metal : support I32 -> I32 copy (llama/17317)

diff --git a/ggml/src/ggml-metal/ggml-metal-device.m b/ggml/src/ggml-metal/ggml-metal-device.m
index e073d7af160981205710a4c6cc0cf8604ee451e6..acf9dfd5fc12c550dedfc5cef5acd514b4f6d956 100644 (file)
--- a/ggml/src/ggml-metal/ggml-metal-device.m
+++ b/ggml/src/ggml-metal/ggml-metal-device.m
@@ -989,7 +989,7 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te
                                 return false;
                         }
                     case GGML_TYPE_I32:
-                        return op->type == GGML_TYPE_F32;
+                        return op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_I32;
                     default:
                         return false;
                 };

diff --git a/ggml/src/ggml-metal/ggml-metal.metal b/ggml/src/ggml-metal/ggml-metal.metal
index cdf270d4e99f8d18a93954ac060bad41efee47d2..59e5761704e685dee81e404d3fb5c9e78e8eb8f2 100644 (file)
--- a/ggml/src/ggml-metal/ggml-metal.metal
+++ b/ggml/src/ggml-metal/ggml-metal.metal
@@ -6560,6 +6560,7 @@ template [[host_name("kernel_cpy_f32_f32")]]   kernel kernel_cpy_t kernel_cpy_t_
 template [[host_name("kernel_cpy_f32_f16")]]   kernel kernel_cpy_t kernel_cpy_t_t<float,   half>;
 template [[host_name("kernel_cpy_f32_i32")]]   kernel kernel_cpy_t kernel_cpy_t_t<float,   int32_t>;
 template [[host_name("kernel_cpy_i32_f32")]]   kernel kernel_cpy_t kernel_cpy_t_t<int32_t, float>;
+template [[host_name("kernel_cpy_i32_i32")]]   kernel kernel_cpy_t kernel_cpy_t_t<int32_t, int32_t>;
 #if defined(GGML_METAL_HAS_BF16)
 template [[host_name("kernel_cpy_f32_bf16")]]  kernel kernel_cpy_t kernel_cpy_t_t<float,   bfloat>;
 #endif