format

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

Author: LucasWilkinson

vllm/v1/worker/gpu_model_runner.py

@@ -41,8 +41,7 @@
 from vllm.sampling_params import SamplingType
 from vllm.sequence import IntermediateTensors
 from vllm.utils import (STR_DTYPE_TO_TORCH_DTYPE, DeviceMemoryProfiler,
-                        GiB_bytes, LazyLoader,
-                        check_use_alibi, get_dtype_size,
+                        GiB_bytes, LazyLoader, check_use_alibi, get_dtype_size,
                         is_pin_memory_available, round_up)
 from vllm.v1.attention.backends.mamba_attn import Mamba2AttentionBackend
 from vllm.v1.attention.backends.utils import (AttentionMetadataBuilder,