Skip to content

[serve] update to support latest vLLM #58945

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
ruisearch42 merged 3 commits into from
Dec 3, 2025
Merged

[serve] update to support latest vLLM #58945

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a1b7cf4
fix
soodoshll Nov 24, 2025
b657d20
upd
soodoshll Nov 24, 2025
cc125f6
fmt
soodoshll Nov 24, 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
24 changes: 15 additions & 9 deletions python/ray/llm/_internal/serve/engines/vllm/vllm_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
import argparse
import inspect
import os
from typing import TYPE_CHECKING, AsyncGenerator, Optional, Tuple, Union

Expand Down Expand Up @@ -195,17 +196,22 @@ async def start(self) -> None:
state = State()
# TODO (Kourosh): There might be some variables that needs protection?
args = argparse.Namespace(
**vllm_frontend_args.__dict__,
**vllm_engine_args.__dict__,
**(vllm_frontend_args.__dict__ | vllm_engine_args.__dict__)
)

await init_app_state(
engine_client=self._engine_client,
# TODO (ahao): remove vllm_config for vllm v1.12
vllm_config=vllm_engine_config,
state=state,
args=args,
)
if "vllm_config" in inspect.signature(init_app_state).parameters:
await init_app_state(
self._engine_client,
vllm_config=vllm_engine_config,
state=state,
args=args,
)
else:
await init_app_state(
self._engine_client,
state=state,
args=args,
)
Comment on lines +202 to +214
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist bot Nov 24, 2025

Choose a reason for hiding this comment

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

medium

To improve maintainability and reduce code duplication, you can refactor this logic to build a dictionary of keyword arguments and then call init_app_state once. This avoids repeating the call and makes the code more concise and easier to read.

        init_kwargs = {
            "engine_client": self._engine_client,
            "state": state,
            "args": args,
        }
        if "vllm_config" in inspect.signature(init_app_state).parameters:
            init_kwargs["vllm_config"] = vllm_engine_config

        await init_app_state(**init_kwargs)


self._oai_models = state.openai_serving_models
self._oai_serving_chat = state.openai_serving_chat
Expand Down