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 --- ggml-cuda/sumrows.cuh | 3 --- 1 file changed, 3 deletions(-) delete mode 100644 ggml-cuda/sumrows.cuh (limited to 'ggml-cuda/sumrows.cuh') diff --git a/ggml-cuda/sumrows.cuh b/ggml-cuda/sumrows.cuh deleted file mode 100644 index e7545f83..00000000 --- a/ggml-cuda/sumrows.cuh +++ /dev/null @@ -1,3 +0,0 @@ -#include "common.cuh" - -void ggml_cuda_op_sum_rows(ggml_backend_cuda_context & ctx, ggml_tensor * dst); -- cgit v1.2.3