[Frontend] Delegate preprocessing to OpenAIServingRender (#36483)

Signed-off-by: Sage Ahrac <sagiahrak@gmail.com>
This commit is contained in:
Sage
2026-03-13 00:39:43 -07:00
committed by GitHub
parent a4ad9db541
commit a2268617cf
10 changed files with 203 additions and 196 deletions
+6 -1
View File
@@ -10,7 +10,7 @@ import logging
import time
import uuid
from collections.abc import AsyncGenerator
from typing import Any
from typing import TYPE_CHECKING, Any
from fastapi import Request
@@ -43,6 +43,9 @@ from vllm.entrypoints.openai.engine.protocol import (
)
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
if TYPE_CHECKING:
from vllm.entrypoints.serve.render.serving import OpenAIServingRender
logger = logging.getLogger(__name__)
@@ -59,6 +62,7 @@ class AnthropicServingMessages(OpenAIServingChat):
models: OpenAIServingModels,
response_role: str,
*,
openai_serving_render: "OpenAIServingRender",
request_logger: RequestLogger | None,
chat_template: str | None,
chat_template_content_format: ChatTemplateContentFormatOption,
@@ -73,6 +77,7 @@ class AnthropicServingMessages(OpenAIServingChat):
engine_client=engine_client,
models=models,
response_role=response_role,
openai_serving_render=openai_serving_render,
request_logger=request_logger,
chat_template=chat_template,
chat_template_content_format=chat_template_content_format,