From 9a426b6a0b998501ece5f1a9cce2461ad6255a97 Mon Sep 17 00:00:00 2001 From: Anas Ahouzi <112881240+aahouzi@users.noreply.github.com> Date: Fri, 19 Apr 2024 15:19:35 +0200 Subject: [PATCH] Recommended build instruction Co-authored-by: Neo Zhang Jianyu --- README-sycl.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README-sycl.md b/README-sycl.md index e2d241b18..7af84cedc 100644 --- a/README-sycl.md +++ b/README-sycl.md @@ -250,7 +250,7 @@ export CPLUS_INCLUDE_DIR=/path/to/oneMKL/include:$CPLUS_INCLUDE_DIR # Build LLAMA with Nvidia BLAS acceleration through SYCL mkdir -p build && cd build -# Option 1: Use FP32 by default +# Option 1: Use FP32 (recommended for better performance in most cases) cmake .. -DLLAMA_SYCL=ON -DLLAMA_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx # Option 2: Use FP16 for better performance in long-prompt inference