mirror of
https://github.com/wassname/vllm.git
synced 2026-06-27 17:32:55 +08:00
[Hardware] Initial TPU integration (#5292)
This commit is contained in:
@@ -0,0 +1,19 @@
|
||||
ARG NIGHTLY_DATE="20240601"
|
||||
ARG BASE_IMAGE="us-central1-docker.pkg.dev/tpu-pytorch-releases/docker/xla:nightly_3.10_tpuvm_$NIGHTLY_DATE"
|
||||
|
||||
FROM $BASE_IMAGE
|
||||
|
||||
WORKDIR /workspace
|
||||
COPY . /workspace/vllm
|
||||
|
||||
ENV VLLM_TARGET_DEVICE="tpu"
|
||||
# Install aiohttp separately to avoid build errors.
|
||||
RUN pip install aiohttp
|
||||
# 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
|
||||
|
||||
# Build vLLM.
|
||||
RUN cd /workspace/vllm && python setup.py develop
|
||||
|
||||
CMD ["/bin/bash"]
|
||||
Reference in New Issue
Block a user