phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-24 18:24:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge 2ab4fc96e4 into b82af5b826

Browse source
This commit is contained in:
Sunny Wan 2025-04-24 15:25:27 +08:00 • committed by GitHub
commit 512860bb8d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 22 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
litellm/llms/openai/openai.py
View file

@ -459,6 +459,7 @@ class OpenAIChatCompletion(BaseLLM, BaseOpenAILLM):
else:
headers = {}
response = raw_response.parse()
# raw_response.http_response.close()
return headers, response
except Exception as e:
if raw_response is not None:

21
tests/load_tests/test_memory_usage.py
View file

@ -83,6 +83,13 @@ async def make_text_completion_request():
api_base="https://exampleopenaiendpoint-production.up.railway.app/",
)
def make_streaming_completion_request():
return litellm.acompletion(
model="openai/gpt-4o",
messages=[{"role": "user", "content": "Test message for memory usage"}],
stream=True,
)
@pytest.mark.asyncio
@pytest.mark.skip(
@ -102,6 +109,20 @@ async def test_atext_completion_memory():
await run_memory_test(make_text_completion_request, "atext_completion")
@pytest.mark.skip(
reason="This test is too slow to run on every commit. We can use this after nightly release"
)
def test_streaming_completion_memory():
"""Test memory usage for streaming litellm.acompletion"""
run_memory_test(make_streaming_completion_request,"completion")
@pytest.mark.skip(
reason="This test is too slow to run on every commit. We can use this after nightly release"
)
def test_streaming_acompletion_memory():
"""Test memory usage for streaming litellm.atext_completion"""
run_memory_test(make_streaming_completion_request,"acompletion")
litellm_router = Router(
model_list=[
{