[Bugfix][Test] fix Qwen3-omni OOM reliability and drop voxcpm2 stability/reliability test cases (#6299)

Signed-off-by: zhumingjue <zhumingjue@huawei.com>
This commit is contained in:
zhumingjue138 authored and GitHub committed 2026-08-18 17:36:08 +08:00
1 parent 0a1846aa45
commit cd9ae66b3a
9 files changed
+5 -601

No files matched your search

@@ -65,7 +65,7 @@ More failure modes (for example, network jitter and network interruption) will b
## Source of Conclusions
The behaviors and conclusions above are summarized from current fault injection validation results on **`Qwen3-Omni`**, **`Wan2.2`**, **`HunyuanImage-3.0-Instruct`** (DiT-only, `/v1/images/generations`), and **`VoxCPM2`** (`/v1/audio/speech`). Automated coverage lives under `tests/dfx/reliability/` (`test_reliability_qwen3_omni.py`, `test_reliability_wan22.py`, `test_reliability_hunyuan_image.py`, `test_reliability_voxcpm2.py`) and runs weekly via `.buildkite/cuda/test-weekly.yml`.
The behaviors and conclusions above are summarized from current fault injection validation results on **`Qwen3-Omni`**, **`Wan2.2`**, and **`HunyuanImage-3.0-Instruct`** (DiT-only, `/v1/images/generations`). Automated coverage lives under `tests/dfx/reliability/` (`test_reliability_qwen3_omni.py`, `test_reliability_wan22.py`, `test_reliability_hunyuan_image.py`) and runs weekly via `.buildkite/cuda/test-weekly.yml`.
### Example: `SIGTERM` fault injection log (Qwen3-Omni)