sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 114 Packages Projects Releases Wiki Activity

ggml-cpu : re-enable fast gelu_quick_f16 (#22339)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2026-04-26 08:28:14 +02:00
committed by GitHub
parent 2dd84169d1
commit 0c6ee1cade
1 changed files with 6 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/vec.h
+6 -13
View File
@@ -1036,12 +1036,12 @@ inline static float ggml_gelu_quick_f32(float x) {
return x*(1.0f/(1.0f+expf(GELU_QUICK_COEF*x))); return x*(1.0f/(1.0f+expf(GELU_QUICK_COEF*x)));
} }
//inline static void ggml_vec_gelu_quick_f16(const int n, ggml_fp16_t * y, const ggml_fp16_t * x) { inline static void ggml_vec_gelu_quick_f16(const int n, ggml_fp16_t * y, const ggml_fp16_t * x) {
// const uint16_t * i16 = (const uint16_t *) x; const uint16_t * i16 = (const uint16_t *) x;
// for (int i = 0; i < n; ++i) { for (int i = 0; i < n; ++i) {
// y[i] = ggml_table_gelu_quick_f16[i16[i]]; y[i] = ggml_table_gelu_quick_f16[i16[i]];
// } }
//} }
#ifdef GGML_GELU_QUICK_FP16 #ifdef GGML_GELU_QUICK_FP16
inline static void ggml_vec_gelu_quick_f32(const int n, float * y, const float * x) { inline static void ggml_vec_gelu_quick_f32(const int n, float * y, const float * x) {
@@ -1060,13 +1060,6 @@ inline static void ggml_vec_gelu_quick_f32(const int n, float * y, const float *
} }
#endif #endif
inline static void ggml_vec_gelu_quick_f16(const int n, ggml_fp16_t * y, const ggml_fp16_t * x) {
for (int i = 0; i < n; ++i) {
float v = GGML_CPU_FP16_TO_FP32(x[i]);
y[i] = GGML_CPU_FP32_TO_FP16(v*(1.0f/(1.0f+expf(GELU_QUICK_COEF*v))));
}
}
// Sigmoid Linear Unit (SiLU) function // Sigmoid Linear Unit (SiLU) function
inline static float ggml_silu_f32(float x) { inline static float ggml_silu_f32(float x) {
return x/(1.0f + expf(-x)); return x/(1.0f + expf(-x));