Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-03 17:51:09 +01:00
Code Issues Packages Projects Releases Wiki Activity

metal : indentations

Browse Source
This commit is contained in:
Georgi Gerganov 2023-10-07 16:16:23 +03:00
parent c60022488a
commit 8f6ad68427
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 16 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
ggml-metal.metal
View File

@ -435,18 +435,23 @@ void mul_vec_q_n_f32(device const void * src0, device const float * src1, device
int64_t ne00, int64_t ne01, int64_t ne02, int64_t ne10, int64_t ne12, int64_t ne0, int64_t ne1, uint gqa,
uint3 tgpig, uint tiisg, uint sgitg) {
const int nb = ne00/QK4_0;
const int r0 = tgpig.x;
const int r1 = tgpig.y;
const int im = tgpig.z;
const int first_row = (r0 * nsg + sgitg) * nr;
const uint offset0 = first_row * nb + im/gqa*(nb*ne0);
device const block_q_type * x = (device const block_q_type *) src0 + offset0;
device const float * y = (device const float *) src1 + r1*ne10 + im*ne00*ne1;
float yl[16]; // src1 vector cache
float sumf[nr]={0.f};
const int ix = tiisg/2;
const int il = 8*(tiisg%2);
float yl[16]; // src1 vector cache
float sumf[nr] = {0.f};
const int ix = (tiisg/2);
const int il = (tiisg%2)*8;
device const float * yb = y + ix * QK4_0 + il;
@ -457,6 +462,7 @@ void mul_vec_q_n_f32(device const void * src0, device const float * src1, device
sumy += yb[i] + yb[i+1];
yl[i+0] = yb[i+ 0];
yl[i+1] = yb[i+ 1]/256.f;
sumy += yb[i+16] + yb[i+17];
yl[i+8] = yb[i+16]/16.f;
yl[i+9] = yb[i+17]/4096.f;
@ -472,7 +478,7 @@ void mul_vec_q_n_f32(device const void * src0, device const float * src1, device
for (int row = 0; row < nr; ++row) {
const float tot = simd_sum(sumf[row]);
if (tiisg == 0 && first_row + row < ne01) {
dst[r1*ne0 + im*ne0*ne1 + first_row + row] = tot;
dst[im*ne0*ne1 + r1*ne0 + first_row + row] = tot;
}
}
}