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

fix pip

Browse source
This commit is contained in:
Robert Washbourne 2023-11-24 01:50:07 -05:00
parent 63961c0e75
commit af5a4371da
1 changed files with 6 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

14
.devops/main-cuda.Dockerfile
View file

@ -23,11 +23,11 @@ COPY . .
ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH} ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
# Enable cuBLAS # Enable cuBLAS
ENV LLAMA_CUBLAS=1 ENV LLAMA_CUBLAS=1
# ENV LLAMA_CUDA_MMV_Y=2 ENV LLAMA_CUDA_MMV_Y=2
# ENV LLAMA_CUDA_DMMV_X=64 ENV LLAMA_CUDA_DMMV_X=64
# ENV LLAMA_CUDA_F16=true ENV LLAMA_CUDA_F16=true
RUN make RUN make -j
# Accept the build argument into an environment variable # Accept the build argument into an environment variable
ARG MODEL_URL ARG MODEL_URL
@ -36,16 +36,14 @@ ENV MODEL_URL=${MODEL_URL}
# Use the environment variable to download the model # Use the environment variable to download the model
RUN wget $MODEL_URL -O /model.gguf RUN wget $MODEL_URL -O /model.gguf
WORKDIR /install
RUN apt-get install -y python3 python3-pip
RUN pip install --prefix /install runpod aiohttp
FROM ${BASE_CUDA_RUN_CONTAINER} as runtime FROM ${BASE_CUDA_RUN_CONTAINER} as runtime
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y python3 python3-pip \ apt-get install -y python3 python3-pip \
&& rm -rf /var/lib/apt/lists/* && rm -rf /var/lib/apt/lists/*
RUN pip install runpod aiohttp
COPY --from=build /app/.devops/handler.py /handler.py COPY --from=build /app/.devops/handler.py /handler.py
COPY --from=build /app/server /server COPY --from=build /app/server /server
COPY --from=build /model.gguf model.gguf COPY --from=build /model.gguf model.gguf