mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-26 11:24:35 +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
21 lines
442 B
Plaintext
21 lines
442 B
Plaintext
#version 450
|
|
|
|
#include "dequant_head.comp"
|
|
|
|
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 {D_TYPE data_b[];};
|
|
|
|
void main() {
|
|
const uint i = gl_GlobalInvocationID.x * 16;
|
|
|
|
if (i >= p.nel) {
|
|
return;
|
|
}
|
|
|
|
[[unroll]] for (uint l = 0; l < 16; l++) {
|
|
data_b[i + l] = D_TYPE(data_a[i + l]);
|
|
}
|
|
}
|