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

[ci] Sync test areas with test-pipeline.yaml and enable new pipeline generator (#33080)

Browse Source 
Signed-off-by: Kevin H. Luu <khluu000@gmail.com>
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Kevin Luu <khluu@Kevins-MacBook-Pro.local>
This commit is contained in:
Kevin H. Luu
2026-01-26 12:28:20 -08:00
committed by GitHub
parent 43a013c3a2
commit ebe0ba91db
24 changed files with 528 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.buildkite/test_areas/quantization.yaml
View File

@@ -16,14 +16,14 @@ steps:
# https://github.com/pytorch/ao/issues/2919, we'll have to skip new torchao tests for now
# we can only upgrade after this is resolved
# TODO(jerryzh168): resolve the above comment
- uv pip install --system torchao==0.13.0 --index-url https://download.pytorch.org/whl/cu129
- uv pip install --system torchao==0.14.1 --index-url https://download.pytorch.org/whl/cu129
- uv pip install --system conch-triton-kernels
- VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py
- label: Quantized MoE Test (B200)
timeout_in_minutes: 60
working_dir: "/vllm-workspace/"
gpu: b200
device: b200
source_file_dependencies:
- tests/quantization/test_blackwell_moe.py
- vllm/model_executor/models/deepseek_v2.py