xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 01:35:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build] Split pooling and generation extended language models tests in CI (#18705)

Browse Source 
Signed-off-by: Isotr0py <2037008807@qq.com>
This commit is contained in:
Isotr0py 2025-05-26 19:00:08 +08:00 committed by GitHub
parent 6d68030f1c
commit 0877750029
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
.buildkite/test-pipeline.yaml
View File

@ -486,16 +486,25 @@ steps:
- pip freeze | grep -E 'torch'
- pytest -v -s models/language -m core_model
- label: Language Models Test (Extended)
- label: Language Models Test (Extended Generation) # 1hr20min
mirror_hardwares: [amdexperimental]
optional: true
source_file_dependencies:
- vllm/
- tests/models/language
- tests/models/language/generation
commands:
# Install causal-conv1d for plamo2 models here, as it is not compatible with pip-compile.
- pip install 'git+https://github.com/Dao-AILab/causal-conv1d@v1.5.0.post8'
- pytest -v -s models/language -m 'not core_model'
- pytest -v -s models/language/generation -m 'not core_model'
- label: Language Models Test (Extended Pooling) # 36min
mirror_hardwares: [amdexperimental]
optional: true
source_file_dependencies:
- vllm/
- tests/models/language/pooling
commands:
- pytest -v -s models/language/pooling -m 'not core_model'
- label: Multi-Modal Models Test (Standard)
mirror_hardwares: [amdexperimental]