Skip to content

update CompletionMessage attributes in openai.proto #86

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
dongwang218 merged 2 commits into from
Sep 4, 2025
Merged

update CompletionMessage attributes in openai.proto #86

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
92fd09d
remove dummy request parameter used for staled libs
yangli5t Sep 4, 2025
a49e598
update openai.proto to adapt new params
yangli5t Sep 4, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 16 additions & 1 deletion matrix/app_server/llm/openai.proto
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,11 +42,26 @@ message Usage {
int32 total_tokens = 3;
}

message FunctionCall {
string name = 1;
string arguments = 2;
}
message ToolCall {
string id = 1;
string type = 2; // Only "function" is valid
FunctionCall function = 3;
}

Comment on lines +45 to +54
Copy link
Contributor

@dongwang218 dongwang218 Sep 4, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

how multiple arguments are represented in proto?

Copy link
Contributor Author

@yangli5t yangli5t Sep 4, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think it will all wrap as string arguments https://github.com/vllm-project/vllm/blob/main/vllm/entrypoints/openai/protocol.py#L1735-L1742

// CompletionMessage is the message that is sent to the server.
message CompletionMessage {
string role = 1;
string content = 2;
string name = 3; // omitempty will need to be handled in implementation
string refusal = 3;
repeated FunctionCall function_call = 4;
repeated ToolCall tool_calls = 5;

// vLLM-specific fields that are not in OpenAI spec
string reasoning_content = 6;
}

message ChatCompletionResponseChoice {
Expand Down
58 changes: 31 additions & 27 deletions matrix/app_server/llm/openai_pb2.py
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

8 changes: 0 additions & 8 deletions matrix/app_server/llm/ray_serve_vllm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -460,14 +460,6 @@ async def CreateCompletion(self, request):
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
Copy link
Contributor

@dongwang218 dongwang218 Sep 4, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

does removing it work for vllm 0.8.3 too?

Copy link
Contributor Author

@yangli5t yangli5t Sep 4, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes. this was updated long time ago.

scope={
"type": "http",
"method": "GET",
"path": "",
"headers": [],
}
),
)
if isinstance(generator, ErrorResponse):
if hasattr(generator, "error"):
Expand Down