ggml: Make fattn kernel use launch bounds w/HIP

Author: bjj

ggml/src/ggml-cuda/fattn-wmma-f16.cu

@@ -19,9 +19,7 @@ namespace wmma = rocwmma;
 
 // D == head size, VKQ_stride == num VKQ rows calculated in parallel:
 template<int D, int ncols, int nwarps, int VKQ_stride, int parallel_blocks, typename KQ_acc_t, bool use_logit_softcap>
-#if !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
 __launch_bounds__(nwarps*ggml_cuda_get_physical_warp_size(), 1)
-#endif // !(defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__))
 static __global__ void flash_attn_ext_f16(
         const char * __restrict__ Q,
         const char * __restrict__ K,