f3f65429c4
* scripts : update sync [no ci] * files : relocate [no ci] * ci : disable kompute build [no ci] * cmake : fixes [no ci] * server : fix mingw build ggml-ci * cmake : minor [no ci] * cmake : link math library [no ci] * cmake : build normal ggml library (not object library) [no ci] * cmake : fix kompute build ggml-ci * make,cmake : fix LLAMA_CUDA + replace GGML_CDEF_PRIVATE ggml-ci * move public backend headers to the public include directory (#8122) * move public backend headers to the public include directory * nix test * spm : fix metal header --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * scripts : fix sync paths [no ci] * scripts : sync ggml-blas.h [no ci] --------- Co-authored-by: slaren <slarengh@gmail.com>
22 lines
521 B
Text
22 lines
521 B
Text
layout(local_size_x_id = 0) in;
|
|
layout(local_size_y = 1) in;
|
|
layout(local_size_z = 1) in;
|
|
|
|
layout (binding = 0) readonly buffer tensorInA { uint8_t inA[]; };
|
|
layout (binding = 1) readonly buffer tensorInB { float inB[]; };
|
|
layout (binding = 2) writeonly buffer tensorOut { float out_[]; };
|
|
|
|
layout (push_constant) uniform parameter {
|
|
uint inAOff;
|
|
uint inBOff;
|
|
uint outOff;
|
|
int ne00;
|
|
int ne01;
|
|
int ne02;
|
|
int ne10;
|
|
int ne12;
|
|
int ne0;
|
|
int ne1;
|
|
uint r2;
|
|
uint r3;
|
|
} pcs;
|