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

[Frontend][4/n] Improve pooling entrypoints | pooling. (#39153)

Browse Source 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
wang.yuqi
2026-04-09 18:09:45 +08:00
committed by GitHub
parent b6c9be509e
commit 66c079ae83
43 changed files with 554 additions and 733 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -87,7 +87,6 @@ def _build_serving_chat(engine: AsyncLLM) -> OpenAIServingChat:
serving_render = OpenAIServingRender(
model_config=engine.model_config,
renderer=engine.renderer,
io_processor=engine.io_processor,
model_registry=models.registry,
request_logger=None,
chat_template=None,
@@ -123,7 +122,6 @@ async def test_chat_error_non_stream():
mock_engine.errored = False
mock_engine.model_config = MockModelConfig()
mock_engine.input_processor = MagicMock()
mock_engine.io_processor = MagicMock()
mock_engine.renderer = _build_renderer(mock_engine.model_config)
serving_chat = _build_serving_chat(mock_engine)
@@ -173,7 +171,6 @@ async def test_chat_error_stream():
mock_engine.errored = False
mock_engine.model_config = MockModelConfig()
mock_engine.input_processor = MagicMock()
mock_engine.io_processor = MagicMock()
mock_engine.renderer = _build_renderer(mock_engine.model_config)
serving_chat = _build_serving_chat(mock_engine)