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 --- examples/quantize-stats/quantize-stats.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'examples/quantize-stats/quantize-stats.cpp') diff --git a/examples/quantize-stats/quantize-stats.cpp b/examples/quantize-stats/quantize-stats.cpp index 4eb8f953..837a17c7 100644 --- a/examples/quantize-stats/quantize-stats.cpp +++ b/examples/quantize-stats/quantize-stats.cpp @@ -154,7 +154,7 @@ static void test_roundtrip_on_chunk( } if (use_reference) { - qfns.from_float_reference(input_scratch, quantized_scratch, chunk_size); + qfns.from_float_ref(input_scratch, quantized_scratch, chunk_size); } else { qfns.from_float(input_scratch, quantized_scratch, chunk_size); } -- cgit v1.2.3