biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[CI] Shard Multi-Modal Models (Standard) into 4 parallel jobs (#37014)

Browse Source 
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Kevin H. Luu
2026-03-14 01:26:54 -07:00
committed by GitHub
parent ffa5d74f15
commit 600a039f57
1 changed files with 48 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
.buildkite/test_areas/models_multimodal.yaml
View File

@@ -2,15 +2,59 @@ group: Models - Multimodal
depends_on:
- image-build
steps:
- label: Multi-Modal Models (Standard) # 60min
timeout_in_minutes: 80
- label: "Multi-Modal Models (Standard) 1: qwen2"
timeout_in_minutes: 45
source_file_dependencies:
- vllm/
- tests/models/multimodal
commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
- pip freeze | grep -E 'torch'
- pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/processing
- pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen2"
- pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: "Multi-Modal Models (Standard) 2: qwen3 + gemma"
timeout_in_minutes: 45
source_file_dependencies:
- vllm/
- tests/models/multimodal
commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
- pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen3 or gemma"
- pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: "Multi-Modal Models (Standard) 3: llava + qwen2_vl"
timeout_in_minutes: 45
source_file_dependencies:
- vllm/
- tests/models/multimodal
commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
- pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "not qwen2 and not qwen3 and not gemma"
- pytest -v -s models/multimodal/generation/test_qwen2_vl.py -m core_model
mirror:
amd:
device: mi325_1
depends_on:
- image-build-amd
- label: "Multi-Modal Models (Standard) 4: other + whisper"
timeout_in_minutes: 45
source_file_dependencies:
- vllm/
- tests/models/multimodal
commands:
- pip install git+https://github.com/TIGER-AI-Lab/Mantis.git
- 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
- cd .. && VLLM_WORKER_MULTIPROC_METHOD=spawn pytest -v -s tests/models/multimodal/generation/test_whisper.py -m core_model # Otherwise, mp_method="spawn" doesn't work
mirror:
amd: