phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

(chore) update load test

Browse source
This commit is contained in:
ishaan-jaff 2024-01-19 08:52:17 -08:00
parent ced0fb1248
commit 54c84e15e6
2 changed files with 7 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

10
litellm/proxy/tests/load_test_completion.py
View file

@ -11,12 +11,10 @@ async def litellm_completion():
# Your existing code for litellm_completion goes here
try:
response = await litellm_client.chat.completions.create(
model="Azure OpenAI GPT-4 Canada-East (External)",
stream=True,
model="azure-gpt-3.5",
messages=[{"role": "user", "content": f"This is a test: {uuid.uuid4()}"}],
)
async for chunk in response:
print(chunk)
print(response)
return response
except Exception as e:
@ -27,9 +25,9 @@ async def litellm_completion():
async def main():
for i in range(1000000):
for i in range(150):
start = time.time()
n = 1000 # Number of concurrent tasks
n = 150 # Number of concurrent tasks
tasks = [litellm_completion() for _ in range(n)]
chat_completions = await asyncio.gather(*tasks)