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

[Core][Bugfix][Perf] Introduce MQLLMEngine to avoid asyncio OH (#8157)

Browse Source 
Co-authored-by: Nick Hill <nickhill@us.ibm.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
This commit is contained in:
Alexander Matveev
2024-09-18 09:56:58 -04:00
committed by GitHub
parent 9d104b5beb
commit 7c7714d856
36 changed files with 1464 additions and 1169 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -4,7 +4,7 @@ from dataclasses import dataclass
from unittest.mock import MagicMock
from vllm.config import MultiModalConfig
from vllm.engine.async_llm_engine import AsyncLLMEngine
from vllm.engine.multiprocessing.client import MQLLMEngineClient
from vllm.entrypoints.openai.protocol import ChatCompletionRequest
from vllm.entrypoints.openai.serving_chat import OpenAIServingChat
from vllm.transformers_utils.tokenizer import get_tokenizer
@@ -52,8 +52,9 @@ def test_async_serving_chat_init():
def test_serving_chat_should_set_correct_max_tokens():
mock_engine = MagicMock(spec=AsyncLLMEngine)
mock_engine = MagicMock(spec=MQLLMEngineClient)
mock_engine.get_tokenizer.return_value = get_tokenizer(MODEL_NAME)
mock_engine.errored = False
serving_chat = OpenAIServingChat(mock_engine,
MockModelConfig(),