vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Recommended build instruction

Browse source 
Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com>
This commit is contained in:
Anas Ahouzi 2024-04-19 15:19:35 +02:00 • committed by GitHub
parent 8cf382b51c
commit 9a426b6a0b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README-sycl.md
View file

@ -250,7 +250,7 @@ export CPLUS_INCLUDE_DIR=/path/to/oneMKL/include:$CPLUS_INCLUDE_DIR
# Build LLAMA with Nvidia BLAS acceleration through SYCL # Build LLAMA with Nvidia BLAS acceleration through SYCL
mkdir -p build && cd build 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 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 # Option 2: Use FP16 for better performance in long-prompt inference