diff --git a/python/sglang/multimodal_gen/runtime/layers/attention/backends/aiter.py b/python/sglang/multimodal_gen/runtime/layers/attention/backends/aiter.py index f897214b7..9606c4849 100755 --- a/python/sglang/multimodal_gen/runtime/layers/attention/backends/aiter.py +++ b/python/sglang/multimodal_gen/runtime/layers/attention/backends/aiter.py @@ -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