Pass through Lora Request Kwargs #513
Open
Conversation
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
This commit adds the ability to pass custom metadata (like request_id) to
tracer.invoke() calls and access it within the trace context. This solves
issues with request/response alignment in batched inference scenarios where
lazy evaluation can cause mismatched completions.
Changes:
- Mediator: Add custom_data parameter to store arbitrary metadata
- Invoker: Extract custom parameters (like request_id) from kwargs before
passing to batcher, store in mediator's custom_data
- Access pattern: Use vllm._interleaver.current.custom_data.get('request_id')
within trace context
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <[email protected]>
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Outdated suggestions cannot be applied.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.
Added support for passing through LORA Requests into vllm.trace