fix ruff

Author: RalphMao

examples/vllm_serve/vllm_serve_fakequant.py

@@ -57,9 +57,6 @@
 import uvloop
 from tqdm import tqdm
 from transformers import AutoTokenizer
-
-import modelopt.torch.quantization as mtq
-from modelopt.torch.utils.dataset_utils import get_dataset_dataloader
 from vllm.distributed.parallel_state import get_pp_group, get_tp_group
 from vllm.entrypoints.openai.api_server import run_server
 from vllm.entrypoints.openai.cli_args import make_arg_parser
@@ -71,6 +68,9 @@
 # from vllm.v1.worker.gpu_model_runner import GPUModelRunner
 from vllm.v1.worker.gpu_worker import Worker
 
+import modelopt.torch.quantization as mtq
+from modelopt.torch.utils.dataset_utils import get_dataset_dataloader
+
 
 @contextmanager
 def disable_compilation(model):

modelopt/torch/quantization/plugins/vllm.py

@@ -18,7 +18,6 @@
 import importlib
 
 import torch
-
 import vllm.model_executor.layers.fused_moe.layer as vllm_fused_moe_layer
 import vllm.model_executor.layers.linear as vllm_linear