biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Refactor][Frontend] Keep all logic about reasoning into one class (#14428)

Browse Source 
Signed-off-by: Ce Gao <cegao@tensorchord.ai>
This commit is contained in:
Ce Gao
2025-03-28 15:23:30 +08:00
committed by GitHub
parent 2d9045fce8
commit 32b14baf8a
18 changed files with 171 additions and 200 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/entrypoints/openai/api_server.py
View File

@@ -68,7 +68,6 @@ from vllm.entrypoints.openai.protocol import (ChatCompletionRequest,
TranscriptionRequest,
TranscriptionResponse,
UnloadLoRAAdapterRequest)
from vllm.entrypoints.openai.reasoning_parsers import ReasoningParserManager
# yapf: enable
from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
from vllm.entrypoints.openai.serving_completion import OpenAIServingCompletion
@@ -85,6 +84,7 @@ from vllm.entrypoints.openai.serving_transcription import (
from vllm.entrypoints.openai.tool_parsers import ToolParserManager
from vllm.entrypoints.utils import load_aware_call, with_cancellation
from vllm.logger import init_logger
from vllm.reasoning import ReasoningParserManager
from vllm.transformers_utils.config import (
maybe_register_config_serialize_by_value)
from vllm.transformers_utils.tokenizer import MistralTokenizer