LLM inference in C/C++
C++ ggml
[SYCL] Fix function signature for `ggml_backend_sycl_split_buffer_type` (#28981)
Michael Tayloraa39d7a3e145
diff --git a/ggml/include/ggml-sycl.h b/ggml/include/ggml-sycl.hindex 418a7ba978..093fa4a7e4 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.cppindex 6f9ead60eb..beaba8a4ae 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 * dsSYCL_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;