Chranos/enginex-mlu370-vllm
1
0
Fork 0
forked from EngineX-Cambricon/enginex-mlu370-vllm
Code Pull Requests Activity

add qwen3

Browse Source
This commit is contained in:
Chranos
2026-02-04 17:22:39 +08:00
parent d1c0f68ab4
commit 8511fe8530
1932 changed files with 300426 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
vllm-v0.6.2/Dockerfile.hpu Normal file
View File

@@ -0,0 +1,18 @@
FROM vault.habana.ai/gaudi-docker/1.18.0/ubuntu22.04/habanalabs/pytorch-installer-2.4.0: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
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"]