Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 7 additions & 6 deletions vllm/model_executor/model_loader/utils.py
Original file line number Diff line number Diff line change
Expand Up @@ -19,12 +19,7 @@
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

Expand Down Expand Up @@ -172,6 +167,12 @@ def device_loading_context(module: torch.nn.Module, target_device: torch.device)


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(
Expand Down
Loading