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.
35 lines
999 B
Docker
35 lines
999 B
Docker
ARG ONEAPI_VERSION=2024.1.1-devel-ubuntu22.04
|
|
|
|
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS build
|
|
|
|
ARG GGML_SYCL_F16=OFF
|
|
RUN apt-get update && \
|
|
apt-get install -y git libcurl4-openssl-dev
|
|
|
|
WORKDIR /app
|
|
|
|
COPY . .
|
|
|
|
RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
|
|
echo "GGML_SYCL_F16 is set" && \
|
|
export OPT_SYCL_F16="-DGGML_SYCL_F16=ON"; \
|
|
fi && \
|
|
echo "Building with dynamic libs" && \
|
|
cmake -B build -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON ${OPT_SYCL_F16} && \
|
|
cmake --build build --config Release --target llama-server
|
|
|
|
FROM intel/oneapi-basekit:$ONEAPI_VERSION AS runtime
|
|
|
|
RUN apt-get update && \
|
|
apt-get install -y libcurl4-openssl-dev curl
|
|
|
|
COPY --from=build /app/build/bin/llama-server /llama-server
|
|
|
|
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" ]
|