mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-29 07:34:18 +01:00
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>
30 lines
592 B
Plaintext
30 lines
592 B
Plaintext
#version 450
|
|
|
|
#extension GL_EXT_control_flow_attributes : enable
|
|
|
|
layout(local_size_x = 256, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
layout (binding = 0) readonly buffer A {float data_a[];};
|
|
layout (binding = 1) writeonly buffer D {float data_d[];};
|
|
|
|
layout (push_constant) uniform parameter {
|
|
uint ne;
|
|
uint k_num;
|
|
} p;
|
|
|
|
void main() {
|
|
const uint idx = gl_GlobalInvocationID.x;
|
|
|
|
if (idx >= p.ne) {
|
|
return;
|
|
}
|
|
|
|
float result = 0.0f;
|
|
|
|
[[unroll]] for (uint i = 0; i < p.k_num; i++) {
|
|
result += data_a[i * p.ne + idx];
|
|
}
|
|
|
|
data_d[idx] = result;
|
|
}
|