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

7
vllm/model_executor/model_loader/utils.py
View File

@@ -21,8 +21,7 @@ from vllm.model_executor.layers.linear import QKVCrossParallelLinear
from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig, QuantizeMethodBase)
from vllm.model_executor.models import ModelRegistry
from vllm.model_executor.models.adapters import (as_classification_model,
as_embedding_model,
from vllm.model_executor.models.adapters import (as_embedding_model,
as_reward_model)
from vllm.model_executor.models.interfaces import SupportsQuant
from vllm.utils import is_pin_memory_available
@@ -246,7 +245,9 @@ def get_model_architecture(
if model_config.task == "embed":
model_cls = as_embedding_model(model_cls)
elif model_config.task == "classify":
model_cls = as_classification_model(model_cls)
# Cannot automatically run as_seq_cls_model,
# otherwise it will cause a circular reference on is_cross_encoder_model
pass
elif model_config.task == "reward":
model_cls = as_reward_model(model_cls)