Create Dockerfile
Browse files- Dockerfile +27 -0
Dockerfile
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
ARG CUDA_IMAGE="12.1.1-devel-ubuntu22.04"
|
| 2 |
+
FROM nvidia/cuda:${CUDA_IMAGE}
|
| 3 |
+
|
| 4 |
+
# We need to set the host to 0.0.0.0 to allow outside access
|
| 5 |
+
ENV HOST 0.0.0.0
|
| 6 |
+
|
| 7 |
+
RUN apt-get update && apt-get upgrade -y \
|
| 8 |
+
&& apt-get install -y git build-essential \
|
| 9 |
+
python3 python3-pip gcc wget \
|
| 10 |
+
ocl-icd-opencl-dev opencl-headers clinfo \
|
| 11 |
+
libclblast-dev libopenblas-dev \
|
| 12 |
+
&& mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd
|
| 13 |
+
|
| 14 |
+
COPY . .
|
| 15 |
+
|
| 16 |
+
# setting build related env vars
|
| 17 |
+
ENV CUDA_DOCKER_ARCH=all
|
| 18 |
+
ENV LLAMA_CUBLAS=1
|
| 19 |
+
|
| 20 |
+
# Install depencencies
|
| 21 |
+
RUN python3 -m pip install --upgrade pip pytest cmake scikit-build setuptools fastapi uvicorn sse-starlette pydantic-settings starlette-context
|
| 22 |
+
|
| 23 |
+
# Install llama-cpp-python (build with cuda)
|
| 24 |
+
RUN CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
|
| 25 |
+
|
| 26 |
+
# Run the server
|
| 27 |
+
CMD python3 -m llama_cpp.server
|