llama-rpc-server / Dockerfile
rgerganov's picture
update
ce43a08
raw
history blame
437 Bytes
ARG UBUNTU_VERSION=22.04
# This needs to generally match the container host's environment.
ARG CUDA_VERSION=12.2.0
# Target the CUDA runtime image
ARG BASE_CUDA_RUN_CONTAINER=nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION}
FROM ${BASE_CUDA_RUN_CONTAINER} AS runtime
RUN apt-get update && \
apt-get install -y libgomp1
COPY rpc-server /rpc-server
EXPOSE 7860
ENTRYPOINT ["/rpc-server", "-p", "7860", "-H", "0.0.0.0"]