Repository navigation
Fix CUDA driver resolution, CPU quota compatibility, and verifier packaging - #50
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fix three infrastructure failures that can prevent evaluation from starting or completing: incompatible CUDA driver libraries, CPU quotas lost through Compose translation, and a missing verifier entrypoint.
/usr/local/cuda/compatprefix from both Compose configurations andchild_env()inspoken-query-searchanddocument-page-search. These processes can then load the host-matched NVIDIA driver library. Previously, the image's compatibility library shadowed that library and caused CUDA error 803.cpus: 0. The CFS quota continues to enforce the budget on Compose versions that ignorecpus. Mismatched budgets and unsupported periods still fail validation. This applies to both phases of ten tasks; configurations without explicit CFS quotas retain their existing handling. Update the runtime documentation and regression tests accordingly.judge_repeats.pyto the Code Embedding verifier's COPY list. Itstest.shalready invokes this file, but the image omitted it, preventing the required three-round audit from starting.Task versions, resource budgets, scoring rules, models and input data are unchanged. The CUDA changes are task-local; the CPU compatibility change is in the shared runner.
Validation
cpus.git diff --checkpassed.GPU checks used the pinned shared base image and current task configuration/launcher code. Packaging validation reused cached verifier dependencies and recreated
/testsusing the production COPY instructions; a fresh full dependency build was not completed. The older Compose host was not retested; its recorded A/B evidence was reviewed. Full model evaluations and live judge API calls were not run.