@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / d47af2bc02
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 16, 23:15 UTC

[CI/Build] Disable LLaVA-NeXT CPU test (#5529)

Cyrus Leung committed Jun 15, 2024 at 00:27 UTC d47af2bc0208d50ed36ae877876c1d2eafdc933a
1 file changed +1 -2
.buildkite/run-cpu-test.sh
+1 -2
@@ -19,6 +19,5 @@ docker exec cpu-test bash -c "python3 examples/offline_inference.py"
19 # Run basic model test
20 docker exec cpu-test bash -c "cd tests;
21 pip install pytest Pillow protobuf
22 - bash ../.buildkite/download-images.sh
22 cd ../
24 - pytest -v -s tests/models --ignore=tests/models/test_llava.py --ignore=tests/models/test_embedding.py --ignore=tests/models/test_registry.py"
23 + pytest -v -s tests/models -m \"not llava\" --ignore=tests/models/test_embedding.py --ignore=tests/models/test_registry.py"