biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Refactor] [8/N] to simplify the vLLM openai responsesapi_serving architecture (#32260)

Browse Source 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-14 15:26:24 +08:00
committed by GitHub
parent 6388b50058
commit 9312a6c03a
21 changed files with 754 additions and 674 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/entrypoints/openai/test_serving_responses.py
View File

@@ -14,8 +14,9 @@ from openai.types.responses.tool import (
)
from vllm.entrypoints.context import ConversationContext
from vllm.entrypoints.openai.engine.protocol import ErrorResponse, ResponsesRequest
from vllm.entrypoints.openai.serving_responses import (
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
from vllm.entrypoints.openai.responses.serving import (
OpenAIServingResponses,
_extract_allowed_tools_from_mcp_requests,
extract_tool_types,