[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:
@@ -9,7 +9,7 @@ from pydantic import (
|
||||
|
||||
from vllm import PoolingParams
|
||||
from vllm.config.pooler import get_use_activation
|
||||
from vllm.entrypoints.openai.protocol import OpenAIBaseModel, UsageInfo
|
||||
from vllm.entrypoints.openai.engine.protocol import OpenAIBaseModel, UsageInfo
|
||||
from vllm.entrypoints.pooling.embed.protocol import (
|
||||
EmbeddingChatRequest,
|
||||
EmbeddingCompletionRequest,
|
||||
|
||||
Reference in New Issue
Block a user