From 850320be8b66eacb3ee3c205335c06586f142d3d Mon Sep 17 00:00:00 2001
From: Riccardo Chiumiento <29974786+steadfastgaze@users.noreply.github.com>
Date: Wed, 26 Aug 2026 17:15:46 +0200
Subject: [PATCH] metal: initialize encode_async in ggml_backend_metal_init
 (#2334)

ggml_metal_init leaves ctx->encode_async nil, but
ggml_backend_metal_graph_compute invokes it unconditionally, so a Metal
backend created without a prior set_n_cb call segfaults on its first
graph. This affects rpc-server and ggml_backend_reg_metal_init; the
llama.cpp path is unaffected, since llama_graph_compute sets n_cb
before every compute.

Upstream added the same call in cad341d88 (#9698), the commit that
introduced encode_async. ik_llama.cpp carries the block but not the
initialization.
---
 ggml/src/ggml-metal.m | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/ggml/src/ggml-metal.m b/ggml/src/ggml-metal.m
index 323d4e45..ef8db66b 100644
--- a/ggml/src/ggml-metal.m
+++ b/ggml/src/ggml-metal.m
@@ -4509,6 +4509,8 @@ ggml_backend_t ggml_backend_metal_init(void) {
         /* .context   = */ ctx,
     };
 
+    ggml_backend_metal_set_n_cb(metal_backend, 1);
+
     return metal_backend;
 }