[Model] Support pooling models (#3122)

### What this PR does / why we need it?

Support pooling models (like `bge-reranker-v2-m3`) in vllm-ascend, this
pr covered the three model types of embed (cls_token, mean_token,
lasttoken).

After this
[commit](17373dcd93),
vllm has provided support for adapting pooling models on the v1 engine.
This PR includes corresponding adaptations on the vllm-ascend side.

Fixes #1960

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: lianyibo <lianyibo1@kunlunit.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
lianyibo
2025-12-10 11:37:57 +08:00
committed by GitHub
parent 1a7a34c5ec
commit e32014ac1d
17 changed files with 577 additions and 338 deletions

View File

@@ -77,6 +77,7 @@ jobs:
# pytest -sv tests/e2e/singlecard/test_aclgraph.py
# pytest -sv tests/e2e/singlecard/test_quantization.py
pytest -sv tests/e2e/singlecard/test_vlm.py::test_multimodal_vl
pytest -sv tests/e2e/singlecard/pooling/test_classification.py::test_classify_correctness
- name: Run e2e test
env:
@@ -91,9 +92,7 @@ jobs:
pytest -sv tests/e2e/singlecard/test_completion_with_prompt_embeds.py
pytest -sv tests/e2e/singlecard/test_aclgraph.py
pytest -sv tests/e2e/singlecard/test_aclgraph_mem.py
pytest -sv tests/e2e/singlecard/test_bge_model.py
pytest -sv tests/e2e/singlecard/test_camem.py
pytest -sv tests/e2e/singlecard/test_embedding.py
# pytest -sv tests/e2e/singlecard/test_embedding_aclgraph.py
pytest -sv tests/e2e/singlecard/test_guided_decoding.py
# torch 2.8 doesn't work with lora, fix me
@@ -104,6 +103,7 @@ jobs:
pytest -sv tests/e2e/singlecard/test_vlm.py
pytest -sv tests/e2e/singlecard/multi-modal/test_internvl.py
pytest -sv tests/e2e/singlecard/test_xlite.py
pytest -sv tests/e2e/singlecard/pooling/
# ------------------------------------ v1 spec decode test ------------------------------------ #
pytest -sv tests/e2e/singlecard/spec_decode_v1/test_v1_mtp_correctness.py