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/sycl/build.sh | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'examples/sycl/build.sh') diff --git a/examples/sycl/build.sh b/examples/sycl/build.sh index db46d57c..8fe0a679 100755 --- a/examples/sycl/build.sh +++ b/examples/sycl/build.sh @@ -8,10 +8,10 @@ cd build source /opt/intel/oneapi/setvars.sh #for FP16 -#cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON # faster for long-prompt inference +#cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON # faster for long-prompt inference #for FP32 -cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx +cmake .. -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx #build example/main #cmake --build . --config Release --target main -- cgit v1.2.3