metal : fix mul-mm condition + fix mul-mv permuted kernels (#16494)

2025-10-11 16:54:10 +03:00
parent 4a8fbe0a5e
commit a3cb04744f
3 changed files with 44 additions and 35 deletions
--- a/src/llama-model.cpp
+++ b/src/llama-model.cpp
@@ -16313,10 +16313,10 @@ struct llm_build_granite_hybrid : public llm_graph_context_mamba {
    }

    ggml_tensor * build_layer_ffn(
-              ggml_tensor       * cur,
-              ggml_tensor       * inpSA,
-        const llama_model       & model,
-        const int                 il) {
+              ggml_tensor * cur,
+              ggml_tensor * inpSA,
+        const llama_model & model,
+        const int           il) {

        // For Granite architectures - scale residual
        if (hparams.f_residual_scale) {