phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 17:30:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: Support "stop" parameter in remote:vLLM

Browse source 
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
This commit is contained in:
Yuan Tang 2025-03-19 22:41:34 -04:00
parent f369871083
commit a1da09e166
No known key found for this signature in database
4 changed files with 34 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

24
tests/integration/inference/test_text_inference.py
View file

@ -99,6 +99,30 @@ def test_text_completion_streaming(client_with_models, text_model_id, test_case)
assert len(content_str) > 10
@pytest.mark.parametrize(
"test_case",
[
"inference:completion:stop_sequence",
],
)
def test_text_completion_stop_sequence(client_with_models, text_model_id, test_case):
skip_if_model_doesnt_support_completion(client_with_models, text_model_id)
tc = TestCase(test_case)
response = client_with_models.inference.completion(
content=tc["content"],
stream=True,
model_id=text_model_id,
sampling_params={
"max_tokens": 50,
"stop": ["1963"],
},
)
streamed_content = [chunk.delta for chunk in response]
content_str = "".join(streamed_content).lower().strip()
assert "1963" not in content_str
@pytest.mark.parametrize(
"test_case",
[