vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

metal : add F32 -> Q8_0 copy kernel

Browse source
This commit is contained in:
Georgi Gerganov 2023-12-04 10:42:10 +02:00
parent d04ee928a2
commit bcfebf241d
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
3 changed files with 70 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

58
ggml-metal.metal
View file

@ -1460,6 +1460,64 @@ kernel void kernel_cpy_f32_f32(
}
}
kernel void kernel_cpy_f32_q8_0(
device const float * src0,
device void * dst,
constant int64_t & ne00,
constant int64_t & ne01,
constant int64_t & ne02,
constant int64_t & ne03,
constant uint64_t & nb00,
constant uint64_t & nb01,
constant uint64_t & nb02,
constant uint64_t & nb03,
constant int64_t & ne0,
constant int64_t & ne1,
constant int64_t & ne2,
constant int64_t & ne3,
constant uint64_t & nb0,
constant uint64_t & nb1,
constant uint64_t & nb2,
constant uint64_t & nb3,
uint3 tgpig[[threadgroup_position_in_grid]],
uint3 tpitg[[thread_position_in_threadgroup]],
uint3 ntg[[threads_per_threadgroup]]) {
const int64_t i03 = tgpig[2];
const int64_t i02 = tgpig[1];
const int64_t i01 = tgpig[0];
const int64_t n = i03*ne02*ne01*ne00 + i02*ne01*ne00 + i01*ne00;
const int64_t i3 = n / (ne2*ne1*ne0);
const int64_t i2 = (n - i3*ne2*ne1*ne0) / (ne1*ne0);
const int64_t i1 = (n - i3*ne2*ne1*ne0 - i2*ne1*ne0) / ne0;
const int64_t i0 = (n - i3*ne2*ne1*ne0 - i2*ne1*ne0 - i1*ne0)/QK8_0;
device block_q8_0 * dst_data = (device block_q8_0 *) ((device char *) dst + i3*nb3 + i2*nb2 + i1*nb1 + i0*nb0);
for (int64_t i00 = tpitg.x*QK8_0; i00 < ne00; i00 += ntg.x*QK8_0) {
device const float * src = (device float *)((device char *) src0 + i03*nb03 + i02*nb02 + i01*nb01 + i00*nb00);
float amax = 0.0f; // absolute max
for (int j = 0; j < QK8_0; j++) {
const float v = src[j];
amax = MAX(amax, fabs(v));
}
const float d = amax / ((1 << 7) - 1);
const float id = d ? 1.0f/d : 0.0f;
dst_data[i00/QK8_0].d = d;
for (int j = 0; j < QK8_0; ++j) {
const float x0 = src[j]*id;
dst_data[i00/QK8_0].qs[j] = round(x0);
}
}
}
kernel void kernel_concat(
device const char * src0,
device const char * src1,