# LoRA Hot Swapping Guide

### :shaved\_ice: vLLM LoRA Hot Swapping / Dynamic LoRAs

To enable LoRA serving for at most 4 LoRAs at 1 time (these are hot swapped / changed), first set the environment flag to allow hot swapping:

```bash
export VLLM_ALLOW_RUNTIME_LORA_UPDATING=True
```

Then, serve it with LoRA support:

```bash
export VLLM_ALLOW_RUNTIME_LORA_UPDATING=True
vllm serve unsloth/Llama-3.1-8B-Instruct \
    --quantization fp8 \
    --kv-cache-dtype fp8 \
    --gpu-memory-utilization 0.8 \
    --max-model-len 65536 \
    --enable-lora \
    --max-loras 4 \
    --max-lora-rank 64
```

To load a LoRA dynamically (set the lora name as well), do:

```bash
curl -X POST http://localhost:8000/v1/load_lora_adapter \
    -H "Content-Type: application/json" \
    -d '{
        "lora_name": "LORA_NAME",
        "lora_path": "/path/to/LORA"
    }'
```

To remove it from the pool:

```bash
curl -X POST http://localhost:8000/v1/unload_lora_adapter \
    -H "Content-Type: application/json" \
    -d '{
        "lora_name": "LORA_NAME"
    }'
```

For example when finetuning with Unsloth:

{% code overflow="wrap" %}

```python
from unsloth import FastLanguageModel
import torch
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "unsloth/Llama-3.1-8B-Instruct",
    max_seq_length = 2048,
    load_in_4bit = True,
)
model = FastLanguageModel.get_peft_model(model)
```

{% endcode %}

Then after training, we save the LoRAs:

```python
model.save_pretrained("finetuned_lora")
tokenizer.save_pretrained("finetuned_lora")
```

We can then load the LoRA:

{% code overflow="wrap" %}

```bash
curl -X POST http://localhost:8000/v1/load_lora_adapter \
    -H "Content-Type: application/json" \
    -d '{
        "lora_name": "LORA_NAME_finetuned_lora",
        "lora_path": "finetuned_lora"
    }'
```

{% endcode %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://unsloth.ai/docs/basics/inference-and-deployment/vllm-guide/lora-hot-swapping-guide.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.