Skip to content

ggml-quants : fix make_qp_quants NANs and IQ1 assertion errors #8

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Aug 17, 2025
Merged

ggml-quants : fix make_qp_quants NANs and IQ1 assertion errors #8

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions ggml/src/ggml-quants.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -901,7 +901,7 @@ static float make_qp_quants(int n, int nmax, const float * GGML_RESTRICT x, uint
for (int i = 0; i < n; ++i) {
max = MAX(max, x[i]);
}
if (!max) { // all zero
if (max < GROUP_MAX_EPS) { // all zero
for (int i = 0; i < n; ++i) { L[i] = 0; }
return 0.f;
}
Expand Down Expand Up @@ -966,7 +966,7 @@ static float make_qp_quants(int n, int nmax, const float * GGML_RESTRICT x, uint
break;
}
}
return sumlx/suml2;
return suml2 > 0.0f ? sumlx / suml2 : 0.0f;
}

static void quantize_row_q2_K_impl(const float * GGML_RESTRICT x, block_q2_K * GGML_RESTRICT y, int k, const float * GGML_RESTRICT quant_weights) {
Expand Down Expand Up @@ -4266,7 +4266,7 @@ static void quantize_row_iq1_s_impl(const float * GGML_RESTRICT x, void * GGML_R
sumw[j+1] = sumw[j] + weight[i];
}
}
float best_score = -FLT_MIN, scale = max;
float best_score = -FLT_MAX, scale = max;
int besti1 = -1, besti2 = -1, best_shift = 0;
for (int i1 = 0; i1 <= block_size; ++i1) {
for (int i2 = i1; i2 <= block_size; ++i2) {
Expand Down Expand Up @@ -4442,7 +4442,7 @@ static void quantize_row_iq1_m_impl(const float * GGML_RESTRICT x, void * GGML_R
idx[2*j] = j;
}
qsort(pairs, block_size, 2*sizeof(float), iq1_sort_helper);
float best_score = -FLT_MIN, scale = max;
float best_score = -FLT_MAX, scale = max;
int besti1 = -1, besti2 = -1, best_k = -1;
// 0: +, +
// 1: +, -
Expand Down
Loading