[Kernel][Model] logits_soft_cap for Gemma2 with flashinfer

vllm/model_executor/models/gemma2.py

@@ -37,7 +37,8 @@
     VocabParallelEmbedding)
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader
 from vllm.model_executor.sampling_metadata import SamplingMetadata
-from vllm.sequence import SamplerOutput
+from vllm.sequence import IntermediateTensors, SamplerOutput
+
 
 from .interfaces import SupportsLoRA