litellm/docs/my-website/docs/proxy/load_balancing.md

66 lines
No EOL
2.4 KiB
Markdown

# Multiple Instances
Load balance multiple instances of the same model
The proxy will handle routing requests (using LiteLLM's Router). **Set `rpm` in the config if you want maximize throughput**
:::info
For more details on routing strategies / params, see [Routing](../routing.md)
:::
## Load Balancing using multiple litellm instances (Kubernetes, Auto Scaling)
LiteLLM Proxy supports sharing rpm/tpm shared across multiple litellm instances, pass `redis_host`, `redis_password` and `redis_port` to enable this. (LiteLLM will use Redis to track rpm/tpm usage )
Example config
```yaml
model_list:
- model_name: gpt-3.5-turbo
litellm_params:
model: azure/<your-deployment-name>
api_base: <your-azure-endpoint>
api_key: <your-azure-api-key>
rpm: 6 # Rate limit for this deployment: in requests per minute (rpm)
- model_name: gpt-3.5-turbo
litellm_params:
model: azure/gpt-turbo-small-ca
api_base: https://my-endpoint-canada-berri992.openai.azure.com/
api_key: <your-azure-api-key>
rpm: 6
router_settings:
redis_host: <your redis host>
redis_password: <your redis password>
redis_port: 1992
```
## Router settings on config - routing_strategy, model_group_alias
litellm.Router() settings can be set under `router_settings`. You can set `model_group_alias`, `routing_strategy`, `num_retries`,`timeout` . See all Router supported params [here](https://github.com/BerriAI/litellm/blob/1b942568897a48f014fa44618ec3ce54d7570a46/litellm/router.py#L64)
Example config with `router_settings`
```yaml
model_list:
- model_name: gpt-3.5-turbo
litellm_params:
model: azure/<your-deployment-name>
api_base: <your-azure-endpoint>
api_key: <your-azure-api-key>
rpm: 6 # Rate limit for this deployment: in requests per minute (rpm)
- model_name: gpt-3.5-turbo
litellm_params:
model: azure/gpt-turbo-small-ca
api_base: https://my-endpoint-canada-berri992.openai.azure.com/
api_key: <your-azure-api-key>
rpm: 6
router_settings:
model_group_alias: {"gpt-4": "gpt-3.5-turbo"} # all requests with `gpt-4` will be routed to models with `gpt-3.5-turbo`
routing_strategy: least-busy # Literal["simple-shuffle", "least-busy", "usage-based-routing", "latency-based-routing"]
num_retries: 2
timeout: 30 # 30 seconds
redis_host: <your redis host>
redis_password: <your redis password>
redis_port: 1992
```