[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:
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user