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

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

vllm/model_executor/models/idefics3.py

@@ -28,7 +28,6 @@ from vllm.config import VllmConfig
 from vllm.model_executor.layers.linear import ReplicatedLinear
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
 from vllm.model_executor.layers.quantization import QuantizationConfig
-from vllm.model_executor.layers.sampler import SamplerOutput, get_sampler
 from vllm.model_executor.layers.vocab_parallel_embedding import ParallelLMHead
 from vllm.model_executor.models.module_mapping import MultiModelKeys
 from vllm.model_executor.sampling_metadata import SamplingMetadata
@@ -603,7 +602,6 @@ class Idefics3ForConditionalGeneration(nn.Module, SupportsMultiModal,
         if self.config.text_config.tie_word_embeddings:
             self.lm_head.weight = self.model.text_model.wte.weight
         self.logits_processor = LogitsProcessor(config.text_config.vocab_size)
-        self.sampler = get_sampler()
 
     def _validate_pixel_values(self, data: torch.Tensor) -> torch.Tensor:
         h = w = self.config.vision_config.image_size
@@ -754,14 +752,6 @@ class Idefics3ForConditionalGeneration(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]]) -> Set[str]:
         loader = AutoWeightsLoader(self)