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

Fix OpenBLAS Docker build

Browse source 
Current build produces the following:
`RuntimeError: Failed to load shared library '/usr/local/lib/python3.11/site-packages/llama_cpp/libllama.so': /usr/local/lib/python3.11/site-packages/llama_cpp/libllama.so: undefined symbol: cblas_sgemm`
This commit is contained in:
Ihsan Soydemir 2023-07-27 19:44:15 +02:00 committed by GitHub
parent ffa81218f6
commit 3e77eea7ec
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
docker/openblas_simple/Dockerfile
View file

@ -9,7 +9,7 @@ COPY . .
RUN apt update && apt install -y libopenblas-dev ninja-build build-essential RUN apt update && apt install -y libopenblas-dev ninja-build build-essential
RUN python -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings RUN python -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings
RUN LLAMA_OPENBLAS=1 pip install llama_cpp_python --verbose RUN CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama_cpp_python --verbose
# Run the server # Run the server
CMD python3 -m llama_cpp.server CMD python3 -m llama_cpp.server