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

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

vllm/model_executor/models/internlm2.py

@@ -23,7 +23,6 @@ from vllm.model_executor.layers.logits_processor import LogitsProcessor
 from vllm.model_executor.layers.pooler import Pooler, PoolingType
 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 (
     ParallelLMHead, VocabParallelEmbedding)
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader
@@ -336,7 +335,6 @@ class InternLM2ForCausalLM(nn.Module, SupportsPP, SupportsLoRA):
         if self.config.tie_word_embeddings:
             self.output.weight = self.model.tok_embeddings.weight
         self.logits_processor = LogitsProcessor(config.vocab_size)
-        self.sampler = get_sampler()
         self.make_empty_intermediate_tensors = (
             self.model.make_empty_intermediate_tensors)
 
@@ -363,14 +361,6 @@ class InternLM2ForCausalLM(nn.Module, SupportsPP, SupportsLoRA):
                                        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]:
         stacked_params_mapping = [
@@ -423,7 +413,7 @@ class InternLM2ForRewardModel(InternLM2ForCausalLM):
                          prefix=prefix,
                          model_type=model_type)
 
-        for attr in ("output", "logits_processor", "sampler"):
+        for attr in ("output", "logits_processor"):
             delattr(self, attr)
 
         config = vllm_config.model_config.hf_config