biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Frontend] Separate pooling APIs in offline inference (#11129)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2024-12-13 18:40:07 +08:00
committed by GitHub
parent f93bf2b189
commit eeec9e3390
21 changed files with 669 additions and 304 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
tests/entrypoints/openai/test_score.py
View File

@@ -39,8 +39,8 @@ async def test_text_1_str_text_2_list(server: RemoteOpenAIServer,
assert score.id is not None
assert score.data is not None
assert len(score.data) == 2
assert score.data[0].score[0] <= 0.01
assert score.data[1].score[0] >= 0.9
assert score.data[0].score <= 0.01
assert score.data[1].score >= 0.9
@pytest.mark.asyncio
@@ -67,8 +67,8 @@ async def test_text_1_list_text_2_list(server: RemoteOpenAIServer,
assert score.id is not None
assert score.data is not None
assert len(score.data) == 2
assert score.data[0].score[0] <= 0.01
assert score.data[1].score[0] >= 0.9
assert score.data[0].score <= 0.01
assert score.data[1].score >= 0.9
@pytest.mark.asyncio
@@ -90,4 +90,4 @@ async def test_text_1_str_text_2_str(server: RemoteOpenAIServer,
assert score.id is not None
assert score.data is not None
assert len(score.data) == 1
assert score.data[0].score[0] >= 0.9
assert score.data[0].score >= 0.9