biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Model] Let more models to support the score template. (#31335)

Browse Source 
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>
This commit is contained in:
wang.yuqi
2026-01-05 19:54:26 +08:00
committed by GitHub
parent caaa482aca
commit 911d38ed99
23 changed files with 764 additions and 334 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
tests/models/language/pooling_mteb_test/test_cross_encoder.py
View File

@@ -11,27 +11,26 @@ from .mteb_score_utils import mteb_test_rerank_models
RERANK_MODELS = [
RerankModelInfo(
"cross-encoder/ms-marco-TinyBERT-L-2-v2",
mteb_score=0.32898,
architecture="BertForSequenceClassification",
pooling_type="CLS",
attn_type="encoder_only",
is_prefix_caching_supported=False,
is_chunked_prefill_supported=False,
mteb_score=0.32898,
),
RerankModelInfo(
"tomaarsen/Qwen3-Reranker-0.6B-seq-cls",
mteb_score=0.25736,
architecture="Qwen3ForSequenceClassification",
pooling_type="LAST",
attn_type="decoder",
is_prefix_caching_supported=True,
is_chunked_prefill_supported=True,
chat_template_name="qwen3_reranker.jinja",
mteb_score=0.33459,
),
]
@pytest.mark.parametrize("model_info", RERANK_MODELS)
def test_rerank_models_mteb(
hf_runner, vllm_runner, model_info: RerankModelInfo
) -> None:
mteb_test_rerank_models(hf_runner, vllm_runner, model_info)
def test_rerank_models_mteb(vllm_runner, model_info: RerankModelInfo) -> None:
mteb_test_rerank_models(vllm_runner, model_info)