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 cd08a02764
commit e6b5152e63
2 changed files with 7 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

5
litellm/proxy/proxy_config.yaml
View file

@ -57,12 +57,13 @@ model_list:
mode: embedding mode: embedding
litellm_settings: litellm_settings:
fallbacks: [{"openai-gpt-3.5": ["azure-gpt-3.5"]}] fallbacks: [{"openai-gpt-3.5": ["azure-gpt-3.5"]}]
success_callback: ['langfuse']
# cache: True # cache: True
# setting callback class # setting callback class
# callbacks: custom_callbacks.proxy_handler_instance # sets litellm.callbacks = [proxy_handler_instance] # callbacks: custom_callbacks.proxy_handler_instance # sets litellm.callbacks = [proxy_handler_instance]
general_settings: # general_settings:
master_key: sk-1234 # master_key: sk-1234
# database_type: "dynamo_db" # database_type: "dynamo_db"
# database_args: { # 👈 all args - https://github.com/BerriAI/litellm/blob/befbcbb7ac8f59835ce47415c128decf37aac328/litellm/proxy/_types.py#L190 # database_args: { # 👈 all args - https://github.com/BerriAI/litellm/blob/befbcbb7ac8f59835ce47415c128decf37aac328/litellm/proxy/_types.py#L190
# "billing_mode": "PAY_PER_REQUEST", # "billing_mode": "PAY_PER_REQUEST",

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