Feat/OpenAI backend worker#3
Merged
Merged
Conversation
- Implement a Dynamo worker that forwards requests to a local OpenAI-compatible server - Support streaming chat/completions responses - Coalesce streamed tool call arguments - Normalize chat :template fields before forwarding requests
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| return | ||
| task.cancel() | ||
| with contextlib.suppress(asyncio.CancelledError): | ||
| await task |
| future.cancel() | ||
| try: | ||
| await future | ||
| except asyncio.CancelledError: |
| ) | ||
| try: | ||
| yield event_source | ||
| except BaseException as exc: |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add an OpenAI-compatible backend worker for Dynamo so SGLang and vLLM can handle chat processing through their own OpenAI-compatible APIs, reducing the lag between upstream engine changes and Dynamo support.
Problem
Dynamo’s native SGLang/vLLM paths are still tightly coupled to model-specific chat processing, which means upstream engine changes to chat templating, reasoning, tool calling, and related request/response behavior often take time to be reflected in Dynamo. That lag makes it harder to stay current with engine behavior and support new upstream capabilities quickly.
Solution
This PR adds an OpenAI-compatible backend worker for Dynamo that forwards chat/completions requests to a colocated engine’s OpenAI-compatible endpoint, so chat processing can be delegated to the engine itself.
To support that cleanly, this PR also:
- chat_template_args -> chat_template_kwargs
- vLLM streamed reasoning -> reasoning_content
- dynamo.openai_backend.sglang
- dynamo.openai_backend.vllm