llama.cpp/ggml
M. Mediouni fcb013847c
ggml-hexagon: Initial Hexagon v68/v69 support (#17394)
* ggml-hexagon: fix build error with GCC

Add stdexcept include to fix GCC build errors

Signed-off-by: Mohamed Mediouni <mohamed@unpredictable.fr>

* ggml-hexagon: check VTCM acquire failures

Signed-off-by: Mohamed Mediouni <mohamed@unpredictable.fr>

* ggml-hexagon: disable destination bypass on older than v73

v68 errors out if having bypass enabled when the VTCM is the destination.

At least on v68 this made things actually work... not a proper fix though, so to look at later...

Signed-off-by: Mohamed Mediouni <mohamed@unpredictable.fr>

* ggml-hexagon: add initial v68/v69 support

v68 is the Hexagon revision notably used on the Snapdragon 8cx
Gen 3 and the QCM6490.

Also add support for v69.

8MB isn't a supported page size, so relax asked for page size constraint
for HAP_compute_res_attr_set_vtcm_param_v2 to optimal.

Signed-off-by: Mohamed Mediouni <mohamed@unpredictable.fr>

---------

Signed-off-by: Mohamed Mediouni <mohamed@unpredictable.fr>
2025-11-23 16:54:49 -08:00
..
cmake ggml: Skip backend library linking code when GGML_BACKEND_DL=ON (#15094) 2025-08-07 13:45:41 +02:00
include ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (#17063) 2025-11-13 20:54:47 +02:00
src ggml-hexagon: Initial Hexagon v68/v69 support (#17394) 2025-11-23 16:54:49 -08:00
.gitignore vulkan : cmake integration (#8119) 2024-07-13 18:12:39 +02:00
CMakeLists.txt ggml: disable vxe for cross-compilation by default (#16966) 2025-11-08 16:00:20 +08:00