youngkingdom/vllm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[V0 deprecation] Remove V0 HPU backend (#21131)

Browse Source 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
This commit is contained in:
Woosuk Kwon
2025-07-17 16:37:36 -07:00
committed by GitHub
parent ac9fb732a5
commit 4de7146351
27 changed files with 10 additions and 3926 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
docker/Dockerfile.hpu
View File

@ -1,21 +0,0 @@
FROM vault.habana.ai/gaudi-docker/1.20.1/ubuntu22.04/habanalabs/pytorch-installer-2.6.0:latest
COPY ./ /workspace/vllm
WORKDIR /workspace/vllm
RUN pip install -v -r requirements/hpu.txt
ENV no_proxy=localhost,127.0.0.1
ENV PT_HPU_ENABLE_LAZY_COLLECTIVES=true
RUN VLLM_TARGET_DEVICE=hpu python3 setup.py install
# install development dependencies (for testing)
RUN python3 -m pip install -e tests/vllm_test_utils
WORKDIR /workspace/
RUN ln -s /workspace/vllm/tests && ln -s /workspace/vllm/examples && ln -s /workspace/vllm/benchmarks
ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]