haraldwolff
/
whisper.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ci : fix wikitext url + compile warnings (llama/5569) 

ggml-ci
pull/1841/merge
Georgi Gerganov 2024-02-18 22:39:30 +02:00
parent 0775374750
commit 0c33928b55
No known key found for this signature in database
GPG Key ID: BF970631944C16B7
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
ggml-quants.c
View File

@ -1837,9 +1837,9 @@ static void quantize_row_q2_K_impl(const float * restrict x, block_q2_K * restri
float sigma2 = sumx2/QK_K;
for (int j = 0; j < QK_K/16; ++j) {
const float * restrict qw = quant_weights + QK_K * i + 16*j;
for (int l = 0; l < 16; ++l) weight[l] = qw[l] * sqrtf(sigma2 + x[16*j + l]*x[16*j + l]);
for (int l = 0; l < 16; ++l) sw[j] += weight[l];
scales[j] = make_qkx3_quants(16, 3, x + 16*j, weight, L + 16*j, &mins[j], Laux, -0.9f, 0.05f, 36, false);
for (int l = 0; l < QK_K/16; ++l) weight[l] = qw[l] * sqrtf(sigma2 + x[16*j + l]*x[16*j + l]);
for (int l = 0; l < QK_K/16; ++l) sw[j] += weight[l];
scales[j] = make_qkx3_quants(QK_K/16, 3, x + 16*j, weight, L + 16*j, &mins[j], Laux, -0.9f, 0.05f, 36, false);
}
float dm = make_qp_quants(QK_K/16, 15, scales, Ls, sw);