diff options
| author | Mark Fairbairn <thebaron88@gmail.com> | 2024-04-07 19:52:19 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-04-07 20:52:19 +0200 |
| commit | 855f54402e866ed19d8d675b56a81c844c64b325 (patch) | |
| tree | 44b3664516b9527a9a90576150354d49ba9567f2 | |
| parent | b909236c0bf0b6e872af95df9490492ecec310ac (diff) | |
Change Windows AMD example to release build to make inference much faster. (#6525)
| -rw-r--r-- | README.md | 2 |
1 files changed, 1 insertions, 1 deletions
@@ -519,7 +519,7 @@ Building the program with BLAS support may lead to some performance improvements set PATH=%HIP_PATH%\bin;%PATH% mkdir build cd build - cmake -G Ninja -DAMDGPU_TARGETS=gfx1100 -DLLAMA_HIPBLAS=ON -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ .. + cmake -G Ninja -DAMDGPU_TARGETS=gfx1100 -DLLAMA_HIPBLAS=ON -DCMAKE_C_COMPILER=clang -DCMAKE_CXX_COMPILER=clang++ -DCMAKE_BUILD_TYPE=Release .. cmake --build . ``` Make sure that `AMDGPU_TARGETS` is set to the GPU arch you want to compile for. The above example uses `gfx1100` that corresponds to Radeon RX 7900XTX/XT/GRE. You can find a list of targets [here](https://llvm.org/docs/AMDGPUUsage.html#processors) |