Skip to content

fix(metal): refuse to serve a pack whose per-layer embeddings cannot … - #334

Merged
linyubupa merged 1 commit into
mainfrom
fix/metal-ple-off-fatal
Nov 21, 2026
Merged

linyubupa merged 1 commit into
mainfrom
fix/metal-ple-off-fatal

Conversation

@linyubupa

Copy link
Copy Markdown
Collaborator

…be used

On a Metal window, PLE off was a silent degradation: the startup line said "PLE OFF" and the model answered without its per-layer embeddings - fluent and wrong, with nothing failing. The table comes from the pack's PLE file and the block needs every ple_* tensor, so PLE off with those weights present means an incomplete or mismatched model folder.

Fail the window's init with that reason instead, so the server reports it rather than serving a model that is not the one the pack describes.

A pack without PLE tensors still runs: that is a different model, and PleRun::ready() returning false there is expected.

What & why

Fixes #

Area

  • Engine, CLI or server (edge0-infer/)
  • Model asset tools (edge0-infer/tools/assets/)
  • Chat app examples (edge0-infer/examples/)
  • Model docs (docs/)
  • edge0-strata/
  • Other

How was it tested?

Checklist

  • Linked an agreed issue, or this PR is documentation-only
  • Related fixes in this area are in this pull request, one commit per fix
  • This is one of at most two open pull requests from me
  • ctest --preset cpu -L "L0|L1" passes locally in edge0-infer/ (engine changes); CI also runs these and the L2 tests not labeled local-only
  • Changes to model computation: ran the local-only answer suites (ctest --preset cpu -L local-only) on Apple silicon with i8mm (M2 or later), which CI cannot judge
  • Ran the higher test levels this change affects (see edge0-infer/docs/testing.md)
  • Added/updated tests for new behavior
  • Updated relevant docs / READMEs (incl. translations if user-facing)

…be used

On a Metal window, PLE off was a silent degradation: the startup line said
"PLE OFF" and the model answered without its per-layer embeddings - fluent and
wrong, with nothing failing. The table comes from the pack's PLE file and the
block needs every ple_* tensor, so PLE off with those weights present means an
incomplete or mismatched model folder.

Fail the window's init with that reason instead, so the server reports it rather
than serving a model that is not the one the pack describes.

A pack without PLE tensors still runs: that is a different model, and
`PleRun::ready()` returning false there is expected.
@github-actions github-actions Bot added the needs-info Title, issue link, test notes, or PR cap still missing label Nov 21, 2026
@github-actions

Copy link
Copy Markdown

This pull request is labeled needs-info and is not in the review queue.
The intake rules are in CONTRIBUTING.md.

  • Replace the template comment under "## How was it tested?" with the commands, platform, and results you actually ran.

@github-actions github-actions Bot added the strata edge0-strata label Nov 21, 2026
@linyubupa
linyubupa merged commit 478612f into main Nov 21, 2026
3 of 4 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

needs-info Title, issue link, test notes, or PR cap still missing strata edge0-strata

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant