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

[CI/Build] Test both text and token IDs in batched OpenAI Completions API (#5568)

Browse Source
This commit is contained in:
Cyrus Leung 2024-06-15 19:29:42 +08:00 committed by GitHub
parent 0e9164b40a
commit 81fbb3655f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 44 additions and 42 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
tests/entrypoints/test_openai_server.py
View File

@ -655,10 +655,12 @@ async def test_completion_stream_options(client: openai.AsyncOpenAI,
[MODEL_NAME, "zephyr-lora"],
)
async def test_batch_completions(client: openai.AsyncOpenAI, model_name: str):
# test both text and token IDs
for prompts in (["Hello, my name is"] * 2, [[0, 0, 0, 0, 0]] * 2):
# test simple list
batch = await client.completions.create(
model=model_name,
prompt=["Hello, my name is", "Hello, my name is"],
prompt=prompts,
max_tokens=5,
temperature=0.0,
)
@ -668,7 +670,7 @@ async def test_batch_completions(client: openai.AsyncOpenAI, model_name: str):
# test n = 2
batch = await client.completions.create(
model=model_name,
prompt=["Hello, my name is", "Hello, my name is"],
prompt=prompts,
n=2,
max_tokens=5,
temperature=0.0,
@ -688,7 +690,7 @@ async def test_batch_completions(client: openai.AsyncOpenAI, model_name: str):
# test streaming
batch = await client.completions.create(
model=model_name,
prompt=["Hello, my name is", "Hello, my name is"],
prompt=prompts,
max_tokens=5,
temperature=0.0,
stream=True,