Fix cudnn routing

This commit is contained in:
Jagrit Digani
2025-08-06 15:05:58 -07:00
parent c66b76a8c8
commit 99d8de8445

View File

@@ -1068,8 +1068,7 @@ void ScaledDotProductAttention::eval_gpu(
flags);
}
// return sdpa_vector_fallback(s, encoder, q, k, v, scale_, o, do_causal_);
return sdpa_cudnn(s, encoder, q, k, v, scale_, o, do_causal_);
return sdpa_vector_fallback(s, encoder, q, k, v, scale_, o, do_causal_);
}
// Full attention mode