forked from vllm-project/vllm
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Dockerfile.tpu
32 lines (26 loc) · 1.18 KB
/
Dockerfile.tpu
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
29
30
31
32
ARG NIGHTLY_DATE="20241017"
ARG BASE_IMAGE="us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/xla:nightly_3.10_tpuvm_$NIGHTLY_DATE"
FROM $BASE_IMAGE
WORKDIR /workspace/vllm
# Install some basic utilities
RUN apt-get update && apt-get install -y \
git \
ffmpeg libsm6 libxext6 libgl1
# Install the TPU and Pallas dependencies.
RUN --mount=type=cache,target=/root/.cache/pip \
python3 -m pip install torch_xla[tpu] -f https://storage.googleapis.com/libtpu-releases/index.html
RUN --mount=type=cache,target=/root/.cache/pip \
python3 -m pip install torch_xla[pallas] -f https://storage.googleapis.com/jax-releases/jax_nightly_releases.html -f https://storage.googleapis.com/jax-releases/jaxlib_nightly_releases.html
# Build vLLM.
COPY . .
ARG GIT_REPO_CHECK=0
RUN --mount=type=bind,source=.git,target=.git \
if [ "$GIT_REPO_CHECK" != 0 ]; then bash tools/check_repo.sh; fi
ENV VLLM_TARGET_DEVICE="tpu"
RUN --mount=type=cache,target=/root/.cache/pip \
--mount=type=bind,source=.git,target=.git \
python3 -m pip install \
'cmake>=3.26' ninja packaging 'setuptools-scm>=8' wheel jinja2 \
-r requirements-tpu.txt
RUN python3 setup.py develop
CMD ["/bin/bash"]