scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-08 22:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

docs(load_test.md): cleanup docs

Browse source
This commit is contained in:
Krrish Dholakia 2024-04-29 16:27:58 -07:00
parent af6a21f27c
commit 77f155d158
1 changed files with 4 additions and 87 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

91
docs/my-website/docs/load_test.md
View file

@ -228,91 +228,7 @@ If you don't want to call a real LLM API endpoint, you can setup a fake openai s
:::
### 1. Setup Router
```python
from litellm import Router
import litellm
litellm.suppress_debug_info = True
litellm.set_verbose = False
import logging
logging.basicConfig(level=logging.CRITICAL)
import os, random, uuid, time, asyncio
os.environ["REDIS_SSL"] = "True"
# Model list for OpenAI and Anthropic models
model_list = [
{
"model_name": "fake-openai-endpoint",
"litellm_params": {
"model": "gpt-3.5-turbo",
"api_key": "my-fake-key",
"api_base": "http://0.0.0.0:8080",
"rpm": 100
},
},
{
"model_name": "fake-openai-endpoint",
"litellm_params": {
"model": "gpt-3.5-turbo",
"api_key": "my-fake-key",
"api_base": "http://0.0.0.0:8081",
"rpm": 100
},
},
]
router_1 = Router(model_list=model_list, num_retries=0, enable_pre_call_checks=True, redis_host=os.getenv("REDIS_HOST"), redis_port=os.getenv("REDIS_PORT"), redis_password=os.getenv("REDIS_PASSWORD"))
router_2 = Router(model_list=model_list, num_retries=0, enable_pre_call_checks=True, redis_host=os.getenv("REDIS_HOST"), redis_port=os.getenv("REDIS_PORT"), redis_password=os.getenv("REDIS_PASSWORD"))
async def router_completion_non_streaming():
try:
client: Router = random.sample([router_1, router_2], 1)[0] # randomly pick b/w clients
# print(f"client={client}")
response = await client.acompletion(
model="fake-openai-endpoint", # [CHANGE THIS] (if you call it something else on your proxy)
messages=[{"role": "user", "content": f"This is a test: {uuid.uuid4()}"}],
)
return response
except Exception as e:
# print(e)
return None
async def loadtest_fn():
start = time.time()
n = 500 # Number of concurrent tasks
tasks = [router_completion_non_streaming() for _ in range(n)]
chat_completions = await asyncio.gather(*tasks)
successful_completions = [c for c in chat_completions if c is not None]
print(n, time.time() - start, len(successful_completions))
def get_utc_datetime():
import datetime as dt
from datetime import datetime
if hasattr(dt, "UTC"):
return datetime.now(dt.UTC) # type: ignore
else:
return datetime.utcnow() # type: ignore
# Run the event loop to execute the async function
async def parent_fn():
for _ in range(10):
dt = get_utc_datetime()
current_minute = dt.strftime("%H-%M")
print(f"triggered new batch - {current_minute}")
await loadtest_fn()
await asyncio.sleep(10)
asyncio.run(parent_fn())
```
### 2. Test it!
### Code
Let's hit the router with 600 requests per minute.
@ -350,8 +266,8 @@ model_list = [
},
]
router_1 = Router(model_list=model_list, num_retries=0, enable_pre_call_checks=True, redis_host=os.getenv("REDIS_HOST"), redis_port=os.getenv("REDIS_PORT"), redis_password=os.getenv("REDIS_PASSWORD"))
router_2 = Router(model_list=model_list, num_retries=0, enable_pre_call_checks=True, redis_host=os.getenv("REDIS_HOST"), redis_port=os.getenv("REDIS_PORT"), redis_password=os.getenv("REDIS_PASSWORD"))
router_1 = Router(model_list=model_list, num_retries=0, enable_pre_call_checks=True, routing_strategy="usage-based-routing-v2", redis_host=os.getenv("REDIS_HOST"), redis_port=os.getenv("REDIS_PORT"), redis_password=os.getenv("REDIS_PASSWORD"))
router_2 = Router(model_list=model_list, num_retries=0, routing_strategy="usage-based-routing-v2", enable_pre_call_checks=True, redis_host=os.getenv("REDIS_HOST"), redis_port=os.getenv("REDIS_PORT"), redis_password=os.getenv("REDIS_PASSWORD"))
@ -439,6 +355,7 @@ router_settings:
redis_host: os.environ/REDIS_HOST ## 👈 IMPORTANT! Setup the proxy w/ redis
redis_password: os.environ/REDIS_PASSWORD
redis_port: os.environ/REDIS_PORT
routing_strategy: usage-based-routing-v2
```
### 2. Start proxy 2 instances