[Misc] Fix import (#20233)

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

vllm/v1/worker/gpu_model_runner.py

@@ -45,7 +45,7 @@ from vllm.sequence import IntermediateTensors
 from vllm.utils import (STR_DTYPE_TO_TORCH_DTYPE, DeviceMemoryProfiler,
                         GiB_bytes, LazyLoader, async_tensor_h2d, cdiv,
                         check_use_alibi, get_dtype_size,
-                        is_pin_memory_available)
+                        is_pin_memory_available, round_up)
 from vllm.v1.attention.backends.mamba_attn import Mamba2AttentionBackend
 from vllm.v1.attention.backends.utils import (AttentionMetadataBuilder,
                                               CommonAttentionMetadata)
@@ -1308,7 +1308,6 @@ class GPUModelRunner(LoRAModelRunnerMixin):
             tp_size = self.vllm_config.parallel_config.tensor_parallel_size
             if self.compilation_config.pass_config. \
                 enable_sequence_parallelism and tp_size > 1:
-                from vllm.utils import round_up
                 num_input_tokens = round_up(num_scheduled_tokens, tp_size)
             else:
                 num_input_tokens = num_scheduled_tokens