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

docs: add more details about using oneMKL and oneAPI for intel processors

Browse source
This commit is contained in:
tikikun 2023-12-22 15:52:47 +07:00
parent 47f0c7bf85
commit 08d94752aa
1 changed files with 2 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

5
README.md
View file

@ -384,8 +384,7 @@ Building the program with BLAS support may lead to some performance improvements
- #### Intel oneMKL
- Using manual oneAPI installation:
By default, `LLAMA_BLAS_VENDOR` is set to `Generic`, so if you already sourced intel environment script and assign `-DLLAMA_BLAS=ON` in cmake, the mkl version of Blas will automatically been selected. Otherwise please install oneAPI and follow the below steps:
By default, `LLAMA_BLAS_VENDOR` is set to `Generic`, so if you already sourced intel environment script and assign `-DLLAMA_BLAS=ON` in cmake, the mkl version of Blas will automatically been selected. Otherwise please install oneAPI and follow the below steps:
```bash
mkdir build
cd build
@ -395,7 +394,7 @@ Building the program with BLAS support may lead to some performance improvements
```
- Using oneAPI docker image:
If you do not want to source the environment vars and install oneAPI manually, you can also build the code using intel docker container: [oneAPI container](https://hub.docker.com/r/intel/oneapi-runtime)
If you do not want to source the environment vars and install oneAPI manually, you can also build the code using intel docker container: [oneAPI container](https://hub.docker.com/r/intel/oneapi-runtime)
```bash
mkdir build