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

[Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240)

Browse Source 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-13 21:01:39 +08:00
committed by GitHub
parent a5bbbd2f24
commit fefce49807
128 changed files with 1221 additions and 1008 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tests/entrypoints/openai/test_chat_error.py
View File

@@ -9,8 +9,9 @@ from unittest.mock import AsyncMock, MagicMock
import pytest
from vllm.config.multimodal import MultiModalConfig
from vllm.entrypoints.openai.protocol import ChatCompletionRequest, ErrorResponse
from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
from vllm.entrypoints.openai.chat_completion.protocol import ChatCompletionRequest
from vllm.entrypoints.openai.chat_completion.serving import OpenAIServingChat
from vllm.entrypoints.openai.engine.protocol import ErrorResponse
from vllm.entrypoints.openai.serving_models import BaseModelPath, OpenAIServingModels
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.tokenizers import get_tokenizer