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

[CI](cp) skip bad UT test_models_chunked_prefill_with_empty_kvcache temporarily (#5919)

Browse Source 
Skip bad UT test_models_chunked_prefill_with_empty_kvcache temporarily,
which is inadaptable with main2main 20260114.
- vLLM version: v0.13.0
- vLLM main:
11b6af5280

Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
This commit is contained in:
Qiu
2026-01-15 15:50:06 +08:00
committed by GitHub
parent a25209252f
commit 72fee47cba
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
tests/e2e/multicard/4-cards/long_sequence/test_chunked_prefill.py
View File

@@ -87,6 +87,7 @@ def test_models_chunked_prefill_mixed_length_prompts_including_1_token(
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": "1"
})
@pytest.mark.parametrize("model", MODELS)
@pytest.mark.skip(reason="skip for bad adaptability with main2main")
def test_models_chunked_prefill_with_empty_kvcache(model: str):
TEST_ROPE_PARAMETERS = {
"rope_theta": 1000000,