[Frontend][Core] Standardize request error handling with VLLMError hierarchy (#49665)

Signed-off-by: Zach Zhu <zzqshu@126.com>
This commit is contained in:
Zach Zhu
2026-07-29 04:20:40 +00:00
committed by GitHub
parent f37f03db4a
commit 58f9659397
46 changed files with 370 additions and 248 deletions
+2 -2
View File
@@ -19,7 +19,7 @@ from pydantic import (
from vllm.config.utils import replace
from vllm.entrypoints.chat_utils import make_tool_call_id
from vllm.exceptions import VLLMValidationError
from vllm.exceptions import VLLMServerError, VLLMValidationError
from vllm.logger import init_logger
from vllm.sampling_params import StructuredOutputsParams
from vllm.utils import random_uuid
@@ -404,7 +404,7 @@ class DeltaMessage(OpenAIBaseModel):
return data
class GenerationError(Exception):
class GenerationError(VLLMServerError):
"""raised when finish_reason indicates internal server error (500)"""
def __init__(self, message: str = "Internal server error"):