8000
We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 5e90adc commit 23e5130Copy full SHA for 23e5130
docker/cuda_simple/Dockerfile
@@ -21,7 +21,7 @@ ENV LLAMA_CUBLAS=1
21
RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings starlette-context
22
23
# Install llama-cpp-python (build with cuda)
24
-RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
+RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install -e .[server]
25
26
# Run the server
27
CMD python3 -m llama_cpp.server
0 commit comments