fix(executor): ModelOp OOM vocabulary + planner-audit issues #369-#371#47
Merged
Conversation
…ct §9); file planner-audit issues #369-#371 The hub's OOM reaction (handleModelFailure -> UNLOAD a resident model for headroom) was dead code: the worker emitted "load_failed" for every LOAD/UNLOAD failure. Classify CUDA OOM into the contract vocabulary. Issues #369 (residency owns executor pipelines / honest vram_bytes), #370 (keep-set disk GC), #371 (worker-side VRAM juggling) filed in agents/progress.md (next_id -> 372); hub counterparts tensorhub #533-#537, design doc tensorhub docs/planner.md.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Gen-worker half of the planner audit (hub half: tensorhub PR #70, docs/planner.md + issues #533-#537).
load_failed, so the orchestrator's OOM reaction (handleModelFailure→ UNLOAD a resident model for headroom) could never fire. OOM exceptions now emitModelEvent{FAILED, error:"oom"}per contract §9. Unit tests included.keepis write-only today, no disk GC exists (contract §7 unimplemented)uv run --extra dev pytest -q: 182 passed, 1 skipped.🤖 Generated with Claude Code