tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-23 11:16:32 +00:00
Code Issues Packages Projects Releases Wiki Activity

metal : disable fast-math for some cpy kernels (#14460)

Browse Source 
* metal : disable fast-math for some cpy kernels

ggml-ci

* cont : disable for q4_1

ggml-ci

* cont : disable for iq4_nl

ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-30 17:04:05 +03:00
committed by GitHub
parent a7417f5594
commit 5dd942de59
1 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-metal/ggml-metal.metal
View File

@ -138,6 +138,7 @@ void quantize_q4_0(device const float * src, device block_q4_0 & dst) {
}
void quantize_q4_1(device const float * src, device block_q4_1 & dst) {
#pragma METAL fp math_mode(safe)
float min = FLT_MAX;
float max = -FLT_MAX;
@ -203,6 +204,7 @@ void quantize_q5_0(device const float * src, device block_q5_0 & dst) {
}
void quantize_q5_1(device const float * src, device block_q5_1 & dst) {
#pragma METAL fp math_mode(safe)
float max = src[0];
float min = src[0];
@ -239,6 +241,7 @@ void quantize_q5_1(device const float * src, device block_q5_1 & dst) {
}
void quantize_iq4_nl(device const float * src, device block_iq4_nl & dst) {
#pragma METAL fp math_mode(safe)
float amax = 0.0f; // absolute max
float max = 0.0f;