[Frontend] Remove frontend pooling multi task support. (#37861)

Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
wang.yuqi
2026-04-21 12:27:44 +00:00
committed by GitHub
co-authored by Cyrus Leung mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent 766cb65d00
commit d2e2e856ad
26 changed files with 260 additions and 273 deletions
@@ -1,6 +1,5 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
import logging
import weakref
import pytest
@@ -38,11 +37,11 @@ def llm():
seed=0,
attention_config=attention_config,
)
assert embedding_size == llm.model_config.embedding_size
yield weakref.proxy(llm)
del llm
cleanup_dist_env_and_memory()
@@ -74,16 +73,6 @@ def test_list_prompts(llm: LLM):
assert len(outputs[i].outputs.embedding) == embedding_size
@pytest.mark.skip_global_cleanup
def test_token_embed(llm: LLM, caplog_vllm):
with caplog_vllm.at_level(level=logging.WARNING, logger="vllm"):
outputs = llm.encode(prompt, pooling_task="token_embed", use_tqdm=False)
assert "deprecated" in caplog_vllm.text
multi_vector = outputs[0].outputs.data
assert multi_vector.shape == (11, 384)
@pytest.mark.skip_global_cleanup
def test_pooling_params(llm: LLM):
def get_outputs(normalize):
@@ -107,10 +96,14 @@ def test_pooling_params(llm: LLM):
)
@pytest.mark.parametrize("task", ["token_classify", "classify", "plugin"])
@pytest.mark.parametrize(
"task", ["token_classify", "classify", "token_embed", "plugin"]
)
def test_unsupported_tasks(llm: LLM, task: PoolingTask):
if task == "plugin":
err_msg = "No IOProcessor plugin installed."
elif task == "token_embed":
err_msg = "Try switching the model's pooling_task via.+"
else:
err_msg = "Classification API is not supported by this model.+"
with pytest.raises(ValueError, match=err_msg):