CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-quants : remove some commented code

Browse Source
This commit is contained in:
Francis Couture-Harpin
2025-03-15 10:29:47 -04:00
parent f27c1afc40
commit 0c9e442489
1 changed files with 0 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-quants.c
View File

@@ -5173,7 +5173,6 @@ static void quantize_row_iq4_nl_impl(const int super_block_size, const int block
for (int j = 0; j < block_size; ++j) weight[j] = qw[j] * sqrtf(sigma2 + xb[j]*xb[j]);
} else {
for (int j = 0; j < block_size; ++j) weight[j] = sqrtf(sigma2 + xb[j]*xb[j]);
// for (int j = 0; j < block_size; ++j) weight[j] = 1;
}
float amax = 0;
for (int j = 0; j < block_size; ++j) {
@@ -5258,7 +5257,6 @@ size_t quantize_iq4_nl(const float * restrict src, void * restrict dst, int64_t
return nrow * nblock * sizeof(block_iq4_nl);
}
//void quantize_row_iq4_nl_ref(const float * restrict x, void * restrict vy, int64_t k) {
void quantize_row_iq4_nl_ref(const float * restrict x, block_iq4_nl * restrict y, int64_t k) {
GGML_ASSERT(k%QK4_NL == 0);
int64_t nblock = k/QK4_NL;