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

4
tests/entrypoints/openai/responses/test_serving_responses.py
View File

@@ -218,7 +218,6 @@ class TestInitializeToolSessions:
engine_client.model_config = model_config
engine_client.input_processor = MagicMock()
engine_client.io_processor = MagicMock()
engine_client.renderer = MagicMock()
models = MagicMock()
@@ -307,7 +306,6 @@ class TestValidateGeneratorInput:
engine_client.model_config = model_config
engine_client.input_processor = MagicMock()
engine_client.io_processor = MagicMock()
engine_client.renderer = MagicMock()
models = MagicMock()
@@ -369,7 +367,6 @@ async def test_reasoning_tokens_counted_for_text_reasoning_model(monkeypatch):
model_config.get_diff_sampling_param.return_value = {}
engine_client.model_config = model_config
engine_client.input_processor = MagicMock()
engine_client.io_processor = MagicMock()
engine_client.renderer = MagicMock()
tokenizer = FakeTokenizer()
@@ -672,7 +669,6 @@ def _make_serving_instance_with_reasoning():
model_config.get_diff_sampling_param.return_value = {}
engine_client.model_config = model_config
engine_client.input_processor = MagicMock()
engine_client.io_processor = MagicMock()
engine_client.renderer = MagicMock()
models = MagicMock()