[refactor] [asr] Add transcription adapter for extensible ASR models support#22181
Merged
mickqian merged 6 commits intosgl-project:mainfrom Apr 8, 2026
Merged
Conversation
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
10 tasks
mickqian
approved these changes
Apr 7, 2026
| @@ -1329,13 +1328,13 @@ def is_generation_model(model_architectures: List[str], is_embedding: bool = Fal | |||
| "Qwen3VLMoeForConditionalGeneration", | |||
| "Qwen3_5ForConditionalGeneration", | |||
| "Qwen3_5MoeForConditionalGeneration", | |||
| "Qwen3ASRForConditionalGeneration", | |||
Collaborator
There was a problem hiding this comment.
maybe detect this by whether we have dedicated processor/adaptor for this model, instead of maintaining a hard-coded list, in the future
Collaborator
|
/tag-and-rerun-ci |
- Introduced `TranscriptionAdapter` abstract class for model-specific transcription logic. - Added `Qwen3ASRAdapter` and `WhisperAdapter` implementations for respective ASR models. - Implemented adapter registration via `@register_transcription_adapter` decorator. - Updated `OpenAIServingTranscription` to utilize the adapter framework for processing requests.
2971bbb to
a51a32f
Compare
This was referenced Apr 10, 2026
5 tasks
yhyang201
pushed a commit
to yhyang201/sglang
that referenced
this pull request
Apr 22, 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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Follow up of #22073. To remove hardcoded model family detection and branching.
See reviews in #22073 and #22089.
Modifications
Mainly scoped under python/sglang/srt/entrypoints/openai/
Will coordinate with #22089 to resolve conflicts and dependencies.
Accuracy Tests
Same as #22073
Speed Tests and Profiling
To be added.
Checklist
Review and Merge Process
/tag-and-rerun-ci,/tag-run-ci-label,/rerun-failed-ci