[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:
@@ -4,14 +4,16 @@ import json
|
||||
from collections.abc import Sequence
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from vllm.entrypoints.openai.parser.harmony_utils import parse_output_into_messages
|
||||
from vllm.entrypoints.openai.protocol import (
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
DeltaMessage,
|
||||
ExtractedToolCallInformation,
|
||||
FunctionCall,
|
||||
ToolCall,
|
||||
)
|
||||
from vllm.entrypoints.openai.parser.harmony_utils import parse_output_into_messages
|
||||
from vllm.logger import init_logger
|
||||
from vllm.tool_parsers.abstract_tool_parser import (
|
||||
ToolParser,
|
||||
|
||||
Reference in New Issue
Block a user