shaofeiqi c78845bfa9 opencl: add kernel to handle mat mul in attention to improve encoding speed (llama/17181) ...

* Add mul_mm_f16_f32_kq_kqv kernel

* Add ggml_cl_mul_mat_kq_kqv_adreno func

* fix whitespace

* remove unused variable

* remove redundant

* refactor and clean up

* remove trailing whitespace

2025-11-17 21:05:46 +02:00

..

cmake

…

include

ggml : add ops SOFTPLUS, EXPM1, TRI, SOLVE_TRI, CUMSUM (llama/17063)

2025-11-17 21:05:46 +02:00

src

opencl: add kernel to handle mat mul in attention to improve encoding speed (llama/17181)

2025-11-17 21:05:46 +02:00

.gitignore

…

CMakeLists.txt

ggml: disable vxe for cross-compilation by default (llama/16966)

2025-11-09 23:38:03 +02:00