CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-quants : rename best_mad to best_error (ggml/1283)

Browse Source 
This commit renames the variable `best_mad` to `best_error` in the
`make_qkx2_quants` function.

The motivation for this is that the name `best_mad` can be somewhat
confusing if mean absolute deviation (MAD) is not in use.
This commit is contained in:
Daniel Bevenius
2025-06-24 06:10:16 +02:00
committed by Georgi Gerganov
parent 79b33b2317
commit 497be7c01d
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
ggml/src/ggml-quants.c
View File

@@ -568,14 +568,14 @@ static float make_qkx2_quants(int n, int nmax, const float * GGML_RESTRICT x, co
} }
float iscale = nmax/(max - min); float iscale = nmax/(max - min);
float scale = 1/iscale; float scale = 1/iscale;
float best_mad = 0; float best_error = 0;
for (int i = 0; i < n; ++i) { for (int i = 0; i < n; ++i) {
int l = nearest_int(iscale*(x[i] - min)); int l = nearest_int(iscale*(x[i] - min));
L[i] = MAX(0, MIN(nmax, l)); L[i] = MAX(0, MIN(nmax, l));
float diff = scale * L[i] + min - x[i]; float diff = scale * L[i] + min - x[i];
diff = use_mad ? fabsf(diff) : diff * diff; diff = use_mad ? fabsf(diff) : diff * diff;
float w = weights[i]; float w = weights[i];
best_mad += w * diff; best_error += w * diff;
} }
if (nstep < 1) { if (nstep < 1) {
*the_min = -min; *the_min = -min;
@@ -601,18 +601,18 @@ static float make_qkx2_quants(int n, int nmax, const float * GGML_RESTRICT x, co
this_min = 0; this_min = 0;
this_scale = sum_xl / sum_l2; this_scale = sum_xl / sum_l2;
} }
float mad = 0; float cur_error = 0;
for (int i = 0; i < n; ++i) { for (int i = 0; i < n; ++i) {
float diff = this_scale * Laux[i] + this_min - x[i]; float diff = this_scale * Laux[i] + this_min - x[i];
diff = use_mad ? fabsf(diff) : diff * diff; diff = use_mad ? fabsf(diff) : diff * diff;
float w = weights[i]; float w = weights[i];
mad += w * diff; cur_error += w * diff;
} }
if (mad < best_mad) { if (cur_error < best_error) {
for (int i = 0; i < n; ++i) { for (int i = 0; i < n; ++i) {
L[i] = Laux[i]; L[i] = Laux[i];
} }
best_mad = mad; best_error = cur_error;
scale = this_scale; scale = this_scale;
min = this_min; min = this_min;
} }