[Chore] Remove unused sampler in models (#25324)

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

vllm/model_executor/models/step3_text.py

@@ -26,7 +26,6 @@ from vllm.model_executor.layers.logits_processor import LogitsProcessor
 from vllm.model_executor.layers.quantization.base_config 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 (
     DEFAULT_VOCAB_PADDING_SIZE, ParallelLMHead, VocabParallelEmbedding)
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader
@@ -391,7 +390,6 @@ class Step3TextForCausalLM(nn.Module, SupportsPP):
             )
             self.logits_processor = LogitsProcessor(self.unpadded_vocab_size,
                                                     config.vocab_size)
-            self.sampler = get_sampler()
         else:
             self.lm_head = PPMissingLayer()
 
@@ -413,14 +411,6 @@ class Step3TextForCausalLM(nn.Module, SupportsPP):
                                        sampling_metadata)
         return logits
 
-    def sample(
-        self,
-        logits: Optional[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]:
         qkv_params_mapping = [