sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-13 12:34:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

iq1_s: Metal works, but quite slow

Browse Source 
As usual, Apple Silicon does not like the code I write.
This commit is contained in:
Iwan Kawrakow
2024-02-13 14:37:16 +02:00
parent 020b548ec3
commit 425c6bbb6c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml-metal.metal
View File

@@ -4399,7 +4399,7 @@ void kernel_mul_mv_iq1_s_f32_impl(
for (int row = 0; row < N_DST; ++row) {
all_sum = simd_sum(sumf[row]);
if (tiisg == 0) {
dst[r1*ne0 + im*ne0*ne1 + first_row + row] = all_sum * 0.5f;
dst[r1*ne0 + im*ne0*ne1 + first_row + row] = all_sum;
}
}
}