[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:
@@ -11,16 +11,18 @@ from fastapi import Request
|
||||
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.entrypoints.logger import RequestLogger
|
||||
from vllm.entrypoints.openai.protocol import (
|
||||
from vllm.entrypoints.openai.chat_completion.protocol import (
|
||||
ChatCompletionLogProb,
|
||||
ChatCompletionLogProbs,
|
||||
ChatCompletionLogProbsContent,
|
||||
)
|
||||
from vllm.entrypoints.openai.engine.protocol import (
|
||||
ErrorResponse,
|
||||
PromptTokenUsageInfo,
|
||||
RequestResponseMetadata,
|
||||
UsageInfo,
|
||||
)
|
||||
from vllm.entrypoints.openai.serving_engine import OpenAIServing, clamp_prompt_logprobs
|
||||
from vllm.entrypoints.openai.engine.serving import OpenAIServing, clamp_prompt_logprobs
|
||||
from vllm.entrypoints.openai.serving_models import OpenAIServingModels
|
||||
from vllm.entrypoints.serve.disagg.protocol import (
|
||||
GenerateRequest,
|
||||
|
||||
Reference in New Issue
Block a user