Skip to content

fix: missing CLBLAST documentation #1374

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

fix: missing CLBLAST documentation #1374

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
28086b5
fix: missing CLBLAS documentation
c-seeger May 9, 2023
7cea31c
fix: typo
c-seeger May 9, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -299,6 +299,22 @@ Building the program with BLAS support may lead to some performance improvements
cmake --build . --config Release
```

- clBLAS

This provides BLAS acceleration using the CUDA cores of your GPU. Make sure to have the clblast installed.
- Using `make`:
```bash
make LLAMA_CLBLAS=1
```
- Using `CMake`:

```bash
mkdir build
cd build
cmake .. -DLLAMA_CLBLAS=ON
cmake --build . --config Release
```

Note: Because llama.cpp uses multiple CUDA streams for matrix multiplication results [are not guaranteed to be reproducible](https://docs.nvidia.com/cuda/cublas/index.html#results-reproducibility). If you need reproducibility, set `GGML_CUDA_MAX_STREAMS` in the file `ggml-cuda.cu` to 1.

### Prepare Data & Run
Expand Down