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

7
tests/entrypoints/pooling/token_embed/test_offline.py
View File

@@ -62,14 +62,17 @@ def test_token_ids_prompts(llm: LLM):
assert outputs[0].outputs.data.shape == (11, 384)
@pytest.mark.parametrize("task", ["embed", "classify", "token_classify"])
@pytest.mark.parametrize("task", ["embed", "classify", "token_classify", "plugin"])
def test_unsupported_tasks(llm: LLM, task: PoolingTask, caplog_vllm):
if task == "embed":
with caplog_vllm.at_level(level=logging.WARNING, logger="vllm"):
llm.encode(prompt, pooling_task=task, use_tqdm=False)
assert "deprecated" in caplog_vllm.text
else:
err_msg = "Classification API is not supported by this model.+"
if task == "plugin":
err_msg = "No IOProcessor plugin installed."
else:
err_msg = "Classification API is not supported by this model.+"
with pytest.raises(ValueError, match=err_msg):
llm.encode(prompt, pooling_task=task, use_tqdm=False)

9
tests/entrypoints/pooling/token_embed/test_online.py
View File

@@ -73,7 +73,7 @@ async def test_pooling_token_embed(server: RemoteOpenAIServer, model_name: str):
@pytest.mark.asyncio
@pytest.mark.parametrize("model_name", [MODEL_NAME])
@pytest.mark.parametrize("task", ["embed", "classify", "token_classify", "plugin"])
@pytest.mark.parametrize("task", ["classify", "token_classify", "plugin"])
async def test_pooling_not_supported(
server: RemoteOpenAIServer, model_name: str, task: str
):
@@ -87,7 +87,8 @@ async def test_pooling_not_supported(
},
)
if task != "embed":
assert response.json()["error"]["type"] == "BadRequestError"
if task == "plugin":
err_msg = "No IOProcessor plugin installed."
else:
err_msg = f"Unsupported task: {task!r}"
assert response.json()["error"]["message"].startswith(err_msg)
assert response.json()["error"]["message"].startswith(err_msg)