LLM inference in C/C++
C++ ggml
metal : add f16 type support to leaky relu (#25981)
Ilia Ilmerc588c4f47683
diff --git a/ggml/src/ggml-metal/ggml-metal-device.m b/ggml/src/ggml-metal/ggml-metal-device.mindex 80e47f2c2f..4edd77c6f2 100644--- a/ggml/src/ggml-metal/ggml-metal-device.m+++ b/ggml/src/ggml-metal/ggml-metal-device.m@@ -1218,8 +1218,9 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te(ggml_get_op_params_i32(op, 4) == 0) && (ggml_get_op_params_i32(op, 6) == 0);case GGML_OP_PAD_REFLECT_1D:case GGML_OP_TIMESTEP_EMBEDDING:- case GGML_OP_LEAKY_RELU:return op->src[0]->type == GGML_TYPE_F32;+ case GGML_OP_LEAKY_RELU:+ return op->src[0]->type == GGML_TYPE_F32 || op->src[0]->type == GGML_TYPE_F16;case GGML_OP_ARGSORT:case GGML_OP_TOP_K:case GGML_OP_ARANGE: