root/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-24 02:14:35 +00:00
Code Issues Actions 11 Packages Projects Releases Wiki Activity

Add info about CUDA_VISIBLE_DEVICES (#1682)

Browse Source
This commit is contained in:
Henri Vasserman 2023-06-03 16:35:20 +03:00 committed by GitHub
parent b5c85468a3
commit d8bd0013e8
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -310,6 +310,8 @@ Building the program with BLAS support may lead to some performance improvements
```
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.
The environment variable [`CUDA_VISIBLE_DEVICES`](https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars) can be used to specify which GPU(s) will be used.
- **CLBlast**
OpenCL acceleration is provided by the matrix multiplication kernels from the [CLBlast](https://github.com/CNugteren/CLBlast) project and custom kernels for ggml that can generate tokens on the GPU.
@ -348,7 +350,7 @@ Building the program with BLAS support may lead to some performance improvements
cmake --install . --prefix /some/path
```
Where `/some/path` is where the built library will be installed (default is `/usr/loca`l`).
Where `/some/path` is where the built library will be installed (default is `/usr/local`).
</details>
Building: