xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-04 05:24:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

[BugFix]: properly catch templating error when preprocess input (#13976)

Browse Source 
Signed-off-by: Guillaume Calmettes <gcalmettes@scaleway.com>
This commit is contained in:
Guillaume Calmettes 2025-03-14 08:58:34 -04:00 committed by GitHub
parent ab93f1360f
commit fd8e055ffb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 37 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
vllm/entrypoints/openai/serving_chat.py
View File

@ -7,6 +7,7 @@ from collections.abc import AsyncGenerator, AsyncIterator
from collections.abc import Sequence as GenericSequence from collections.abc import Sequence as GenericSequence
from typing import Callable, Final, Optional, Union from typing import Callable, Final, Optional, Union
import jinja2
from fastapi import Request from fastapi import Request
from vllm.config import ModelConfig from vllm.config import ModelConfig
@ -199,6 +200,15 @@ class OpenAIServingChat(OpenAIServing):
except ValueError as e: except ValueError as e:
logger.exception("Error in preprocessing prompt inputs") logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e)) return self.create_error_response(str(e))
except TypeError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
except RuntimeError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
except jinja2.TemplateError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
request_id = "chatcmpl-" \ request_id = "chatcmpl-" \
f"{self._base_request_id(raw_request, request.request_id)}" f"{self._base_request_id(raw_request, request.request_id)}"

10
vllm/entrypoints/openai/serving_completion.py
View File

@ -6,6 +6,7 @@ from collections.abc import AsyncGenerator, AsyncIterator
from collections.abc import Sequence as GenericSequence from collections.abc import Sequence as GenericSequence
from typing import Optional, Union, cast from typing import Optional, Union, cast
import jinja2
from fastapi import Request from fastapi import Request
from vllm.config import ModelConfig from vllm.config import ModelConfig
@ -114,6 +115,15 @@ class OpenAIServingCompletion(OpenAIServing):
except ValueError as e: except ValueError as e:
logger.exception("Error in preprocessing prompt inputs") logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e)) return self.create_error_response(str(e))
except TypeError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
except RuntimeError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
except jinja2.TemplateError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
# Schedule the request and get the result generator. # Schedule the request and get the result generator.
generators: list[AsyncGenerator[RequestOutput, None]] = [] generators: list[AsyncGenerator[RequestOutput, None]] = []

3
vllm/entrypoints/openai/serving_embedding.py
View File

@ -142,6 +142,9 @@ class OpenAIServingEmbedding(OpenAIServing):
except ValueError as e: except ValueError as e:
logger.exception("Error in preprocessing prompt inputs") logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e)) return self.create_error_response(str(e))
except TypeError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
# Schedule the request and get the result generator. # Schedule the request and get the result generator.
generators: list[AsyncGenerator[PoolingRequestOutput, None]] = [] generators: list[AsyncGenerator[PoolingRequestOutput, None]] = []

7
vllm/entrypoints/openai/serving_pooling.py
View File

@ -6,6 +6,7 @@ import time
from collections.abc import AsyncGenerator from collections.abc import AsyncGenerator
from typing import Final, Literal, Optional, Union, cast from typing import Final, Literal, Optional, Union, cast
import jinja2
import numpy as np import numpy as np
from fastapi import Request from fastapi import Request
from typing_extensions import assert_never from typing_extensions import assert_never
@ -138,6 +139,12 @@ class OpenAIServingPooling(OpenAIServing):
except ValueError as e: except ValueError as e:
logger.exception("Error in preprocessing prompt inputs") logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e)) return self.create_error_response(str(e))
except TypeError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
except jinja2.TemplateError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
# Schedule the request and get the result generator. # Schedule the request and get the result generator.
generators: list[AsyncGenerator[PoolingRequestOutput, None]] = [] generators: list[AsyncGenerator[PoolingRequestOutput, None]] = []

7
vllm/entrypoints/openai/serving_tokenization.py
View File

@ -2,6 +2,7 @@
from typing import Final, Optional, Union from typing import Final, Optional, Union
import jinja2
from fastapi import Request from fastapi import Request
from vllm.config import ModelConfig from vllm.config import ModelConfig
@ -91,6 +92,12 @@ class OpenAIServingTokenization(OpenAIServing):
except ValueError as e: except ValueError as e:
logger.exception("Error in preprocessing prompt inputs") logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e)) return self.create_error_response(str(e))
except TypeError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
except jinja2.TemplateError as e:
logger.exception("Error in preprocessing prompt inputs")
return self.create_error_response(str(e))
input_ids: list[int] = [] input_ids: list[int] = []
for i, engine_prompt in enumerate(engine_prompts): for i, engine_prompt in enumerate(engine_prompts):