vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server : Fixed wrong function name in llamacpp server unit test (#11473)

Browse source 
The test_completion_stream_with_openai_library() function is actually with stream=False by default, and test_completion_with_openai_library() with stream=True
This commit is contained in:
peidaqi 2025-01-28 16:03:42 -07:00 • committed by GitHub
parent d0c08040b6
commit cf8cc856d7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/server/tests/unit/test_completion.py
View file

@ -87,7 +87,7 @@ def test_completion_stream_vs_non_stream():
assert content_stream == res_non_stream.body["content"]
def test_completion_stream_with_openai_library():
def test_completion_with_openai_library():
global server
server.start()
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1")
@ -102,7 +102,7 @@ def test_completion_stream_with_openai_library():
assert match_regex("(going|bed)+", res.choices[0].text)
def test_completion_with_openai_library():
def test_completion_stream_with_openai_library():
global server
server.start()
client = OpenAI(api_key="dummy", base_url=f"http://{server.server_host}:{server.server_port}/v1")