[V0 Deprecation] Remove V0 sampling metadata (#25345)
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
This commit is contained in:
@@ -21,7 +21,6 @@ from vllm.attention.layer import check_upstream_fa_availability
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.distributed import get_tensor_model_parallel_world_size
|
||||
from vllm.logger import init_logger
|
||||
from vllm.model_executor import SamplingMetadata
|
||||
from vllm.model_executor.layers.linear import (ColumnParallelLinear,
|
||||
QKVParallelLinear,
|
||||
RowParallelLinear)
|
||||
@@ -1556,10 +1555,8 @@ class BaseKeyeModule(nn.Module):
|
||||
def compute_logits(
|
||||
self,
|
||||
hidden_states: torch.Tensor,
|
||||
sampling_metadata: SamplingMetadata,
|
||||
) -> Optional[torch.Tensor]:
|
||||
return self.language_model.compute_logits(hidden_states,
|
||||
sampling_metadata)
|
||||
return self.language_model.compute_logits(hidden_states)
|
||||
|
||||
def load_weights(self, weights: Iterable[tuple[str,
|
||||
torch.Tensor]]) -> set[str]:
|
||||
|
||||
Reference in New Issue
Block a user