@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / d3d9cb6e4b
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, 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]