diff --git a/ggml/src/ggml-cuda/common.cuh b/ggml/src/ggml-cuda/common.cuh index 26d9412a2..1c2e00c1e 100644 --- a/ggml/src/ggml-cuda/common.cuh +++ b/ggml/src/ggml-cuda/common.cuh @@ -459,7 +459,7 @@ static __device__ __forceinline__ uint32_t __hgt2_mask(const half2 a, const half static __device__ __forceinline__ int ggml_cuda_dp4a(const int a, const int b, int c) { #if defined(GGML_USE_HIPBLAS) && defined(__HIP_PLATFORM_AMD__) -#if defined(__gfx906__) || defined(__gfx908__) || defined(__gfx90a__) || defined(__gfx1030__) +#if defined(__gfx906__) || defined(__gfx908__) || defined(__gfx90a__) || defined(RDNA2) c = __builtin_amdgcn_sdot4(a, b, c, false); #elif defined(RDNA3) c = __builtin_amdgcn_sudot4( true, a, true, b, c, false);