From 154e0d75fccf1784fe9ff6fd76a630b66563da3d Mon Sep 17 00:00:00 2001 From: Kawrakow <48489457+ikawrakow@users.noreply.github.com> Date: Sat, 27 Jul 2024 07:55:01 +0200 Subject: Merge mainline llama.cpp (#3) * Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow --- tests/test-double-float.cpp | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'tests/test-double-float.cpp') diff --git a/tests/test-double-float.cpp b/tests/test-double-float.cpp index 753dae91..6aac4737 100644 --- a/tests/test-double-float.cpp +++ b/tests/test-double-float.cpp @@ -14,7 +14,7 @@ #pragma GCC diagnostic push #pragma GCC diagnostic ignored "-Wdouble-promotion" -// ggml.c::quantize_row_q4_0_reference +// ggml.c::quantize_row_q4_0_ref inline static uint8_t round_orig(float v0) { return ((int8_t) (round(v0))) + 8; } // ggml.c::ggml_silu_f32 @@ -24,7 +24,7 @@ inline static float silu_orig(float x) { #pragma GCC diagnostic pop -// ggml.c::quantize_row_q4_0_reference +// ggml.c::quantize_row_q4_0_ref inline static uint8_t round_float(float v0) { return (int8_t)roundf(v0) + 8; } // ggml.c::ggml_silu_f32 -- cgit v1.2.3