diff options
author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-07-27 07:55:01 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-07-27 07:55:01 +0200 |
commit | 154e0d75fccf1784fe9ff6fd76a630b66563da3d (patch) | |
tree | 81ce6dbb5b1900c1aa78a879f0593c694cab9d27 /examples/sycl/build.sh | |
parent | 0684c3e9c70d49323b4fc517128cbe222cab7f96 (diff) |
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 <iwan.kawrakow@gmail.com>
Diffstat (limited to 'examples/sycl/build.sh')
-rwxr-xr-x | examples/sycl/build.sh | 4 |
1 files changed, 2 insertions, 2 deletions
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 |