[Rebase] Rebase to vllm 0.12.0 (#335)

Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Rein Yang <ruiruyang2@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

vllm_omni/diffusion/model_loader/diffusers_loader.py

@@ -13,7 +13,6 @@ from torch import nn
 from vllm.config import ModelConfig
 from vllm.config.load import LoadConfig
 from vllm.logger import init_logger
-from vllm.model_executor.model_loader.utils import set_default_torch_dtype
 from vllm.model_executor.model_loader.weight_utils import (
     download_safetensors_index_file_from_hf,
     download_weights_from_hf,
@@ -22,6 +21,7 @@ from vllm.model_executor.model_loader.weight_utils import (
     maybe_download_from_modelscope,
     safetensors_weights_iterator,
 )
+from vllm.utils.torch_utils import set_default_torch_dtype
 
 from vllm_omni.diffusion.data import OmniDiffusionConfig
 from vllm_omni.diffusion.registry import initialize_model