---
language:
- en
tags:
- paligemma2
- lora
- multi-lora
- serving
- openai-api
- visual-inspection
- peft
- google
license: apache-2.0
---

# Anchor — PaliGemma2 Multi-LoRA Server

**Load multiple LoRA adapters once. Switch between them at inference time — 216ms, no reload.**

→ **GitHub:** [recursia-lab/anchor](https://github.com/recursia-lab/anchor)

## What is this?

Anchor is a lightweight serving server for PaliGemma2 with multiple LoRA adapters.
Unlike frameworks that load adapters per-request from disk, Anchor keeps all adapters
in GPU memory simultaneously — switching is a pointer swap.

```
Request: model="open_circuit"  →  set_adapter()  →  generate()  →  216ms
Request: model="missing_hole"  →  set_adapter()  →  generate()  →  216ms
Request: model="base"          →  disable_adapters()             →  generate()
```

## Quick Start

```bash
git clone https://github.com/recursia-lab/anchor
docker build -t anchor .
docker run --gpus all -v /model:/model -v /lora:/lora -p 8080:8080 anchor
```

## API (OpenAI-compatible)

```bash
curl http://localhost:8080/v1/chat/completions \
  -d '{"model": "your_adapter", "messages": [...]}'
```

## Framework Support

| Framework | PaliGemma2 LoRA |
|---|---|
| **Anchor** | ✅ pre-loaded, 216ms switch |
| vLLM | ✅ per-request load |
| SGLang | 🚧 [PR #24034](https://github.com/sgl-project/sglang/pull/24034) |

## Community Adapters

See [recursia-lab/paligemma2-adapters](https://github.com/recursia-lab/paligemma2-adapters)
for a curated index of community fine-tuned PaliGemma2 LoRA adapters.

---

Built by [Recursia Lab](https://github.com/recursia-lab) • Apache 2.0