Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-15 14:50:51 +01:00
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
Show Stats 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) { for (int row = 0; row < N_DST; ++row) {
all_sum = simd_sum(sumf[row]); all_sum = simd_sum(sumf[row]);
if (tiisg == 0) { 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;
} }
} }
} }