Skip to content

GitLab

Unverified Commit 71baf85a authored by Ning Xie's avatar Ning Xie Committed by GitHub
Browse files

[Kernel] mark TorchSDPABackend swap_blocks NotImplementedError (#19749)

parent 79f2f1c2
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/attention/backends/torch_sdpa.py
View file @ 71baf85a
...@@ -65,7 +65,7 @@ class TorchSDPABackend(AttentionBackend): ...@@ -65,7 +65,7 @@ class TorchSDPABackend(AttentionBackend):
dst_kv_cache: torch.Tensor, dst_kv_cache: torch.Tensor,
src_to_dst: torch.Tensor, src_to_dst: torch.Tensor,
) -> None: ) -> None:
PagedAttention.swap_blocks(src_kv_cache, dst_kv_cache, src_to_dst) raise NotImplementedError("Swap is not supported in TorchSDPABackend.")
@staticmethod @staticmethod
def copy_blocks( def copy_blocks(
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment