mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 10:54:36 +00:00
75207b3a88
Some checks are pending
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-cuda.Dockerfile platforms:linux/amd64 tag:full-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full-musa.Dockerfile platforms:linux/amd64 tag:full-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/full.Dockerfile platforms:linux/amd64,linux/arm64 tag:full]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-cuda.Dockerfile platforms:linux/amd64 tag:light-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-intel.Dockerfile platforms:linux/amd64 tag:light-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli-musa.Dockerfile platforms:linux/amd64 tag:light-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-cli.Dockerfile platforms:linux/amd64,linux/arm64 tag:light]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-cuda.Dockerfile platforms:linux/amd64 tag:server-cuda]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-intel.Dockerfile platforms:linux/amd64 tag:server-intel]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server-musa.Dockerfile platforms:linux/amd64 tag:server-musa]) (push) Waiting to run
Publish Docker image / Push Docker image to Docker Hub (map[dockerfile:.devops/llama-server.Dockerfile platforms:linux/amd64,linux/arm64 tag:server]) (push) Waiting to run
Nix CI / nix-eval (macos-latest) (push) Waiting to run
Nix CI / nix-eval (ubuntu-latest) (push) Waiting to run
Nix CI / nix-build (macos-latest) (push) Waiting to run
Nix CI / nix-build (ubuntu-latest) (push) Waiting to run
flake8 Lint / Lint (push) Waiting to run
35 lines
1019 B
Docker
35 lines
1019 B
Docker
ARG ONEAPI_VERSION=2025.0.0-0-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_NATIVE=OFF -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" ]
|