extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-08-10 14:38:32 +02:00
Code Issues Packages Projects Releases Wiki Activity

metal : disable fast math in all quantize kernels (llama/14528)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-04 19:19:09 +03:00
parent af304ef080
commit 10d0d28f7c
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

@ -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;
@ -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;
@ -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++) {