[Performance] Remove unnecessary zero-fill of MLA decode output tensor in Aiter backend (#37539)
Signed-off-by: xaguilar-amd <xaguilar@amd.com>
This commit is contained in:
@@ -416,7 +416,7 @@ class AiterMLAImpl(MLACommonImpl[AiterMLAMetadata]):
|
||||
else:
|
||||
kernel_num_heads = self.num_heads
|
||||
|
||||
o = torch.zeros(
|
||||
o = torch.empty(
|
||||
B,
|
||||
kernel_num_heads,
|
||||
self.kv_lora_rank,
|
||||
|
||||
Reference in New Issue
Block a user