EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

ggml : implement GEGLU_ERF and GEGLU_QUICK ops (#14445)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-07-03 23:07:22 +02:00
committed by GitHub
parent bee28421be
commit 28657a8229
20 changed files with 789 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
ggml/src/ggml-vulkan/vulkan-shaders/geglu_erf.comp Normal file
View File

@@ -0,0 +1,27 @@
#version 450
#include "glu_head.comp"
// based on Abramowitz and Stegun formula 7.1.26 or similar Hastings' approximation
// ref: https://www.johndcook.com/blog/python_erf/
const float p_erf = 0.3275911f;
const float a1_erf = 0.254829592f;
const float a2_erf = -0.284496736f;
const float a3_erf = 1.421413741f;
const float a4_erf = -1.453152027f;
const float a5_erf = 1.061405429f;
const float SQRT_2_INV = 0.70710678118654752440084436210484f;
float op(float a, float b) {
const float a_div_sqr2 = a * SQRT_2_INV;
const float sign_x = sign(a_div_sqr2);
const float x = abs(a_div_sqr2);
const float t = 1.0f / (1.0f + p_erf * x);
const float y = 1.0f - (((((a5_erf * t + a4_erf) * t) + a3_erf) * t + a2_erf) * t + a1_erf) * t * exp(-x * x);
const float erf_approx = sign_x * y;
return 0.5f * a * (1.0f + erf_approx) * b;
}
#include "glu_main.comp"

11
ggml/src/ggml-vulkan/vulkan-shaders/geglu_quick.comp Normal file
View File

@@ -0,0 +1,11 @@
#version 450
#include "glu_head.comp"
const float GELU_QUICK_COEF = -1.702f;
float op(float a, float b) {
return a * (1.0f / (1.0f + exp(GELU_QUICK_COEF * a))) * b;
}
#include "glu_main.comp"

4
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
View File

@@ -593,6 +593,10 @@ void process_shaders() {
string_to_spv("reglu_f32", "reglu.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("swiglu_f16", "swiglu.comp", {{"A_TYPE", "float16_t"}, {"D_TYPE", "float16_t"}});
string_to_spv("swiglu_f32", "swiglu.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("geglu_erf_f16", "geglu_erf.comp", {{"A_TYPE", "float16_t"}, {"D_TYPE", "float16_t"}});
string_to_spv("geglu_erf_f32", "geglu_erf.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("geglu_quick_f16","geglu_quick.comp", {{"A_TYPE", "float16_t"}, {"D_TYPE", "float16_t"}});
string_to_spv("geglu_quick_f32","geglu_quick.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("leaky_relu_f32", "leaky_relu.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
string_to_spv("silu_back_f32", "silu_back.comp", {{"A_TYPE", "float"}, {"B_TYPE", "float"}, {"D_TYPE", "float"}});