Skip to content

ggml : add asserts #14720

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 2 commits into from
Jul 16, 2025
Merged

ggml : add asserts #14720

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c1656c1
ggml : add asserts
ggerganov Jul 16, 2025
97f7b10
cont : fix constant type
ggerganov Jul 16, 2025
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
3 changes: 3 additions & 0 deletions ggml/src/ggml-cpu/ops.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4015,6 +4015,9 @@ static void ggml_compute_forward_rms_norm_f32(

const float scale = 1.0f/sqrtf(mean + eps);

// if you hit this, likely you got an inf somewhere earlier
assert(scale > 0.0);

ggml_vec_scale_f32(ne00, y, scale);
}
}
Expand Down
3 changes: 3 additions & 0 deletions ggml/src/ggml-cpu/vec.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -221,6 +221,9 @@ void ggml_vec_dot_f16(int n, float * GGML_RESTRICT s, size_t bs, ggml_fp16_t * G
for (int i = np; i < n; ++i) {
sumf += (ggml_float)(GGML_CPU_FP16_TO_FP32(x[i])*GGML_CPU_FP16_TO_FP32(y[i]));
}

// if you hit this, you are likely running outside the FP range
assert(!isnan(sumf) && !isinf(sumf));
#else
for (int i = 0; i < n; ++i) {
sumf += (ggml_float)(GGML_CPU_FP16_TO_FP32(x[i])*GGML_CPU_FP16_TO_FP32(y[i]));
Expand Down
Loading