xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-23 16:14:37 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix: Resolve circular import in model_loader/utils.py (#29189)

Browse Source 
Signed-off-by: nandan2003 <nandan.vallamdasu@outlook.com>
Signed-off-by: Nandan Vallamdasu  <nandan.vallamdasu@outlook.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Nandan Vallamdasu 2025-11-22 18:28:22 +05:30 committed by GitHub
parent 5a4802588e
commit 6965a392a4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
vllm/model_executor/model_loader/utils.py
View File

@ -19,12 +19,7 @@ from vllm.model_executor.layers.quantization.base_config import (
QuantizationConfig,
QuantizeMethodBase,
)
from vllm.model_executor.models.adapters import (
as_embedding_model,
as_reward_model,
as_seq_cls_model,
try_create_mm_pooling_model_cls,
)
from vllm.model_executor.models.interfaces import SupportsQuant, supports_multimodal
from vllm.utils.platform_utils import is_pin_memory_available
@ -172,6 +167,12 @@ _MODEL_ARCH_BY_HASH = dict[int, tuple[type[nn.Module], str]]()
def _get_model_architecture(model_config: ModelConfig) -> tuple[type[nn.Module], str]:
from vllm.model_executor.models.adapters import (
as_embedding_model,
as_reward_model,
as_seq_cls_model,
try_create_mm_pooling_model_cls,
)
architectures = getattr(model_config.hf_config, "architectures", [])
model_cls, arch = model_config.registry.resolve_model_cls(