update CompletionMessage attributes in openai.proto #86
Merged
dongwang218 merged 2 commits intomainfrom Sep 4, 2025
Merged
Conversation
meta-cla
bot
added
the
CLA Signed
dongwang218
reviewed
Sep 4, 2025
| await self.openai_serving_chat.models.init_static_loras() | ||
| generator = await self.openai_serving_completion.create_completion( | ||
| completion_request, | ||
| Request( # this Request is purely dummy, it is changed to optional in vllm's recent pull https://github.com/vllm-project/vllm/pull/12503 |
Contributor
There was a problem hiding this comment.
does removing it work for vllm 0.8.3 too?
Contributor
Author
There was a problem hiding this comment.
yes. this was updated long time ago.
dongwang218
reviewed
Sep 4, 2025
Comment on lines
+45
to
+54
| message FunctionCall { | ||
| string name = 1; | ||
| string arguments = 2; | ||
| } | ||
| message ToolCall { | ||
| string id = 1; | ||
| string type = 2; // Only "function" is valid | ||
| FunctionCall function = 3; | ||
| } | ||
|
|
Contributor
There was a problem hiding this comment.
how multiple arguments are represented in proto?
Contributor
Author
There was a problem hiding this comment.
I think it will all wrap as string arguments https://github.com/vllm-project/vllm/blob/main/vllm/entrypoints/openai/protocol.py#L1735-L1742
dongwang218
approved these changes
Sep 4, 2025
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why ?
add refusal, function_call, tool_call, reasoning_content
according to openai protocol https://github.com/vllm-project/vllm/blob/main/vllm/entrypoints/openai/protocol.py#L1735-L1742
so that grpc call can be made with models like gpt-oss-120b
python -m grpc_tools.protoc -I. --python_out=. --grpc_python_out=. ./matrix/app_server/llm/openai.protoTest plan
deployed a gpt-oss-120b model
python -m matrix deploy_applications --action add --applications "[{'model_name': '/datasets/pretrained-llms/gpt-oss-120b', 'model_size': 'gpt-oss-120b', 'name': 'gpt120b_grpc', 'use_grpc': 'true'}]"successfully got response.