From bd3f1d9d65113737e795cd6d62eb66f90628663c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20G=C3=A4=C3=9Fler?= <johannesg@5d6.de>
Date: Sun, 22 Mar 2026 17:53:33 +0100
Subject: [PATCH] CUDA: fix BF16 FA compilation (#20865)

---
 ggml/src/ggml-cuda/convert.cuh | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/ggml/src/ggml-cuda/convert.cuh b/ggml/src/ggml-cuda/convert.cuh
index b8caeacf09..f5d37c7b99 100644
--- a/ggml/src/ggml-cuda/convert.cuh
+++ b/ggml/src/ggml-cuda/convert.cuh
@@ -42,11 +42,15 @@ template<typename dst_t, typename src_t>
     } else if constexpr(std::is_same_v<src_t, float2> && std::is_same_v<dst_t, half2>) {
         return __float22half2_rn(x);
     } else if constexpr(std::is_same_v<src_t, nv_bfloat162> && std::is_same_v<dst_t, float2>) {
-#if !defined(GGML_USE_HIP) && defined(__CUDA_ARCH__) && __CUDA_ARCH__ >= 800
+#ifdef GGML_USE_HIP
+        return make_float2(__bfloat162float(__low2bfloat16(x)), __bfloat162float(__high2bfloat16(x)));
+#else
+#if __CUDA_ARCH__ >= 800
         return __bfloat1622float2(x);
 #else
-        return make_float2(__bfloat162float(__low2bfloat16(x)), __bfloat162float(__high2bfloat16(x)));
-#endif // !defined(GGML_USE_HIP) && defined(__CUDA_ARCH__) && __CUDA_ARCH__ >= 800
+        return make_float2(__bfloat162float(x.x), __bfloat162float(x.y));
+#endif // __CUDA_ARCH__ >= 800
+#endif // GGML_USE_HIP
     } else if constexpr(std::is_same_v<src_t, float2> && std::is_same_v<dst_t, nv_bfloat162>) {
         // bypass compile error on cuda 12.0.1
 #ifdef GGML_USE_HIP