root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-27 03:44:35 +00:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity

Now fix test-quantize-fns

Browse Source
This commit is contained in:
Iwan Kawrakow 2024-03-21 12:18:03 +01:00
parent 30eef31b07
commit 68e4fed4d9
1 changed files with 1 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ggml-quants.c
View File

@ -11847,14 +11847,11 @@ void quantize_row_iq4_nl(const float * restrict x, void * restrict vy, int k) {
quantize_row_iq4_nl_impl(QK4_NL, 32, x + QK4_NL*ibl, &iq4[ibl].d, iq4[ibl].qs, &unused_h, unused_l,
&scale, weight, L, kvalues_iq4nl, NULL, -1);
}
//assert(k % QK4_NL == 0);
//block_iq4_nl * restrict y = vy;
//quantize_row_iq4_nl_reference(x, y, k);
}
void quantize_row_iq4_nl_reference(const float * restrict x, block_iq4_nl * restrict y, int k) {
assert(k % QK4_NL == 0);
quantize_iq4_nl(x, y, 1, k, NULL);
quantize_row_iq4_nl(x, y, k);
}
size_t quantize_iq4_xs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {