xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-05-17 21:21:22 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix lint (#3388)

Browse Source
This commit is contained in:
Antoni Baum 2024-03-13 13:56:49 -07:00 committed by GitHub
parent 7e9bd08f60
commit c33afd89f5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/model_executor/layers/rotary_embedding.py
View File

@ -143,8 +143,8 @@ class RotaryEmbedding(nn.Module):
offsets: Optional[torch.Tensor] = None, offsets: Optional[torch.Tensor] = None,
) -> Tuple[torch.Tensor, torch.Tensor]: ) -> Tuple[torch.Tensor, torch.Tensor]:
self.cos_sin_cache = self.cos_sin_cache.to(positions.get_device()) self.cos_sin_cache = self.cos_sin_cache.to(positions.get_device())
# ops.rotary_embedding()/batched_rotary_embedding() are in-place operations that # ops.rotary_embedding()/batched_rotary_embedding()
# update the query and key tensors. # are in-place operations that update the query and key tensors.
if offsets is not None: if offsets is not None:
ops.batched_rotary_embedding(positions, query, key, self.head_size, ops.batched_rotary_embedding(positions, query, key, self.head_size,
self.cos_sin_cache, self.cos_sin_cache,