[V0 deprecation] Remove _VLLM_V1 suffixes from attention backend names (#25489)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com> Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
This commit is contained in:
@@ -155,7 +155,7 @@ class TritonAttentionBackend(AttentionBackend):
|
||||
|
||||
@staticmethod
|
||||
def get_name() -> str:
|
||||
return "TRITON_ATTN_VLLM_V1"
|
||||
return "TRITON_ATTN"
|
||||
|
||||
@staticmethod
|
||||
def get_impl_cls() -> type["TritonAttentionImpl"]:
|
||||
|
||||
Reference in New Issue
Block a user