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

Merge pull request #235 from Pipboyguy/main

Browse source 
Decrement CUDA version and bump Ubuntu
This commit is contained in:
Andrei 2023-05-18 13:42:04 -04:00 committed by GitHub
commit 69f9d50090
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 3 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
Dockerfile.cuda
View file

@ -1,4 +1,5 @@
FROM nvidia/cuda:12.1.1-devel-ubuntu20.04
ARG CUDA_VERSION=12.1.1
FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu22.04
# We need to set the host to 0.0.0.0 to allow outside access
ENV HOST 0.0.0.0
@ -12,4 +13,4 @@ RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fa
RUN LLAMA_CUBLAS=1 python3 setup.py develop
# Run the server
CMD python3 -m llama_cpp.server
CMD python3 -m llama_cpp.server