[Frontend] Split ServingRender into renderer and entrypoint. (#44285)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
@@ -13,12 +13,8 @@ from starlette.datastructures import Headers
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.generate.beam_search.online import BeamSearchOnlineMixin
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.completion.protocol import (
|
||||
CompletionRequest,
|
||||
)
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
|
||||
from vllm.entrypoints.openai.completion.protocol import CompletionRequest
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
ErrorResponse,
|
||||
GenerationError,
|
||||
|
||||
Reference in New Issue
Block a user