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

[Misc] Update dockerfile for CPU to cover protobuf installation (#7182)

Browse Source
This commit is contained in:
PHILO-HE 2024-08-16 01:03:01 +08:00 committed by GitHub
parent 9c1f78d5d6
commit f4da5f7b6d
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.buildkite/run-cpu-test.sh
View File

@ -22,7 +22,7 @@ docker exec cpu-test-avx2 bash -c "python3 examples/offline_inference.py"
# Run basic model test # Run basic model test
docker exec cpu-test bash -c " docker exec cpu-test bash -c "
pip install pytest Pillow protobuf pip install pytest
pytest -v -s tests/models -m \"not vlm\" --ignore=tests/models/test_embedding.py --ignore=tests/models/test_oot_registration.py --ignore=tests/models/test_registry.py --ignore=tests/models/test_jamba.py --ignore=tests/models/test_danube3_4b.py" # Mamba and Danube3-4B on CPU is not supported pytest -v -s tests/models -m \"not vlm\" --ignore=tests/models/test_embedding.py --ignore=tests/models/test_oot_registration.py --ignore=tests/models/test_registry.py --ignore=tests/models/test_jamba.py --ignore=tests/models/test_danube3_4b.py" # Mamba and Danube3-4B on CPU is not supported
# online inference # online inference

2
Dockerfile.cpu
View File

@ -13,7 +13,7 @@ RUN --mount=type=cache,target=/var/cache/apt \
RUN --mount=type=cache,target=/root/.cache/pip \ RUN --mount=type=cache,target=/root/.cache/pip \
pip install intel-openmp pip install intel-openmp
ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/usr/local/lib/libiomp5.so:$LD_PRELOAD" ENV LD_PRELOAD="/usr/lib/x86_64-linux-gnu/libtcmalloc_minimal.so.4:/usr/local/lib/libiomp5.so"
RUN echo 'ulimit -c 0' >> ~/.bashrc RUN echo 'ulimit -c 0' >> ~/.bashrc

1
requirements-common.txt
View File

@ -6,6 +6,7 @@ tqdm
py-cpuinfo py-cpuinfo
transformers >= 4.43.2 # Required for Chameleon and Llama 3.1 hotfox. transformers >= 4.43.2 # Required for Chameleon and Llama 3.1 hotfox.
tokenizers >= 0.19.1 # Required for Llama 3. tokenizers >= 0.19.1 # Required for Llama 3.
protobuf # Required by LlamaTokenizer.
fastapi fastapi
aiohttp aiohttp
openai openai