines llama.cpp#39
  • the submodule guard replaces the observed NULL Metal pipeline dereference with an explicit nil Metal compute pipeline backend failure at both pipeline dereference points
  • add issue evidence documenting the local checks and the A18 Pro device verification still required

Refs #11612.

Evidence

  • PASS: git diff --check inside plugins/plugin-local-inference/native/llama.cpp
  • PASS: parent git diff --check
  • PASS: parent pointer reviewed with git diff --submodule=log -- plugins/plugin-local-inference/native/llama.cpp

Not captured here

Residual

This is the defensive stop-the-NULL-deref patch. It does not resolve why the A18 Pro mul_mat pipeline is nil; root-cause kernel selection/compilation still needs real-device Metal diagnostics.

@greptile-apps greptile-apps Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Your trial has ended. Reactivate Greptile to resume code reviews.

@coderabbitai

coderabbitai Bot commented Jul 2, 2026

Copy link
Copy Markdown
Contributor

Important

Review skipped

Auto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: 298f6f48-164f-4bff-a5da-934abb99a4ce

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • 🔍 Trigger review
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch fix/11612-ios-metal-null-pipeline

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.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

…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>

@greptile-apps greptile-apps Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Your trial has ended. Reactivate Greptile to resume code reviews.

@lalalune
lalalune merged commit e8fd731 into develop Jul 2, 2026
24 of 29 checks passed
@lalalune
lalalune deleted the fix/11612-ios-metal-null-pipeline branch July 2, 2026 22:25
@lalalune

lalalune commented Jul 2, 2026

Copy link
Copy Markdown
Member Author

Post-merge review note: I verified the llama.cpp submodule pointer against elizaOS/llama.cpp PR #39 and inspected the actual diff (2bdcef89..299d5b78): it is a 10-line defensive nil-pipeline guard at the two Metal pipeline dereference points, and the submodule diff itself is clean.

One parent-repo issue remained after merge: git diff --check origin/develop flagged whitespace in three evidence log files under .github/issue-evidence/11612-ios-metal-null-pipeline/mac-metal-regression/. I opened follow-up PR #11645 with only that evidence whitespace cleanup: #11645

@claude

claude Bot commented Jul 3, 2026

Copy link
Copy Markdown
Contributor

Claude encountered an error —— View job


I'll analyze this and get back to you.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant