HIP: Disable ROCWMMA fattn on CDNA when compiled against ROCWMMA 2.0.0 (#16221)

* HIP: Disable ROCWMMA fatt on CDNA when compiled against ROCWMMA 2.0.0

rocwmma 2.0.0 includes a bug in the code fakeing fp16 accumulation on CDNA

* CUDA: Fix volta condition in ggml_cuda_should_use_wmma_fattn

ggml/src/ggml-cuda/fattn-tile.cu

@@ -1,6 +1,7 @@
 #include "common.cuh"
 #include "fattn-common.cuh"
 #include "fattn-tile.cuh"
+#include "fattn-wmma-f16.cuh"
 
 // kq_stride == number of KQ rows to process per iteration
 // kq_nbatch == number of K columns to load in parallel for KQ calculation
@@ -190,10 +191,10 @@ static __global__ void flash_attn_tile(
 #ifdef FLASH_ATTN_AVAILABLE
 
     // Skip unused kernel variants for faster compilation:
-#ifdef FP16_MMA_AVAILABLE
+#ifdef GGML_USE_WMMA_FATTN
     NO_DEVICE_CODE;
     return;
-#endif // FP16_MMA_AVAILABLE
+#endif // GGML_USE_WMMA_FATTN
 
     if (use_logit_softcap && !(D == 128 || D == 256)) {
         GGML_UNUSED_VARS(Q, K, V, mask, sinks, KV_max, dst, dst_meta, scale,