summaryrefslogtreecommitdiff
path: root/examples/sycl/build.sh
diff options
context:
space:
mode:
authorKawrakow <48489457+ikawrakow@users.noreply.github.com>2024-07-27 07:55:01 +0200
committerGitHub <noreply@github.com>2024-07-27 07:55:01 +0200
commit154e0d75fccf1784fe9ff6fd76a630b66563da3d (patch)
tree81ce6dbb5b1900c1aa78a879f0593c694cab9d27 /examples/sycl/build.sh
parent0684c3e9c70d49323b4fc517128cbe222cab7f96 (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-xexamples/sycl/build.sh4
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