CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-10 10:27:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

opencl: add swiglu_oai and add_id (#15121)

Browse Source 
* opencl: add `swiglu-oai`

* opencl: add `add_id`

* opencl: add missing `add_id.cl`
This commit is contained in:
lhez
2025-08-07 04:12:17 +09:00
committed by GitHub
parent 3db4da56a5
commit e725a1a982
4 changed files with 194 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
ggml/src/ggml-opencl/kernels/add_id.cl Normal file
View File

@@ -0,0 +1,42 @@
#pragma OPENCL EXTENSION cl_khr_fp16 : enable
//------------------------------------------------------------------------------
// add_id
//------------------------------------------------------------------------------
kernel void kernel_add_id(
global char * src0,
ulong offset0,
global char * src1,
ulong offset1,
global char * src2,
ulong offset2,
global char * dst,
ulong offsetd,
ulong nb01,
ulong nb02,
ulong nb11,
ulong nb21,
int ne0,
int ne1
) {
src0 = (global char*)((global char*)src0 + offset0);
src1 = (global char*)((global char*)src1 + offset1);
src2 = (global char*)((global char*)src2 + offset2);
dst = (global char*)((global char*)dst + offsetd);
int i1 = get_group_id(0);
int i2 = get_group_id(1);
const int i11 = *((global const int *) (src2 + i1*sizeof(int) + i2*nb21));
const size_t nb1 = ne0 * sizeof(float);
const size_t nb2 = ne1 * nb1;
global float * dst_row = (global float *)((global char *)dst + i1*nb1 + i2*nb2);
global float * src0_row = (global float *)((global char *)src0 + i1*nb01 + i2*nb02);
global float * src1_row = (global float *)((global char *)src1 + i11*nb11);
for (int i0 = get_local_id(0); i0 < ne0; i0 += get_local_size(0)) {
dst_row[i0] = src0_row[i0] + src1_row[i0];
}
}

41
ggml/src/ggml-opencl/kernels/glu.cl
View File

@@ -202,6 +202,47 @@ kernel void kernel_swiglu_f16(
}
}
//------------------------------------------------------------------------------
// swiglu_oai
//------------------------------------------------------------------------------
kernel void kernel_swiglu_oai(
global char * src0,
ulong offset0,
global char * src1,
ulong offset1,
global char * dst,
ulong offsetd,
ulong nb01,
ulong nb11,
int ne0,
ulong nb1,
int ne00_off,
int ne10_off,
float limit,
float alpha
) {
src0 = (global char*)((global char*)src0 + offset0);
src1 = (global char*)((global char*)src1 + offset1);
dst = (global char*)((global char*)dst + offsetd);
global float * src0_row = (global float *) ((global char *) src0 + get_group_id(0)*nb01) + ne00_off;
global float * src1_row = (global float *) ((global char *) src1 + get_group_id(0)*nb11) + ne10_off;
global float * dst_row = (global float *) ((global char *) dst + get_group_id(0)*nb1);
for (int i0 = get_local_id(0); i0 < ne0; i0 += get_local_size(0)) {
float x0 = src0_row[i0];
float x1 = src1_row[i0];
x0 = min(x0, limit);
x1 = max(min(x1, limit), -limit);
float out_glu = x0 / (1.0f + exp(-x0 * alpha));
out_glu = out_glu * (1.0f + x1);
dst_row[i0] = out_glu;
}
}
//------------------------------------------------------------------------------
// geglu_erf
//------------------------------------------------------------------------------