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

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-04-09 18:09:45 +08:00
parent b6c9be509e
commit 66c079ae83
43 changed files with 554 additions and 733 deletions
--- a/tests/entrypoints/serve/lora/test_serving_models.py
+++ b/tests/entrypoints/serve/lora/test_serving_models.py
@@ -34,7 +34,6 @@ async def _async_serving_models_init() -> OpenAIServingModels:
    mock_model_config.max_model_len = 2048
    mock_engine_client.model_config = mock_model_config
    mock_engine_client.input_processor = MagicMock()
-    mock_engine_client.io_processor = MagicMock()
    mock_engine_client.renderer = MagicMock()

    serving_models = OpenAIServingModels(