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

[Model][2/N] Automatic conversion of CrossEncoding model (#19978)

Browse Source 
Signed-off-by: wang.yuqi <noooop@126.com>
This commit is contained in:
wang.yuqi
2025-07-03 21:59:23 +08:00
committed by GitHub
parent 1819fbda63
commit 6f1229f91d
16 changed files with 199 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
tests/models/test_registry.py
View File

@@ -9,9 +9,9 @@ import torch.cuda
from vllm.model_executor.models import (is_pooling_model,
is_text_generation_model,
supports_multimodal)
from vllm.model_executor.models.adapters import (as_classification_model,
as_embedding_model,
as_reward_model)
from vllm.model_executor.models.adapters import (as_embedding_model,
as_reward_model,
as_seq_cls_model)
from vllm.model_executor.models.registry import (_MULTIMODAL_MODELS,
_SPECULATIVE_DECODING_MODELS,
_TEXT_GENERATION_MODELS,
@@ -38,7 +38,7 @@ def test_registry_imports(model_arch):
assert is_text_generation_model(model_cls)
# All vLLM models should be convertible to a pooling model
assert is_pooling_model(as_classification_model(model_cls))
assert is_pooling_model(as_seq_cls_model(model_cls))
assert is_pooling_model(as_embedding_model(model_cls))
assert is_pooling_model(as_reward_model(model_cls))