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"