Removed unused methods

Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>

Author: alex-jw-brooks

vllm/model_executor/models/granite_speech.py

@@ -34,7 +34,7 @@
 from vllm.model_executor.layers.linear import (ColumnParallelLinear,
                                                RowParallelLinear)
 from vllm.model_executor.layers.quantization import QuantizationConfig
-from vllm.model_executor.layers.sampler import SamplerOutput, get_sampler
+from vllm.model_executor.layers.sampler import get_sampler
 from vllm.model_executor.models.module_mapping import MultiModelKeys
 from vllm.model_executor.sampling_metadata import SamplingMetadata
 from vllm.multimodal import MULTIMODAL_REGISTRY
@@ -73,13 +73,6 @@ class GraniteSpeechMultiModalProcessingInfo(BaseProcessingInfo):
     def get_supported_mm_limits(self) -> Mapping[str, Optional[int]]:
         return {"audio": 1}
 
-    def get_mm_max_tokens_per_item(
-        self,
-        seq_len: int,
-        mm_counts: Mapping[str, int],
-    ) -> Mapping[str, int]:
-        return {"audio": self.get_max_audio_tokens()}
-
     # There is no limit to the maximum number of audio tokens that can be
     # encoded as features; we pick ~5000 as a number that is probably higher
     # than we would expect to encounter. The sequence of length
@@ -768,13 +761,6 @@ def compute_logits(
             sampling_metadata,
         )
 
-    def sample(
-        self,
-        logits: torch.Tensor,
-        sampling_metadata: SamplingMetadata,
-    ) -> Optional[SamplerOutput]:
-        return self.language_model.sample(logits, sampling_metadata)
-
     def load_weights(
         self,
         weights: Iterable[Tuple[str, torch.Tensor]],