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

docs: Remove references to deprecated opencl backend. Closes #1512

Browse source
This commit is contained in:
Andrei Betlen 2024-06-20 10:50:40 -04:00
parent 6c331909ca
commit d98a24a25b
2 changed files with 0 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
Makefile
View file

@ -24,9 +24,6 @@ build.debug:
build.cuda:
CMAKE_ARGS="-DLLAMA_CUDA=on" python3 -m pip install --verbose -e .
build.opencl:
CMAKE_ARGS="-DLLAMA_CLBLAST=on" python3 -m pip install --verbose -e .
build.openblas:
CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" python3 -m pip install --verbose -e .

11
README.md
View file

@ -165,17 +165,6 @@ pip install llama-cpp-python \
--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/metal
```
</details>
<details>
<summary>CLBlast (OpenCL)</summary>
To install with CLBlast, set the `LLAMA_CLBLAST=on` environment variable before installing:
```bash
CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python
```
</details>
<details>