mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-30 16:07:17 +01:00
34 lines
1.1 KiB
Docker
34 lines
1.1 KiB
Docker
ARG UBUNTU_VERSION=22.04
|
|
# This needs to generally match the container host's environment.
|
|
ARG CUDA_VERSION=12.6.0
|
|
# Target the CUDA build image
|
|
ARG BASE_CUDA_DEV_CONTAINER=nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION}
|
|
|
|
FROM ${BASE_CUDA_DEV_CONTAINER} AS build
|
|
|
|
# CUDA architecture to build for (defaults to all supported archs)
|
|
ARG CUDA_DOCKER_ARCH=default
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y build-essential cmake python3 python3-pip git libcurl4-openssl-dev libgomp1
|
|
|
|
COPY requirements.txt requirements.txt
|
|
COPY requirements requirements
|
|
|
|
RUN pip install --upgrade pip setuptools wheel \
|
|
&& pip install -r requirements.txt
|
|
|
|
WORKDIR /app
|
|
|
|
COPY . .
|
|
|
|
# Use the default CUDA archs if not specified
|
|
RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
|
|
export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
|
|
fi && \
|
|
cmake -B build -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DLLAMA_CURL=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
|
|
cmake --build build --config Release -j$(nproc) && \
|
|
cp build/bin/* .
|
|
|
|
ENTRYPOINT ["/app/.devops/tools.sh"]
|