[V0 Deprecation] Remove V0 sampling metadata (#25345)

Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>

vllm/model_executor/models/deepseek_mtp.py

@@ -15,7 +15,6 @@ from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.vocab_parallel_embedding import (
     ParallelLMHead, VocabParallelEmbedding)
 from vllm.model_executor.model_loader.weight_utils import default_weight_loader
-from vllm.model_executor.sampling_metadata import SamplingMetadata
 from vllm.sequence import IntermediateTensors
 
 from .deepseek_v2 import (DeepseekV2DecoderLayer,
@@ -124,15 +123,13 @@ class DeepSeekMultiTokenPredictor(nn.Module):
     def compute_logits(
         self,
         hidden_states: torch.Tensor,
-        sampling_metadata: SamplingMetadata,
         spec_step_idx: int = 0,
     ) -> torch.Tensor:
         current_step_idx = (spec_step_idx % self.num_mtp_layers)
         mtp_layer = self.layers[str(self.mtp_start_layer_idx +
                                     current_step_idx)]
         logits = self.logits_processor(mtp_layer.shared_head.head,
-                                       mtp_layer.shared_head(hidden_states),
-                                       sampling_metadata)
+                                       mtp_layer.shared_head(hidden_states))
         return logits
 
 
@@ -161,11 +158,9 @@ class DeepSeekMTP(nn.Module, SupportsPP):
     def compute_logits(
         self,
         hidden_states: torch.Tensor,
-        sampling_metadata: SamplingMetadata,
         spec_step_idx: int = 0,
     ) -> Optional[torch.Tensor]:
-        return self.model.compute_logits(hidden_states, sampling_metadata,
-                                         spec_step_idx)
+        return self.model.compute_logits(hidden_states, spec_step_idx)
 
     def load_weights(self, weights: Iterable[tuple[str,
                                                    torch.Tensor]]) -> set[str]: