Skip to content

LLM inference in C/C++

C++ ggml

metal : check for BF16 support in concat kernel (#24747)

Georgi Gerganovcae0a3b0b074
diff --git a/ggml/src/ggml-metal/ggml-metal.metal b/ggml/src/ggml-metal/ggml-metal.metal
index 31b5326ec5..25e78e1008 100644
--- a/ggml/src/ggml-metal/ggml-metal.metal
+++ b/ggml/src/ggml-metal/ggml-metal.metal
@@ -7557,7 +7557,9 @@ typedef decltype(kernel_concat<float>) kernel_concat_t;
template [[host_name("kernel_concat_f32")]] kernel kernel_concat_t kernel_concat<float>;
template [[host_name("kernel_concat_f16")]] kernel kernel_concat_t kernel_concat<half>;
+#if defined(GGML_METAL_HAS_BF16)
template [[host_name("kernel_concat_bf16")]] kernel kernel_concat_t kernel_concat<bfloat>;
+#endif
template [[host_name("kernel_concat_i8")]] kernel kernel_concat_t kernel_concat<char>;
template [[host_name("kernel_concat_i16")]] kernel kernel_concat_t kernel_concat<short>;
template [[host_name("kernel_concat_i32")]] kernel kernel_concat_t kernel_concat<int>;