From 22e1b45c02a4b532cd01b9330d034d2b6696e1cb Mon Sep 17 00:00:00 2001
From: jianyuzh <jianyu.zhang@intel.com>
Date: Wed, 24 Jan 2024 17:24:24 +0800
Subject: [PATCH] fix build break on MacOS, due to CI of MacOS depend on
 external ggml, instead of internal ggml

---
 llama.cpp | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/llama.cpp b/llama.cpp
index ce74fb557..b8d0f1bba 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -6703,10 +6703,14 @@ static int llama_decode_internal(
     }
 
     const bool fully_offloaded = model.n_gpu_layers >= (int) hparams.n_layer + 1;
-    if ((ggml_cpu_has_cublas() || ggml_cpu_has_sycl()) && fully_offloaded) {
+    if (ggml_cpu_has_cublas() && fully_offloaded) {
         n_threads = 1;
     }
 
+#ifdef GGML_USE_SYCL
+    n_threads = 1;
+#endif
+
 #ifdef GGML_USE_MPI
     const int64_t n_layer = hparams.n_layer;
     ggml_mpi_graph_compute_pre(lctx.ctx_mpi, gf, n_layer);