[V0 Deprecation] Remove V0 sampling metadata (#25345)
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
This commit is contained in:
@@ -41,7 +41,6 @@ from vllm.model_executor.layers.logits_processor import LogitsProcessor
|
||||
from vllm.model_executor.layers.quantization import QuantizationConfig
|
||||
from vllm.model_executor.layers.vocab_parallel_embedding import (
|
||||
ParallelLMHead, VocabParallelEmbedding)
|
||||
from vllm.model_executor.sampling_metadata import SamplingMetadata
|
||||
from vllm.multimodal import MULTIMODAL_REGISTRY, MultiModalKwargsItems
|
||||
from vllm.multimodal.inputs import (MultiModalDataDict, MultiModalFieldConfig,
|
||||
MultiModalInputs, MultiModalUUIDDict,
|
||||
@@ -798,10 +797,8 @@ class TransformersForCausalLM(TransformersBase):
|
||||
def compute_logits(
|
||||
self,
|
||||
hidden_states: torch.Tensor,
|
||||
sampling_metadata: SamplingMetadata,
|
||||
) -> Optional[torch.Tensor]:
|
||||
logits = self.logits_processor(self.lm_head, hidden_states,
|
||||
sampling_metadata)
|
||||
logits = self.logits_processor(self.lm_head, hidden_states)
|
||||
return logits
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user