[Refactor] [10/N] to simplify the vLLM openai completion serving architecture (#32369)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-15 07:41:34 +00:00
committed by GitHub
parent ae1eba6a9a
commit 4c1c501a7e
43 changed files with 777 additions and 642 deletions
+1 -1
View File
@@ -10,10 +10,10 @@ from fastapi import APIRouter, Depends, FastAPI, HTTPException, Request, Respons
from fastapi.responses import JSONResponse, StreamingResponse
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.openai.api_server import validate_json_request
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
)
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.serve.disagg.protocol import (
GenerateRequest,
GenerateResponse,
+1 -1
View File
@@ -6,10 +6,10 @@ from pydantic import BaseModel, Field
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionLogProbs
from vllm.entrypoints.openai.engine.protocol import (
Logprob,
SamplingParams,
StreamOptions,
)
from vllm.logprobs import Logprob
from vllm.utils import random_uuid
+1 -1
View File
@@ -23,7 +23,7 @@ from vllm.entrypoints.openai.engine.protocol import (
UsageInfo,
)
from vllm.entrypoints.openai.engine.serving import OpenAIServing, clamp_prompt_logprobs
from vllm.entrypoints.openai.serving_models import OpenAIServingModels
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.serve.disagg.protocol import (
GenerateRequest,
GenerateResponse,
@@ -9,10 +9,10 @@ from fastapi import APIRouter, Depends, FastAPI, HTTPException, Request
from fastapi.responses import JSONResponse
from vllm.engine.protocol import EngineClient
from vllm.entrypoints.openai.api_server import validate_json_request
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
)
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.serve.elastic_ep.middleware import (
get_scaling_elastic_ep,
set_scaling_elastic_ep,
+3 -2
View File
@@ -7,11 +7,12 @@ from fastapi import APIRouter, Depends, FastAPI, Request
from fastapi.responses import JSONResponse, Response
from vllm import envs
from vllm.entrypoints.openai.api_server import models, validate_json_request
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
)
from vllm.entrypoints.openai.serving_models import OpenAIServingModels
from vllm.entrypoints.openai.models.api_router import models
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.serve.lora.protocol import (
LoadLoRAAdapterRequest,
UnloadLoRAAdapterRequest,
@@ -9,10 +9,10 @@ from fastapi.exceptions import RequestValidationError
from fastapi.responses import JSONResponse
from typing_extensions import assert_never
from vllm.entrypoints.openai.api_server import validate_json_request
from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
)
from vllm.entrypoints.openai.utils import validate_json_request
from vllm.entrypoints.serve.tokenize.protocol import (
DetokenizeRequest,
DetokenizeResponse,
+1 -1
View File
@@ -13,7 +13,7 @@ from vllm.entrypoints.openai.engine.protocol import (
ErrorResponse,
)
from vllm.entrypoints.openai.engine.serving import OpenAIServing
from vllm.entrypoints.openai.serving_models import OpenAIServingModels
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.entrypoints.renderer import RenderConfig
from vllm.entrypoints.serve.tokenize.protocol import (
DetokenizeRequest,