Fix linting -part 2

Signed-off-by: Flavia Beo <[email protected]>

vllm/config.py

@@ -9,15 +9,15 @@
 import vllm.envs as envs
 from transformers import PretrainedConfig
 from vllm.logger import init_logger
-from vllm.model_executor.layers.pooler import PoolingConfig # noqa: F401
+from vllm.model_executor.layers.pooler import PoolingConfig  # noqa: F401
 from vllm.model_executor.layers.quantization import QUANTIZATION_METHODS
 from vllm.model_executor.models import ModelRegistry
 from vllm.platforms import current_platform
 from vllm.tracing import is_otel_available, otel_import_error_traceback
+from vllm.transformers_utils.config import get_pooling_config  # noqa: F401
 from vllm.transformers_utils.config import (ConfigFormat, get_config,
                                             get_hf_image_processor_config,
-                                            get_hf_text_config,
-                                            get_pooling_config) # noqa: F401
+                                            get_hf_text_config)
 from vllm.utils import (GiB_bytes, cuda_device_count_stateless, get_cpu_memory,
                         is_hip, is_openvino, is_xpu, print_warning_once)
 

vllm/model_executor/model_loader/loader.py

@@ -28,7 +28,7 @@
                               get_tensor_model_parallel_world_size)
 from vllm.envs import VLLM_USE_MODELSCOPE
 from vllm.logger import init_logger
-from vllm.model_executor.layers.pooler import PoolingConfig # noqa: F401
+from vllm.model_executor.layers.pooler import PoolingConfig  # noqa: F401
 from vllm.model_executor.layers.quantization.base_config import (
     QuantizationConfig)
 from vllm.model_executor.model_loader.tensorizer import (

vllm/model_executor/models/bert.py

@@ -12,7 +12,8 @@
 from vllm.model_executor.layers.linear import (ColumnParallelLinear,
                                                QKVParallelLinear,
                                                RowParallelLinear)
-from vllm.model_executor.layers.pooler import Pooler, PoolingConfig # noqa: F401
+from vllm.model_executor.layers.pooler import (Pooler,  # noqa: F401
+                                               PoolingConfig)
 from vllm.model_executor.layers.quantization.base_config import (
     QuantizationConfig)
 from vllm.model_executor.layers.vocab_parallel_embedding import (