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

[Refactor] [10/N] to simplify the vLLM openai completion serving architecture (#32369)

Browse Source 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
This commit is contained in:
Chauncey
2026-01-15 15:41:34 +08:00
committed by GitHub
parent ae1eba6a9a
commit 4c1c501a7e
43 changed files with 777 additions and 642 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/entrypoints/openai/test_chat_error.py
View File

@@ -12,7 +12,8 @@ from vllm.config.multimodal import MultiModalConfig
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.entrypoints.openai.models.protocol import BaseModelPath
from vllm.entrypoints.openai.models.serving import OpenAIServingModels
from vllm.outputs import CompletionOutput, RequestOutput
from vllm.tokenizers import get_tokenizer
from vllm.v1.engine.async_llm import AsyncLLM