[AMD] Don't request the unused softmax LSE in the AITER diffusion backend (#32926)

Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
Co-authored-by: YC Yen-Ching Tseng <yctseng@amd.com>
This commit is contained in:
sushil Dubey
2026-08-24 22:27:42 -07:00
committed by GitHub
co-authored by Claude Opus 5 YC Yen-Ching Tseng
parent 13d2ee8180
commit 2d6c12e2fd
@@ -204,14 +204,14 @@ class AITerImpl(AttentionImpl):
)
# BF16 path
output, _ = aiter.flash_attn_func(
output = aiter.flash_attn_func(
query,
key,
value,
dropout_p=self.dropout_p,
causal=self.causal,
return_attn_probs=False,
return_lse=True,
return_lse=False,
)
return output