[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-13 13:01:39 +00:00
committed by GitHub
parent a5bbbd2f24
commit fefce49807
128 changed files with 1221 additions and 1008 deletions
@@ -16,7 +16,10 @@ from openai.types.responses.response_reasoning_item import (
)
from vllm.entrypoints.constants import MCP_PREFIX
from vllm.entrypoints.openai.protocol import ResponseInputOutputItem, ResponsesRequest
from vllm.entrypoints.openai.engine.protocol import (
ResponseInputOutputItem,
ResponsesRequest,
)
from vllm.outputs import CompletionOutput
from vllm.reasoning.abs_reasoning_parsers import ReasoningParser
from vllm.tokenizers import TokenizerLike