You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardexpand all lines: README.md
+16-2
Original file line number
Diff line number
Diff line change
@@ -752,15 +752,29 @@ pip install --upgrade pip
752
752
pip install -e .
753
753
754
754
# if you want to use the fastapi / openapi server
755
-
pip install -e .[server]
755
+
pip install -e '.[server]'
756
756
757
757
# to install all optional dependencies
758
-
pip install -e .[all]
758
+
pip install -e '.[all]'
759
759
760
760
# to clear the local build cache
761
761
make clean
762
762
```
763
763
764
+
Now try running the tests
765
+
766
+
```bash
767
+
pytest
768
+
```
769
+
770
+
There's a `Makefile` available with useful targets.
771
+
A typical workflow would look like this:
772
+
773
+
```bash
774
+
make build
775
+
make test
776
+
```
777
+
764
778
You can also test out specific commits of `llama.cpp` by checking out the desired commit in the `vendor/llama.cpp` submodule and then running `make clean` and `pip install -e .` again. Any changes in the `llama.h` API will require
765
779
changes to the `llama_cpp/llama_cpp.py` file to match the new API (additional changes may be required elsewhere).
0 commit comments