Make the verl OPD workflow product-first - #65
Merged
Conversation
DaoyuanLi2816
marked this pull request as ready for review
August 13, 2026 03:44
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
vllmvocabulary in the packaged Qwen3 profile while retaining explicit local-HF reinterpretation classifications;srcsetassets.Why
v0.8.0 shipped the executable profile, but the public surface still read primarily like a collection of research studies. This release makes the supported product journey discoverable without changing its algorithmic or distributed boundary. The research record remains public and is compressed to four direct links on the landing page.
Compatibility boundary
The supported profile remains
verl-opd-v0.8-single-gpu-v1, pinned to verl v0.8.0 at7aed6b230776f963fa09509c10d9c3a767d1102c. Local execution remains sequential HF phases. No distributed job or new scientific comparison was run.Validation
src/miniverlandscripts: passed53fc1d4d5b7adee09618d77ad62d4086ba56b78569832d6fc7c3bcd5c2695bbc