other(torch_compile): parametrize e2e test over RBLN_WEIGHT_FREE (wf_on xfail)#647
Open
rebel-jinhwan wants to merge 1 commit into
Open
other(torch_compile): parametrize e2e test over RBLN_WEIGHT_FREE (wf_on xfail)#647rebel-jinhwan wants to merge 1 commit into
rebel-jinhwan wants to merge 1 commit into
Conversation
Add an autouse, parametrized fixture in the e2e conftest so every e2e test runs once with weight-free compilation off and once on, without touching the individual test files. RBLN_WEIGHT_FREE is read by the rebel compiler at compile time inside the spawn-ed EngineCore worker, so setting it before the LLM is built is enough; no separate test process is needed. The compile-cache hash does not include the weight-free mode, so the cache is disabled to stop the on leg from silently cache-hitting the off artifact. The wf_on leg is marked xfail (non-strict) since the weight-free path is not yet correctness-complete across all models/features; flip to strict=True once it is fully supported. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
rebel-jinhwan
changed the title
rebel-jinhwan
changed the title
rebel-jinhwan
requested review from
rebel-sjlee,
rebel-wonsubkim and
rebel-ykchoi
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add an autouse, parametrized fixture in the e2e conftest so every e2e test runs once with weight-free compilation off and once on, without touching the individual test files.
RBLN_WEIGHT_FREE is read by the rebel compiler at compile time inside the spawn-ed EngineCore worker, so setting it before the LLM is built is enough; no separate test process is needed. The compile-cache hash does not include the weight-free mode, so the cache is disabled to stop the on leg from silently cache-hitting the off artifact.
The wf_on leg is marked xfail (non-strict) since the weight-free path is not yet correctness-complete across all models/features; flip to strict=True once it is fully supported.
🚀 Summary of Changes
📌 Related Issues / Tickets
✅ Type of Change
release)feature)model)core)fix)perf)refactor)docs)other): please describe🧪 How to Test
.........📸 Screenshots / Logs (if applicable)
📋 Checklist
💬 Notes