File size: 1,512 Bytes
395201c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 |
import time, asyncio
from openai import AsyncOpenAI
import uuid
import traceback
litellm_client = AsyncOpenAI(
api_key="test",
base_url="http://0.0.0.0:8000"
)
async def litellm_completion():
# Your existing code for litellm_completion goes here
try:
response = await litellm_client.chat.completions.create(
model="gpt-3.5-turbo",
messages=[{"role": "user", "content": f"This is a test: {uuid.uuid4()}"*180}], # this is about 4k tokens per request
)
print(response)
return response
except Exception as e:
# If there's an exception, log the error message
with open("error_log.txt", "a") as error_log:
error_log.write(f"Error during completion: {str(e)}\n")
pass
async def main():
start = time.time()
n = 60 # Send 60 concurrent requests, each with 4k tokens = 240k Tokens
tasks = [litellm_completion() for _ in range(n)]
chat_completions = await asyncio.gather(*tasks)
successful_completions = [c for c in chat_completions if c is not None]
# Write errors to error_log.txt
with open("error_log.txt", "a") as error_log:
for completion in chat_completions:
if isinstance(completion, str):
error_log.write(completion + "\n")
print(n, time.time() - start, len(successful_completions))
if __name__ == "__main__":
# Blank out contents of error_log.txt
open("error_log.txt", "w").close()
asyncio.run(main())
|