lhez 71e74a3ac9 opencl: add backend_synchronize (#13939) ...

* This is not needed by the normal use where the result is read
  using `tensor_get`, but it allows perf mode of `test-backend-ops`
  to properly measure performance.

2025-06-02 16:54:58 -07:00

..

cmake

cmake: Factor out CPU architecture detection (#13883)

2025-05-29 12:50:25 +02:00

include

ggml : remove ggml_graph_import and ggml_graph_export declarations (ggml/1247)

2025-06-01 13:43:57 +03:00

src

opencl: add backend_synchronize (#13939)

2025-06-02 16:54:58 -07:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

vulkan: use timestamp queries for GGML_VULKAN_PERF (#13817)

2025-05-27 18:39:07 +02:00