mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-01-01 00:39:00 +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>
27 lines
702 B
Plaintext
27 lines
702 B
Plaintext
#version 450
|
|
|
|
#include "types.comp"
|
|
#include "generic_binary_head.comp"
|
|
|
|
void main() {
|
|
const uint i00 = gl_GlobalInvocationID.x;
|
|
const uint i10 = gl_GlobalInvocationID.y;
|
|
const uint i11 = (gl_GlobalInvocationID.z)/p.ne12;
|
|
const uint i12 = (gl_GlobalInvocationID.z)%p.ne12;
|
|
|
|
if (i00 >= p.ne00) {
|
|
return;
|
|
}
|
|
|
|
const uint i01 = data_b[i10*p.nb10 + i11*p.nb11 + i12*p.nb12];
|
|
|
|
const uint a_offset = i01*p.nb01 + i11*p.nb02 + i12*p.nb03;
|
|
const uint d_offset = i10*p.nb21 + i11*p.nb22 + i12*p.nb23;
|
|
|
|
#ifndef OPTIMIZATION_ERROR_WORKAROUND
|
|
data_d[d_offset + i00] = D_TYPE(data_a[a_offset + i00]);
|
|
#else
|
|
data_d[d_offset + i00] = data_a[a_offset + i00];
|
|
#endif
|
|
}
|