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

* metal : disable fast-math for some cpy kernels

ggml-ci

* cont : disable for q4_1

ggml-ci

* cont : disable for iq4_nl

ggml-ci

diff --git a/ggml/src/ggml-metal/ggml-metal.metal b/ggml/src/ggml-metal/ggml-metal.metal
index fc3cfe35a34bf96c3f989d6143deaeba3aae8048..dac45c7a99b52b326963efc549f23e425ae3a776 100644 (file)
--- a/ggml/src/ggml-metal/ggml-metal.metal
+++ b/ggml/src/ggml-metal/ggml-metal.metal
@@ -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;