mirror of https://github.com/vllm-project/vllm
24 lines
830 B
Docker
24 lines
830 B
Docker
ARG NIGHTLY_DATE="20240726"
|
|
ARG BASE_IMAGE="us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/xla:nightly_3.10_tpuvm_$NIGHTLY_DATE"
|
|
|
|
FROM $BASE_IMAGE
|
|
WORKDIR /workspace
|
|
|
|
# Install aiohttp separately to avoid build errors.
|
|
RUN pip install aiohttp
|
|
# Install NumPy 1 instead of NumPy 2.
|
|
RUN pip install "numpy<2"
|
|
# Install the TPU and Pallas dependencies.
|
|
RUN pip install torch_xla[tpu] -f https://storage.googleapis.com/libtpu-releases/index.html
|
|
RUN 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
|
|
|
|
# Fix FastAPI dependence
|
|
RUN pip install "starlette<0.38.0"
|
|
|
|
# Build vLLM.
|
|
COPY . /workspace/vllm
|
|
ENV VLLM_TARGET_DEVICE="tpu"
|
|
RUN cd /workspace/vllm && python setup.py develop
|
|
|
|
CMD ["/bin/bash"]
|