From 5dd942de5922a22ec8446a4ad2203738dbcb9389 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Mon, 30 Jun 2025 17:04:05 +0300 Subject: [PATCH] metal : disable fast-math for some cpy kernels (#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 --- ggml/src/ggml-metal/ggml-metal.metal | 3 +++ 1 file changed, 3 insertions(+) diff --git a/ggml/src/ggml-metal/ggml-metal.metal b/ggml/src/ggml-metal/ggml-metal.metal index fc3cfe35a3..dac45c7a99 100644 --- 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;