Dockerfile

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}
# Target the CUDA runtime image
ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${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 git cmake libcurl4-openssl-dev

WORKDIR /app

RUN git clone https://github.com/ggerganov/llama.cpp --depth 1 .

# Use the default CUDA archs if not specified
RUN LDFLAGS="-cudart=static -lcublas_static -lcublasLt_static -lculibos" GGML_CUDA=1 LLAMA_CURL=1 LLAMA_CUDA=1 make llama-server -j


FROM node:22 AS runtime

RUN npm i -g http-server

WORKDIR /app
COPY --from=build /app/llama-server /app/llama-server

CMD ["http-server", "/app", "-p", "7860", "-c-1"]