HIP: fix RDNA3 FP16/BF16 matrix multiplication (#17817)

2025-12-06 13:45:36 +01:00
parent a28e3c7567
commit f334b79494
1 changed files with 2 additions and 2 deletions
@@ -160,9 +160,9 @@ bool ggml_cuda_should_use_mmf(enum ggml_type type, int cc, int warp_size, const
        case GGML_TYPE_F32:
            return ampere_mma_available(cc);
        case GGML_TYPE_F16:
-            return volta_mma_available(cc) || turing_mma_available(cc) || amd_wmma_available(cc);
+            return volta_mma_available(cc) || turing_mma_available(cc) || (amd_wmma_available(cc) && GGML_CUDA_CC_IS_RDNA4(cc));
        case GGML_TYPE_BF16:
-            return ampere_mma_available(cc) || amd_wmma_available(cc);
+            return ampere_mma_available(cc) || (amd_wmma_available(cc) && GGML_CUDA_CC_IS_RDNA4(cc));
        default:
            return false;
    }