Public/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-09-18 08:44:49 +02:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
Michael Taylor
2026-09-16 23:15:47 -03:00
committed by GitHub
parent 4bc272fd72
commit aa39d7a3e1
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/include/ggml-sycl.h
+1 -1
View File
@@ -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.
ggml/src/ggml-sycl/ggml-sycl.cpp
+2 -2
View File
@@ -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;