mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-02-26 16:14:10 +00:00
154e0d75fc
* Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
28 lines
519 B
Docker
28 lines
519 B
Docker
ARG UBUNTU_VERSION=22.04
|
|
|
|
FROM ubuntu:$UBUNTU_VERSION AS build
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y build-essential git libcurl4-openssl-dev curl
|
|
|
|
WORKDIR /app
|
|
|
|
COPY . .
|
|
|
|
ENV LLAMA_CURL=1
|
|
|
|
RUN make -j$(nproc) llama-server
|
|
|
|
FROM ubuntu:$UBUNTU_VERSION AS runtime
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y libcurl4-openssl-dev libgomp1
|
|
|
|
COPY --from=build /app/llama-server /llama-server
|
|
|
|
ENV LC_ALL=C.utf8
|
|
|
|
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
|
|
|
ENTRYPOINT [ "/llama-server" ]
|