mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-30 08:42:00 +00:00
34 lines
742 B
Docker
34 lines
742 B
Docker
ARG UBUNTU_VERSION=22.04
|
|
|
|
# This needs to generally match the container host's environment.
|
|
ARG CUDA_VERSION=11.7.1
|
|
|
|
# Target the CUDA build image
|
|
ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
|
|
|
FROM ${BASE_CUDA_DEV_CONTAINER} as build
|
|
|
|
# Unless otherwise specified, we make a fat build.
|
|
ARG CUDA_DOCKER_ARCH=all
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y build-essential python3 python3-pip git
|
|
|
|
COPY requirements.txt requirements.txt
|
|
|
|
RUN pip install --upgrade pip setuptools wheel \
|
|
&& pip install -r requirements.txt
|
|
|
|
WORKDIR /app
|
|
|
|
COPY . .
|
|
|
|
# Set nvcc architecture
|
|
ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
|
|
# Enable cuBLAS
|
|
ENV LLAMA_CUBLAS=1
|
|
|
|
RUN make
|
|
|
|
ENTRYPOINT ["/app/.devops/tools.sh"]
|