[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:
xaguilar-amd
2026-04-10 11:27:35 +00:00
committed by GitHub
parent d468322dc1
commit f976e3b98b
@@ -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,