Skip to content

metal : disable fast math in all quantize kernels #14528

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
Jul 4, 2025
Merged

metal : disable fast math in all quantize kernels #14528

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
3 changes: 3 additions & 0 deletions ggml/src/ggml-metal/ggml-metal.metal
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,6 +109,7 @@ void dequantize_q4_0_t4(device const block_q4_0 * xb, short il, thread type4 & r
}

void quantize_q4_0(device const float * src, device block_q4_0 & dst) {
#pragma METAL fp math_mode(safe)
float amax = 0.0f; // absolute max
float max = 0.0f;

Expand Down Expand Up @@ -167,6 +168,7 @@ void quantize_q4_1(device const float * src, device block_q4_1 & dst) {
}

void quantize_q5_0(device const float * src, device block_q5_0 & dst) {
#pragma METAL fp math_mode(safe)
float amax = 0.0f; // absolute max
float max = 0.0f;

Expand Down Expand Up @@ -461,6 +463,7 @@ void dequantize_q8_0_t4(device const block_q8_0 *xb, short il, thread type4 & re
}

void quantize_q8_0(device const float * src, device block_q8_0 & dst) {
#pragma METAL fp math_mode(safe)
float amax = 0.0f; // absolute max

for (int j = 0; j < QK8_0; j++) {
Expand Down
Loading