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, 18:15 UTC
[ci] fix model tests (#7507)
youkaichao committed
Aug 14, 2024 at 01:01 UTC
d3d9cb6e4b8185b4e56e1dda92c6fc31cdc05de1
1 file changed
+2
-1
.buildkite/test-pipeline.yaml
+2
-1
@@ -159,7 +159,8 @@ steps:
159
- tests/models
160
commands:
161
- pip install -e ./plugins/vllm_add_dummy_model
162
- - pytest -v -s models -m \"not vlm\"
162
+ - pytest -v -s models/test_oot_registration.py # it needs a clean process
163
+ - pytest -v -s models -m \"not vlm\" --ignore=models/test_oot_registration.py
164
165
- label: Vision Language Models Test # 42min
166
mirror_hardwares: [amd]