Revert PR 4764 & 4813 related to R1 RoPE (#4959)
This commit is contained in:
@@ -651,18 +651,6 @@ class DeepseekScalingRotaryEmbedding(RotaryEmbedding):
|
||||
query: torch.Tensor,
|
||||
key: torch.Tensor,
|
||||
offsets: Optional[torch.Tensor] = None,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
if _is_cuda_available:
|
||||
return self.forward_cuda(positions, query, key, offsets)
|
||||
else:
|
||||
return self.forward_native(positions, query, key, offsets)
|
||||
|
||||
def forward_native(
|
||||
self,
|
||||
positions: torch.Tensor,
|
||||
query: torch.Tensor,
|
||||
key: torch.Tensor,
|
||||
offsets: Optional[torch.Tensor] = None,
|
||||
) -> Tuple[torch.Tensor, torch.Tensor]:
|
||||
"""PyTorch-native implementation equivalent to forward()."""
|
||||
query_rot = query[..., : self.rotary_dim]
|
||||
|
||||
Reference in New Issue
Block a user