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

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

vllm/model_executor/models/aria.py

@@ -15,11 +15,10 @@ from vllm.model_executor.layers.fused_moe import FusedMoE
 from vllm.model_executor.layers.linear import (ColumnParallelLinear,
                                                RowParallelLinear)
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
-from vllm.model_executor.layers.sampler import (SamplerOutput,
-                                                SamplingMetadata, get_sampler)
 from vllm.model_executor.layers.vocab_parallel_embedding import ParallelLMHead
 from vllm.model_executor.model_loader.weight_utils import (
     default_weight_loader, maybe_remap_kv_scale_name)
+from vllm.model_executor.sampling_metadata import SamplingMetadata
 from vllm.multimodal import MULTIMODAL_REGISTRY
 from vllm.multimodal.inputs import (MultiModalDataDict, MultiModalFieldConfig,
                                     MultiModalKwargs)
@@ -527,7 +526,6 @@ class AriaForConditionalGeneration(nn.Module, SupportsMultiModal):
         logit_scale = getattr(config, "logit_scale", 1.0)
         self.logits_processor = LogitsProcessor(self.unpadded_vocab_size,
                                                 self.vocab_size, logit_scale)
-        self.sampler = get_sampler()
 
     def _validate_image_sizes(
             self, images: List[torch.Tensor]) -> List[torch.Tensor]:
@@ -653,14 +651,6 @@ class AriaForConditionalGeneration(nn.Module, SupportsMultiModal):
                                        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]]):
         loader = AutoWeightsLoader(self)
         loader.load_weights(weights, mapper=self.hf_to_vllm_mapper)