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

[Bugfix] fix xlite decode-only e2e test (#5354)

Browse Source 
### What this PR does / why we need it?
fix xlite decode-only e2e test, xlite decode-only mode utilizes
aclgraph's prefill and will be affected by aclgraph, so shortened test
length.

- vLLM version: release/v0.13.0
- vLLM main:
bc0a5a0c08

Signed-off-by: changdawei1 <changdawei3@huawei.com>
Co-authored-by: changdawei1 <changdawei3@huawei.com>
This commit is contained in:
Magnus
2025-12-25 16:30:17 +08:00
committed by GitHub
parent d752c030e9
commit 59f11dd1cb
1 changed files with 5 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
tests/e2e/singlecard/test_xlite.py
View File

@@ -36,7 +36,7 @@ MODELS = [
@pytest.mark.parametrize("model", MODELS)
@pytest.mark.parametrize("max_tokens", [32])
@pytest.mark.parametrize("max_tokens", [15])
def test_models_with_xlite_decode_only(
model: str,
max_tokens: int,
@@ -61,10 +61,10 @@ def test_models_with_xlite_decode_only(
vllm_xlite_outputs_list[idx][1])
vllm_xlite_answers = [
"Hello, my name is Lina. I'm a 22-year-old student from China. I'm interested in studying in the US. I'm looking for a job in the",
'The president of the United States is the same as the president of the United Nations. This is because the president of the United States is the same as the president of the United Nations. The president',
'The capital of France is Paris. The capital of Italy is Rome. The capital of Spain is Madrid. The capital of China is Beijing. The capital of Japan is Tokyo. The capital',
'The future of AI is not just a technological challenge but a profound transformation of how we live, work, and interact with the world. As we stand at the intersection of artificial intelligence and'
"Hello, my name is Lina. I'm a 22-year-old student from China.",
'The president of the United States is the same as the president of the United Nations. This is because the president',
'The capital of France is Paris. The capital of Italy is Rome. The capital of Spain is Madrid',
'The future of AI is not just a technological challenge but a profound transformation of how we live, work'
]
vllm_eager_outputs_list = []