mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2025-09-11 09:34:37 +00:00
ggml : add ggml_gelu_erf() (#13667)
* ggml : add ggml_gelu_na (not approximated) * fix naming order * rename na --> erf * apply review suggesions * revert naming order
This commit is contained in:
parent
0d5c742161
commit
cf4cb59e64
7 changed files with 213 additions and 2 deletions
|
@ -428,6 +428,7 @@ inline static void ggml_vec_exp_f16 (const int n, ggml_fp16_t * y, const ggml_fp
|
|||
static const float GELU_COEF_A = 0.044715f;
|
||||
static const float GELU_QUICK_COEF = -1.702f;
|
||||
static const float SQRT_2_OVER_PI = 0.79788456080286535587989211986876f;
|
||||
static const float SQRT_2_INV = 0.70710678118654752440084436210484f;
|
||||
|
||||
inline static float ggml_gelu_f32(float x) {
|
||||
return 0.5f*x*(1.0f + tanhf(SQRT_2_OVER_PI*x*(1.0f + GELU_COEF_A*x*x)));
|
||||
|
@ -440,6 +441,14 @@ inline static void ggml_vec_gelu_f16(const int n, ggml_fp16_t * y, const ggml_fp
|
|||
}
|
||||
}
|
||||
|
||||
inline static void ggml_vec_gelu_erf_f16(const int n, ggml_fp16_t * y, const ggml_fp16_t * x) {
|
||||
for (int i = 0; i < n; ++i) {
|
||||
float xi = GGML_FP16_TO_FP32(x[i]);
|
||||
float res = 0.5f*xi*(1.0f + erff(xi*SQRT_2_INV));
|
||||
y[i] = GGML_FP32_TO_FP16(res);
|
||||
}
|
||||
}
|
||||
|
||||
#ifdef GGML_GELU_FP16
|
||||
inline static void ggml_vec_gelu_f32(const int n, float * y, const float * x) {
|
||||
uint16_t t;
|
||||
|
@ -463,6 +472,13 @@ inline static void ggml_vec_gelu_f32(const int n, float * y, const float * x) {
|
|||
}
|
||||
#endif
|
||||
|
||||
inline static void ggml_vec_gelu_erf_f32(const int n, float * y, const float * x) {
|
||||
for (int i = 0; i < n; ++i) {
|
||||
float xi = x[i];
|
||||
y[i] = 0.5f*xi*(1.0f + erff(xi*SQRT_2_INV));
|
||||
}
|
||||
}
|
||||
|
||||
inline static float ggml_gelu_quick_f32(float x) {
|
||||
return x*(1.0f/(1.0f+expf(GELU_QUICK_COEF*x)));
|
||||
}
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue