[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
@@ -4,6 +4,7 @@ import pytest
import torch
from vllm import TokensPrompt
from vllm.config import PoolerConfig
@pytest.mark.parametrize(
@@ -20,6 +21,7 @@ def test_extract_hidden_states(hf_runner, vllm_runner, model: str):
max_model_len=128,
enforce_eager=True,
runner="pooling",
pooler_config=PoolerConfig(task="token_embed"),
enable_prefix_caching=True,
) as vllm_model:
pooling_outputs = vllm_model.llm.encode(
@@ -44,14 +46,3 @@ def test_extract_hidden_states(hf_runner, vllm_runner, model: str):
assert len(output.prompt_token_ids) == n
assert len(output.outputs.data) == n
assert output.num_cached_tokens == 0
# skip_reading_prefix_cache can still write to cache
# to accelerate following requests
pooling_outputs = vllm_model.llm.encode(
[TokensPrompt(prompt_token_ids=t) for t in token_prompts],
pooling_task="embed",
)
for n, output in zip(n_prompt_tokens, pooling_outputs):
assert len(output.prompt_token_ids) == n
assert output.num_cached_tokens > 0