8000 Merge pull request #498 from ctejada85/windows-pip-install · MobinX/llama-cpp-python@a05cfaf · GitHub
[go: up one dir, main page]

Skip to content
< 10000 /react-partial>

Commit a05cfaf

Browse files
authored
Merge pull request abetlen#498 from ctejada85/windows-pip-install
Added info to set ENV variables in PowerShell
2 parents c9985ab + b24b10e commit a05cfaf

File tree

1 file changed

+21
-0
lines changed

1 file changed

+21
-0
lines changed

README.md

Lines changed: 21 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -71,6 +71,27 @@ To install with Metal (MPS), set the `LLAMA_METAL=on` environment variable befor
7171
CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install llama-cpp-python
7272
```
7373

74+
#### Windows remarks
75+
76+
To set the variables `CMAKE_ARGS` and `FORCE_CMAKE` in PowerShell, follow the next steps (Example using, OpenBLAS):
77+
78+
```ps
79+
$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"
80+
```
81+
82+
```ps
83+
$env:FORCE_CMAKE = 1
84+
```
85+
86+
Then, call `pip` after setting the variables:
87+
```
88+
pip install llama-cpp-python
89+
```
90+
91+
See the above instructions and set `CMAKE_ARGS` to the BLAS backend you want to use.
92+
93+
#### MacOS remarks
94+
7495
Detailed MacOS Metal GPU install documentation is available at [docs/install/macos.md](docs/install/macos.md)
7596

7697
## High-level API

0 commit comments

Comments
 (0)
0