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 5, 07:15 UTC
[ROCm][CI/Build] Fix memory cleanup in MM test (#39555)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Andreas Karatzas committed
Apr 11, 2026 at 22:13 UTC
0f7be0f2f76814f80f9091220a5fbbb53912ad00
1 file changed
+6
-3
.buildkite/test-amd.yaml
+6
-3
@@ -1073,7 +1073,8 @@ steps:
1073
- tests/models/multimodal/test_mapping.py
1074
commands:
1075
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
1076
- - pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/processing
1076
+ - pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/generation/test_memory_leak.py --ignore models/multimodal/processing
1077
+ - pytest -v -s models/multimodal/generation/test_memory_leak.py -m core_model
1078
- cd .. && VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -v -s tests/models/multimodal/generation/test_whisper.py -m core_model
1079
1080
@@ -2298,7 +2299,8 @@ steps:
2299
- tests/models/multimodal/generation
2300
commands:
2301
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
2301
- - pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/processing
2302
+ - pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/generation/test_memory_leak.py --ignore models/multimodal/processing
2303
+ - pytest -v -s models/multimodal/generation/test_memory_leak.py -m core_model
2304
- cd .. && VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -v -s tests/models/multimodal/generation/test_whisper.py -m core_model
2305
2306
@@ -3452,7 +3454,8 @@ steps:
3454
- tests/models/multimodal/generation
3455
commands:
3456
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
3455
- - pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/processing
3457
+ - pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/generation/test_memory_leak.py --ignore models/multimodal/processing
3458
+ - pytest -v -s models/multimodal/generation/test_memory_leak.py -m core_model
3459
- cd .. && VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -v -s tests/models/multimodal/generation/test_whisper.py -m core_model
3460
3461