Skip to content

Add bounded GRPO constructor diagnostic - #270

Draft
ProfSynapse wants to merge 8 commits into
release/api-v1-completionfrom
t3/grpo-constructor-diagnostic
Draft

ProfSynapse wants to merge 8 commits into
release/api-v1-completionfrom
t3/grpo-constructor-diagnostic

Conversation

@ProfSynapse

Copy link
Copy Markdown
Owner

Scope

Adds a constructor-only GRPO diagnostic under the existing derived-image qualification CLI. The probe derives exact four-row input from the normal plan/recipe/dataset, binds committed probe/helper/CLI source plus release/image/model inventory, and returns closed stage/category and class/signature hashes. The effectful mode uses one consumed claim, a private verified model copy, no network, one GPU, two CPUs, 8 GiB RAM, a 120-second workload wait, bounded logs, terminal inspection, and identity-checked container cleanup. It never explicitly calls training or generation.

The published Unsloth Zoo 2026.1.2 wheel requires an accelerator during import, so CPU cannot exercise the installed patched constructor. This is a diagnostic capability, not a fix for the consumed Modal run or training qualification.

Verification

  • 10 focused CPU tests pass, including actual hung/flooding process termination and Docker lifecycle/timeout substitutes.
  • GRPO offline and outer closure checks: CURRENT. Modal runtime lock: CURRENT. Skill trees: synchronized.
  • Provider-free input projection against retained 0d515 plan: 4 rows, 1,873 bytes, SHA256 3c5c179a0aca0e2ab9899c6a11cb6064761ec2df766e76c60899192093c89416.

Review boundary

No Docker image pull/build, GPU/model download, Modal call, training, or old-resource cleanup occurred. The host has no usable GPU, and the derived image and retained Modal snapshot are not local. The reviewed GPU admission still needs exact image capture and an independently verified offline snapshot on the execution machine. See docs/review/grpo-constructor-diagnostic.md. The old attempt remains consumed; no root cause is claimed.

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant