EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[CI] cleanup single/multi-card test (#5623)

Browse Source 
1. speed up e2e light test.
2. create `2-cards` and `4-cards` folder in multicard
3. move ops to nightly
4. run test in Alphabetical Order

- vLLM version: v0.13.0
- vLLM main:
8be6432bda

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2026-01-07 14:13:34 +08:00
committed by GitHub
parent 1afbc01ed4
commit 6f7a81cd9f
30 changed files with 114 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docs/source/developer_guide/contribution/testing.md
View File

@@ -231,13 +231,13 @@ VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/singlecard/test_offline_inference.
```bash
cd /vllm-workspace/vllm-ascend/
# Run all the single card tests
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/multicard/
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/singlecard/
# Run a certain test script
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/multicard/test_dynamic_npugraph_batchsize.py
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/singlecard/test_aclgraph_accuracy.py
# Run a certain case in test script
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/multicard/test_offline_inference.py::test_models
VLLM_USE_MODELSCOPE=true pytest -sv tests/e2e/singlecard/test_aclgraph_accuracy.py::test_models_output
```
::::