Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update GPU Dockerimage (Cuda 11, Fix faiss) #836

Merged
merged 1 commit into from
Feb 17, 2021
Merged

Update GPU Dockerimage (Cuda 11, Fix faiss) #836

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 9 additions & 3 deletions Dockerfile-GPU
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,8 +1,9 @@
FROM nvidia/cuda:10.1-runtime
FROM nvidia/cuda:11.0-runtime-ubuntu20.04

WORKDIR /home/user

RUN apt-get update && apt-get install -y python3.7 python3.7-dev python3.7-distutils python3-pip curl git pkg-config cmake
RUN apt-get update && apt-get install -y software-properties-common && add-apt-repository ppa:deadsnakes/ppa
RUN apt-get update && apt-get install -y python3.7 python3.7-dev python3.7-distutils python3-pip curl git pkg-config cmake swig

ENV LC_ALL=C.UTF-8
ENV LANG=C.UTF-8
Expand All @@ -18,6 +19,11 @@ COPY haystack /home/user/haystack
COPY setup.py requirements.txt README.md /home/user/
RUN pip3 install numpy scipy Cython

# Install PyTorch for CUDA 11
RUN pip3 install torch==1.7.1+cu110 -f https://download.pytorch.org/whl/torch_stable.html
# Install faiss separately as building latest versions can cause trouble with swig
RUN pip3 install faiss-cpu==1.6.3

RUN pip3 install -r requirements.txt
RUN pip3 install -e .

Expand All @@ -36,4 +42,4 @@ COPY rest_api /home/user/rest_api
EXPOSE 8000

# cmd for running the API (note: "--preload" is not working with cuda)
CMD ["gunicorn", "rest_api.application:app", "-b", "0.0.0.0", "-k", "uvicorn.workers.UvicornWorker", "--workers", "1", "--timeout", "180"]
CMD ["gunicorn", "rest_api.application:app", "-b", "0.0.0.0", "-k", "uvicorn.workers.UvicornWorker", "--workers", "1", "--timeout", "180"]