Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-26 14:20:31 +01:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix handling of zero blocks in IQ quants

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-06-16 10:41:53 +03:00
parent 7c7836d9d4
commit 28f7a4d028
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
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

@ -13139,7 +13139,7 @@ static int iq1_find_best_neighbour(const uint16_t * restrict neighbours, const u
const float * restrict xval, const float * restrict weight, float * scale, int8_t * restrict L, int ngrid) { const float * restrict xval, const float * restrict weight, float * scale, int8_t * restrict L, int ngrid) {
int num_neighbors = neighbours[0]; int num_neighbors = neighbours[0];
GGML_ASSERT(num_neighbors > 0); GGML_ASSERT(num_neighbors > 0);
float best_score = 0; float best_score = -FLT_MAX;
int grid_index = -1; int grid_index = -1;
for (int j = 1; j <= num_neighbors; ++j) { for (int j = 1; j <= num_neighbors; ++j) {
const int8_t * pg = (const int8_t *)(grid + neighbours[j]); const int8_t * pg = (const int8_t *)(grid + neighbours[j]);
@ -13337,7 +13337,7 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
sumw[j+1] = sumw[j] + weight[i]; sumw[j+1] = sumw[j] + weight[i];
} }
} }
float best_score = 0, scale = max; float best_score = -FLT_MIN, scale = max;
int besti1 = -1, besti2 = -1, best_shift = 0; int besti1 = -1, besti2 = -1, best_shift = 0;
for (int i1 = 0; i1 <= block_size; ++i1) { for (int i1 = 0; i1 <= block_size; ++i1) {
for (int i2 = i1; i2 <= block_size; ++i2) { for (int i2 = i1; i2 <= block_size; ++i2) {
@ -13513,7 +13513,7 @@ static void quantize_row_iq1_m_impl(const float * restrict x, void * restrict vy
idx[2*j] = j; idx[2*j] = j;
} }
qsort(pairs, block_size, 2*sizeof(float), iq1_sort_helper); qsort(pairs, block_size, 2*sizeof(float), iq1_sort_helper);
float best_score = 0, scale = max; float best_score = -FLT_MIN, scale = max;
int besti1 = -1, besti2 = -1, best_k = -1; int besti1 = -1, besti2 = -1, best_k = -1;
// 0: +, + // 0: +, +
// 1: +, - // 1: +, -