[Chore] Remove Sampler from Model Code (#17084)

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

vllm/model_executor/models/gemma2.py

@@ -34,7 +34,6 @@ from vllm.model_executor.layers.linear import (MergedColumnParallelLinear,
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
 from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.rotary_embedding import get_rope
-from vllm.model_executor.layers.sampler import SamplerOutput, get_sampler
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     VocabParallelEmbedding)
 from vllm.model_executor.model_loader.weight_utils import (
@@ -388,7 +387,6 @@ class Gemma2ForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
                                  prefix=maybe_prefix(prefix, "model"))
         self.logits_processor = LogitsProcessor(
             config.vocab_size, soft_cap=config.final_logit_softcapping)
-        self.sampler = get_sampler()
         self.make_empty_intermediate_tensors = (
             self.model.make_empty_intermediate_tensors)
 
@@ -415,14 +413,6 @@ class Gemma2ForCausalLM(nn.Module, SupportsLoRA, SupportsPP):
                                        sampling_metadata)
         return logits
 
-    def sample(
-        self,
-        logits: torch.Tensor,
-        sampling_metadata: SamplingMetadata,
-    ) -> Optional[SamplerOutput]:
-        next_tokens = self.sampler(logits, sampling_metadata)
-        return next_tokens
-
     def load_weights(self, weights: Iterable[Tuple[str,
                                                    torch.Tensor]]) -> Set[str]:
         loader = AutoWeightsLoader(