diff --git a/ggml/src/ggml-cuda.cu b/ggml/src/ggml-cuda.cu
index 6ddbce80e..94004b3c1 100644
--- a/ggml/src/ggml-cuda.cu
+++ b/ggml/src/ggml-cuda.cu
@@ -2785,6 +2785,12 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
                 if (op->op == GGML_OP_MUL_MAT && a->ne[3] != b->ne[3]) {
                     return false;
                 }
+#ifdef GGML_USE_MUSA
+                if (b->type == GGML_TYPE_F16 && b->ne[2]*b->ne[3] > 1 &&
+                    !ggml_is_transposed(a) && !ggml_is_transposed(b)) {
+                    return false;
+                }
+#endif // GGML_USE_MUSA
                 switch (a->type) {
                     case GGML_TYPE_F32:
                     case GGML_TYPE_F16:
@@ -2808,6 +2814,11 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
                     case GGML_TYPE_IQ3_XXS:
                     case GGML_TYPE_IQ4_NL:
                     case GGML_TYPE_IQ4_XS:
+#ifdef GGML_USE_MUSA
+                        if (a->type == GGML_TYPE_Q3_K) {
+                            return false;
+                        }
+#endif // GGML_USE_MUSA
                         return true;
                     default:
                         return false;
@@ -2924,6 +2935,9 @@ GGML_CALL static bool ggml_backend_cuda_supports_op(ggml_backend_t backend, cons
         case GGML_OP_LEAKY_RELU:
             return true;
         case GGML_OP_FLASH_ATTN_EXT:
+#ifndef FLASH_ATTN_AVAILABLE
+            return false;
+#endif
 #if defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)
             return (op->src[0]->ne[0] == 64 && op->src[1]->type == GGML_TYPE_F16) || op->src[0]->ne[0] == 128;
 #else
diff --git a/ggml/src/ggml-cuda/common.cuh b/ggml/src/ggml-cuda/common.cuh
index eb39b6d23..6b437d378 100644
--- a/ggml/src/ggml-cuda/common.cuh
+++ b/ggml/src/ggml-cuda/common.cuh
@@ -50,6 +50,8 @@
 #define CC_RDNA1      (CC_OFFSET_AMD + 1010)
 #define CC_RDNA2      (CC_OFFSET_AMD + 1030)
 #define CC_RDNA3      (CC_OFFSET_AMD + 1100)
+#define CC_QY1        210
+#define CC_QY2        220
 
 #define MATRIX_ROW_PADDING 512 // last row of quant. matrices is a multiple of this to avoid out-of-bounds memory accesses
 
@@ -134,6 +136,10 @@ typedef float2 dfloat2;
 #define INT8_MMA_AVAILABLE
 #endif // !(defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__)) && __CUDA_ARCH__ >= CC_TURING
 
+#if !(defined(GGML_USE_MUSA) && __MUSA_ARCH__ <= CC_QY1)
+#define FLASH_ATTN_AVAILABLE
+#endif // !(defined(GGML_USE_MUSA) && __MUSA_ARCH__ <= CC_QY1)
+
 static constexpr bool fast_fp16_available(const int cc) {
     return cc >= CC_PASCAL && cc != 610;
 }
diff --git a/ggml/src/ggml-cuda/fattn-tile-f32.cu b/ggml/src/ggml-cuda/fattn-tile-f32.cu
index 827437ca0..f402195ce 100644
--- a/ggml/src/ggml-cuda/fattn-tile-f32.cu
+++ b/ggml/src/ggml-cuda/fattn-tile-f32.cu
@@ -44,13 +44,17 @@ static __global__ void flash_attn_tile_ext_f32(
         const int ne1,
         const int ne2,
         const int ne3) {
+#ifndef FLASH_ATTN_AVAILABLE
+    NO_DEVICE_CODE;
+    return;
+#endif // FLASH_ATTN_AVAILABLE
     // Skip unused kernel variants for faster compilation:
     if (use_logit_softcap && !(D == 128 || D == 256)) {
         NO_DEVICE_CODE;
         return;
     }
 
-    //In this kernel Q, K, V are matrices while i, j, k are matrix indices.
+    // In this kernel Q, K, V are matrices while i, j, k are matrix indices.
 
     const int ic0 = (blockIdx.x / parallel_blocks) * ncols; // Index of the Q/QKV column to work on.
     const int ip  =  blockIdx.x % parallel_blocks; // Index in group of blocks running for the same column in parallel.