Repository navigation
WIP: Keep vLLM context failures within individual annotations - #138
Draft
ErlisLushtaku wants to merge 4 commits into
Draft
ErlisLushtaku wants to merge 4 commits into
ErlisLushtaku wants to merge 4 commits into
Conversation
This was referenced Oct 8, 2026
This was referenced Oct 9, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
WIP. Not ready for review yet.
Checks each vLLM chat request with the native renderer before generating. Prompts exceeding the model context return empty, failed annotations while the remaining requests run normally. Model settings and battle membership stay unchanged.
Marks skipped requests as errors so they are excluded from raw-output caches and successful-response usage. Genuine empty model outputs retain their existing behavior. Other validation errors still propagate.
This is separate from the judge-tuning stack and applies to vLLM chat inference. Hosted-provider context errors and raw base-model generation are outside this change.