[Model] Remove model sampler (#21059)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

vllm/model_executor/models/mimo_mtp.py

@@ -30,7 +30,6 @@ from vllm.config import CacheConfig, ModelConfig, VllmConfig
 from vllm.model_executor.layers.layernorm import RMSNorm
 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, VocabParallelEmbedding)
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader
@@ -161,8 +160,6 @@ class MiMoMTP(nn.Module):
         self.lm_head = ParallelLMHead(self.config.vocab_size,
                                       self.config.hidden_size)
 
-        self.sampler = get_sampler()
-
     def forward(
         self,
         input_ids: torch.Tensor,
@@ -187,14 +184,6 @@ class MiMoMTP(nn.Module):
         return self.model.compute_logits(hidden_states, self.lm_head,
                                          sampling_metadata, spec_step_idx)
 
-    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 = [