feat: enhanced guided decoding params validation and migration to StructuredOutputsParams #117
+99
−3
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Outdated suggestions cannot be applied.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.
This PR modernizes the backend's handling of structured outputs and introduces strict runtime validation to protect the vLLM engine from malformed requests. It migrates from the deprecated
GuidedDecodingParamstoStructuredOutputsParams, ensuring compatibility with recent vLLM versions (0.13.0+) while maintaining support for legacy clients.Key Goals:
StructuredOutputsParams.Changes:
GuidedDecodingParamswithStructuredOutputsParams.guided_decodingparameters tostructured_outputs, ensuring seamless operation across vLLM versions (tested on 0.11.2 and 0.13.0).interegularto ensure compilability.xgrammarto catch syntax errors immediately.choice,json, andwhitespace_patternfields.backendparameter.Testing:
guided_decodingrequests on vLLM 0.11.2 and 0.13.0.ValueErrorresponses.