Commit aa39d7a3e for llama.cpp

commit aa39d7a3e145a88202793a89462d65e94a5fc25f
Author: Michael Taylor <162068037+mctylr-gh@users.noreply.github.com>
Date:   Wed Sep 16 23:15:47 2026 -0300

    [SYCL] Fix function signature for `ggml_backend_sycl_split_buffer_type` (#28981)

diff --git a/ggml/include/ggml-sycl.h b/ggml/include/ggml-sycl.h
index 418a7ba97..093fa4a7e 100644
--- a/ggml/include/ggml-sycl.h
+++ b/ggml/include/ggml-sycl.h
@@ -25,7 +25,7 @@ GGML_BACKEND_API bool ggml_backend_is_sycl(ggml_backend_t backend);
 GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_sycl_buffer_type(int device);

 // split tensor buffer that splits matrices by rows across multiple devices
-GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_sycl_split_buffer_type(const float * tensor_split);
+GGML_BACKEND_API ggml_backend_buffer_type_t ggml_backend_sycl_split_buffer_type([[maybe_unused]] int main_device, const float * tensor_split);

 // Tensor parallelism (--split-mode tensor): comm_init/free/allreduce_tensor
 // trio queried by the meta-backend via ggml_backend_reg_get_proc_address.
diff --git a/ggml/src/ggml-sycl/ggml-sycl.cpp b/ggml/src/ggml-sycl/ggml-sycl.cpp
index 6f9ead60e..beaba8a4a 100644
--- a/ggml/src/ggml-sycl/ggml-sycl.cpp
+++ b/ggml/src/ggml-sycl/ggml-sycl.cpp
@@ -1484,7 +1484,7 @@ static ggml_backend_buffer_type_i ggml_backend_sycl_split_buffer_type_interface
     /* .is_host          = */ ggml_backend_sycl_split_buffer_type_is_host,
 };

-ggml_backend_buffer_type_t ggml_backend_sycl_split_buffer_type(const float * tensor_split) {
+ggml_backend_buffer_type_t ggml_backend_sycl_split_buffer_type([[maybe_unused]] int main_device, const float * tensor_split) {
     GGML_SYCL_DEBUG("[SYCL] call ggml_backend_sycl_split_buffer_type\n");

     static std::mutex mutex;
@@ -3243,7 +3243,7 @@ inline void ggml_sycl_op_scale(ggml_backend_sycl_context & ctx, ggml_tensor * ds
     SYCL_CHECK(0);
 }

-static void ggml_sycl_set_peer_access(const int n_tokens, int main_device) {
+static void ggml_sycl_set_peer_access(const int n_tokens, [[maybe_unused]] int main_device) {
     static bool peer_access_enabled = false;

     const bool enable_peer_access = n_tokens <= GGML_SYCL_PEER_MAX_BATCH_SIZE;