llama_cpp_for_radxa_dragon_.../ggml
Sam/Samuel f4ce81c45e
metal: optimise GGML_OP_SUM (#16559)
* optimise GGML_OP_SUM

* add non-contiguous tests by permuting the input

* change tests to require full contiguity of OP_SUM

* cuda : add check GGML_OP_SUM

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2025-10-15 17:05:56 +03:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include rpc : add support for multiple devices (#16276) 2025-10-04 12:49:16 +03:00
src metal: optimise GGML_OP_SUM (#16559) 2025-10-15 17:05:56 +03:00
.gitignore
CMakeLists.txt ggml webgpu: profiling, CI updates, reworking of command submission (#16452) 2025-10-07 13:48:56 -07:00