mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-17 11:37:10 +00:00
e29acf74fe
* vulkan (DRAFT): split shader generation by GLSL source file, to improve incremental build times * support dep-files so shaders are recompiled if their included files change * rename shader files which are used as "headers" to use .glsl extension * move glslc extension detection shaders to separate folders * the above is to prevent them from getting glob'd with the actual compute shaders that need to be compiled * vulkan : only write embedded shader .hpp/.cpp when they change * avoid recompiling ggml-vulkan.cpp when editing shaders * pass single --source argument instead of --input-dir & --filter to shader gen * check for source file match earlier * fix hang in vulkan-shaders-gen when there are compilation errors * early out did not decrement compile_count * clean up * fix glslc integer dot product test * unconditionally write the embedded shader cpp output * replace output filepath in generated dep-files to match output in CMakeLists --------- Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
42 lines
1.1 KiB
Plaintext
42 lines
1.1 KiB
Plaintext
#version 450
|
|
|
|
#include "rope_head.glsl"
|
|
|
|
void main() {
|
|
const uint i0 = 2*gl_GlobalInvocationID.y;
|
|
uint ne0 = p.ncols;
|
|
uint ne1 = p.p_delta_rows;
|
|
|
|
if (i0 >= ne0) {
|
|
return;
|
|
}
|
|
|
|
const uint row_dst = gl_GlobalInvocationID.x;
|
|
|
|
const uint row_x = row_dst % ne1;
|
|
const uint channel_x = row_dst / ne1;
|
|
|
|
const uint idst = row_dst*ne0 + i0/2;
|
|
const uint ix = channel_x*p.s2 + row_x*p.s1 + i0/2;
|
|
|
|
if (i0 >= p.n_dims) {
|
|
data_d[idst + i0/2 + 0] = data_a[ix + i0/2 + 0];
|
|
data_d[idst + i0/2 + 1] = data_a[ix + i0/2 + 1];
|
|
|
|
return;
|
|
}
|
|
|
|
const float theta_base = data_pos[channel_x] * pow(p.theta_scale, i0/2.0f);
|
|
|
|
const float freq_factor = p.has_ff != 0 ? data_ff[i0/2] : 1.0f;
|
|
|
|
float cos_theta, sin_theta;
|
|
rope_yarn(theta_base / freq_factor, i0, cos_theta, sin_theta);
|
|
|
|
const float x0 = float(data_a[ix + 0]);
|
|
const float x1 = float(data_a[ix + p.n_dims/2]);
|
|
|
|
data_d[idst + 0] = D_TYPE(x0*cos_theta - x1*sin_theta);
|
|
data_d[idst + p.n_dims/2] = D_TYPE(x0*sin_theta + x1*cos_theta);
|
|
}
|