mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-09-23 05:26:19 +00:00
7c7836d9d4
* Refactor shaders, extract GLSL code from ggml_vk_generate_shaders.py into vulkan-shaders directory * Improve debug log code * Add memory debug output option * Fix flake8 * Fix unnecessary high llama-3 VRAM use
17 lines
419 B
Plaintext
17 lines
419 B
Plaintext
#version 450
|
|
|
|
#include "types.comp"
|
|
#include "generic_unary_head.comp"
|
|
|
|
void main() {
|
|
if (gl_GlobalInvocationID.x >= p.ne) {
|
|
return;
|
|
}
|
|
|
|
#ifndef OPTIMIZATION_ERROR_WORKAROUND
|
|
data_d[p.d_offset + dst_idx(gl_GlobalInvocationID.x)] = D_TYPE(data_a[src0_idx(gl_GlobalInvocationID.x)]);
|
|
#else
|
|
data_d[p.d_offset + dst_idx(gl_GlobalInvocationID.x)] = data_a[src0_idx(gl_GlobalInvocationID.x)];
|
|
#endif
|
|
}
|