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

readme: add -DAMDGPU_TARGETS to linux cmake invocation

Browse source
This commit is contained in:
person4268 2023-12-13 17:30:04 -05:00 • committed by GitHub
parent 948ff137ec
commit e2286a2025
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -425,7 +425,7 @@ Building the program with BLAS support may lead to some performance improvements
```bash
mkdir build
cd build
CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++ cmake .. -DLLAMA_HIPBLAS=ON
CC=/opt/rocm/llvm/bin/clang CXX=/opt/rocm/llvm/bin/clang++ cmake .. -DAMDGPU_TARGETS=gfx1100 -DLLAMA_HIPBLAS=ON
cmake --build .
```
- Using `CMake` for Windows (using x64 Native Tools Command Prompt for VS):