mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-28 15:18:26 +01:00
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
26 lines
700 B
Plaintext
26 lines
700 B
Plaintext
#version 450
|
|
|
|
#include "generic_head.comp"
|
|
#include "types.comp"
|
|
|
|
#extension GL_EXT_control_flow_attributes : enable
|
|
|
|
layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
|
|
|
|
layout (binding = 0) readonly buffer X {A_TYPE data_a[];};
|
|
layout (binding = 1) writeonly buffer D {D_TYPE data_d[];};
|
|
|
|
void main() {
|
|
const float GELU_COEF_A = 0.044715f;
|
|
const float SQRT_2_OVER_PI = 0.79788456080286535587989211986876f;
|
|
const uint i = gl_GlobalInvocationID.x;
|
|
|
|
if (i >= p.KX) {
|
|
return;
|
|
}
|
|
|
|
const float xi = float(data_a[i]);
|
|
const float val = SQRT_2_OVER_PI*xi*(1.0f + GELU_COEF_A*xi*xi);
|
|
data_d[i] = D_TYPE(0.5f*xi*(2.0f - 2.0f / (exp(2 * val) + 1)));
|
|
}
|