mirror of
https://github.com/ikawrakow/ik_llama.cpp.git
synced 2026-01-26 17:20:01 +00:00
e68dabc242
server : handle models with missing EOS token (#8997) server : fix segfault on long system prompt (#8987) * server : fix segfault on long system prompt * server : fix parallel generation with very small batch sizes * server : fix typo in comment server : init stop and error fields of the result struct (#9026) server : fix duplicated n_predict key in the generation_settings (#8994) server : support reading arguments from environment variables (#9105) * server : support reading arguments from environment variables * add -fa and -dt * readme : specify non-arg env var server : add some missing env variables (#9116) * server : add some missing env variables * add LLAMA_ARG_HOST to server dockerfile * also add LLAMA_ARG_CONT_BATCHING Credits are to the respective authors. Not a single merge conflict occurred. Compiled, then tested without bug.
32 lines
942 B
Docker
32 lines
942 B
Docker
ARG UBUNTU_VERSION=jammy
|
|
|
|
FROM ubuntu:$UBUNTU_VERSION AS build
|
|
|
|
# Install build tools
|
|
RUN apt update && apt install -y git build-essential cmake wget
|
|
|
|
# Install Vulkan SDK and cURL
|
|
RUN wget -qO - https://packages.lunarg.com/lunarg-signing-key-pub.asc | apt-key add - && \
|
|
wget -qO /etc/apt/sources.list.d/lunarg-vulkan-jammy.list https://packages.lunarg.com/vulkan/lunarg-vulkan-jammy.list && \
|
|
apt update -y && \
|
|
apt-get install -y vulkan-sdk libcurl4-openssl-dev curl
|
|
|
|
# Build it
|
|
WORKDIR /app
|
|
COPY . .
|
|
RUN cmake -B build -DGGML_VULKAN=1 -DLLAMA_CURL=1 && \
|
|
cmake --build build --config Release --target llama-server
|
|
|
|
# Clean up
|
|
WORKDIR /
|
|
RUN cp /app/build/bin/llama-server /llama-server && \
|
|
rm -rf /app
|
|
|
|
ENV LC_ALL=C.utf8
|
|
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
|
ENV LLAMA_ARG_HOST=0.0.0.0
|
|
|
|
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
|
|
|
ENTRYPOINT [ "/llama-server" ]
|