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 12, 09:45 UTC
[CI/Build] Rework CPU multimodal processor test (#29684)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Isotr0py committed
Nov 29, 2025 at 01:10 UTC
d40c854009225adde370be30a1a876afe1e5b529
1 file changed
+12
-2
.buildkite/test-pipeline.yaml
+12
-2
@@ -820,14 +820,24 @@ steps:
820
commands:
821
- pytest -v -s models/language/pooling_mteb_test
822
823
-- label: Multi-Modal Processor Test # 44min
823
+- label: Multi-Modal Processor Test (CPU)
824
+ timeout_in_minutes: 60
825
+ source_file_dependencies:
826
+ - vllm/
827
+ - tests/models/multimodal
828
+ no_gpu: true
829
+ commands:
830
+ - pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
831
+ - pytest -v -s models/multimodal/processing --ignore models/multimodal/processing/test_tensor_schema.py
832
+
833
+- label: Multi-Modal Processor Test
834
timeout_in_minutes: 60
835
source_file_dependencies:
836
- vllm/
837
- tests/models/multimodal
838
commands:
839
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
830
- - pytest -v -s models/multimodal/processing
840
+ - pytest -v -s models/multimodal/processing/test_tensor_schema.py
841
842
- label: Multi-Modal Models Test (Standard) # 60min
843
timeout_in_minutes: 80