forked from HabanaAI/vllm-fork
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Dockerfile.openvino
28 lines (21 loc) · 941 Bytes
/
Dockerfile.openvino
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
# The vLLM Dockerfile is used to construct vLLM image that can be directly used
# to run the OpenAI compatible server.
FROM ubuntu:22.04 AS dev
RUN apt-get update -y && \
apt-get install -y \
git python3-pip \
ffmpeg libsm6 libxext6 libgl1
WORKDIR /workspace
COPY . .
ARG GIT_REPO_CHECK=0
RUN --mount=type=bind,source=.git,target=.git \
if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh ; fi
# install build requirements
RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" python3 -m pip install -r /workspace/requirements-build.txt
# build vLLM with OpenVINO backend
RUN PIP_EXTRA_INDEX_URL="https://download.pytorch.org/whl/cpu" VLLM_TARGET_DEVICE="openvino" python3 -m pip install /workspace
COPY examples/ /workspace/examples
COPY benchmarks/ /workspace/benchmarks
# install development dependencies (for testing)
RUN python3 -m pip install -e tests/vllm_test_utils
CMD ["/bin/bash"]