# Llama.cpp Server

Run LLMs efficiently with llama.cpp server on GPU.

{% hint style="success" %}
All examples can be run on GPU servers rented through [CLORE.AI Marketplace](https://clore.ai/marketplace).
{% endhint %}

## Server Requirements

| Parameter    | Minimum       | Recommended |
| ------------ | ------------- | ----------- |
| RAM          | 8GB           | 16GB+       |
| VRAM         | 6GB           | 8GB+        |
| Network      | 200Mbps       | 500Mbps+    |
| Startup Time | \~2-5 minutes | -           |

{% hint style="info" %}
Llama.cpp is memory-efficient due to GGUF quantization. 7B models can run on 6-8GB VRAM.
{% endhint %}

## Renting on CLORE.AI

1. Visit [CLORE.AI Marketplace](https://clore.ai/marketplace)
2. Filter by GPU type, VRAM, and price
3. Choose **On-Demand** (fixed rate) or **Spot** (bid price)
4. Configure your order:
   * Select Docker image
   * Set ports (TCP for SSH, HTTP for web UIs)
   * Add environment variables if needed
   * Enter startup command
5. Select payment: **CLORE**, **BTC**, or **USDT/USDC**
6. Create order and wait for deployment

### Access Your Server

* Find connection details in **My Orders**
* Web interfaces: Use the HTTP port URL
* SSH: `ssh -p <port> root@<proxy-address>`

## What is Llama.cpp?

Llama.cpp is the fastest CPU/GPU inference engine for LLMs:

* Supports GGUF quantized models
* Low memory usage
* OpenAI-compatible API
* Multi-user support

## Quantization Levels

| Format   | Size (7B) | Speed   | Quality   |
| -------- | --------- | ------- | --------- |
| Q2\_K    | 2.8GB     | Fastest | Low       |
| Q4\_K\_M | 4.1GB     | Fast    | Good      |
| Q5\_K\_M | 4.8GB     | Medium  | Great     |
| Q6\_K    | 5.5GB     | Slower  | Excellent |
| Q8\_0    | 7.2GB     | Slowest | Best      |

## Quick Deploy

**Docker Image:**

```
ghcr.io/ggerganov/llama.cpp:server-cuda
```

**Ports:**

```
22/tcp
8080/http
```

**Command:**

```bash

# Download model
wget https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf

# Run server
./llama-server \
    -m Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf \
    --host 0.0.0.0 \
    --port 8080 \
    -ngl 35 \
    -c 4096
```

## Accessing Your Service

After deployment, find your `http_pub` URL in **My Orders**:

1. Go to **My Orders** page
2. Click on your order
3. Find the `http_pub` URL (e.g., `abc123.clorecloud.net`)

Use `https://YOUR_HTTP_PUB_URL` instead of `localhost` in examples below.

### Verify It's Working

```bash
# Check health
curl https://your-http-pub.clorecloud.net/health

# Get server info
curl https://your-http-pub.clorecloud.net/props
```

{% hint style="warning" %}
If you get HTTP 502, the service may still be starting or downloading the model. Wait 2-5 minutes and retry.
{% endhint %}

## Complete API Reference

### Standard Endpoints

| Endpoint               | Method | Description                         |
| ---------------------- | ------ | ----------------------------------- |
| `/health`              | GET    | Health check                        |
| `/v1/models`           | GET    | List models                         |
| `/v1/chat/completions` | POST   | Chat (OpenAI compatible)            |
| `/v1/completions`      | POST   | Text completion (OpenAI compatible) |
| `/v1/embeddings`       | POST   | Generate embeddings                 |
| `/completion`          | POST   | Native completion endpoint          |
| `/tokenize`            | POST   | Tokenize text                       |
| `/detokenize`          | POST   | Detokenize tokens                   |
| `/props`               | GET    | Server properties                   |
| `/metrics`             | GET    | Prometheus metrics                  |

#### Tokenize Text

```bash
curl https://your-http-pub.clorecloud.net/tokenize \
    -H "Content-Type: application/json" \
    -d '{"content": "Hello world"}'
```

Response:

```json
{"tokens": [15496, 1917]}
```

#### Server Properties

```bash
curl https://your-http-pub.clorecloud.net/props
```

Response:

```json
{
  "total_slots": 1,
  "chat_template": "...",
  "default_generation_settings": {...}
}
```

## Build from Source

```bash

# Clone repo
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp

# Build with CUDA
make LLAMA_CUDA=1

# Or with CMake
mkdir build && cd build
cmake .. -DLLAMA_CUDA=ON
cmake --build . --config Release
```

## Download Models

```bash

# Llama 3.1 8B
wget https://huggingface.co/bartowski/Meta-Llama-3.1-8B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf

# Mistral 7B
wget https://huggingface.co/bartowski/Mistral-7B-Instruct-v0.3-GGUF/resolve/main/Mistral-7B-Instruct-v0.3-Q4_K_M.gguf

# Mixtral 8x7B
wget https://huggingface.co/bartowski/Mixtral-8x7B-Instruct-v0.1-GGUF/resolve/main/Mixtral-8x7B-Instruct-v0.1-Q4_K_M.gguf

# Phi-2
wget https://huggingface.co/bartowski/Phi-4-GGUF/resolve/main/Phi-4-Q4_K_M.gguf

# CodeLlama 7B
wget https://huggingface.co/bartowski/CodeLlama-7B-Instruct-GGUF/resolve/main/CodeLlama-7B-Instruct-Q4_K_M.gguf
```

## Server Options

### Basic Server

```bash
./llama-server \
    -m model.gguf \
    --host 0.0.0.0 \
    --port 8080
```

### Full GPU Offload

```bash
./llama-server \
    -m model.gguf \
    --host 0.0.0.0 \
    --port 8080 \
    -ngl 99 \           # GPU layers (99 = all)
    -c 4096 \           # Context size
    -t 8 \              # CPU threads
    --parallel 4        # Concurrent requests
```

### All Options

```bash
./llama-server \
    -m model.gguf \           # Model file
    --host 0.0.0.0 \          # Bind address
    --port 8080 \             # Port
    -ngl 35 \                 # GPU layers
    -c 4096 \                 # Context size
    -t 8 \                    # Threads
    -b 512 \                  # Batch size
    --parallel 4 \            # Parallel requests
    --mlock \                 # Lock memory
    --no-mmap \               # Disable mmap
    --cont-batching \         # Continuous batching
    --flash-attn \            # Flash attention
    --metrics                 # Enable metrics endpoint
```

## API Usage

### Chat Completions (OpenAI Compatible)

```python
import openai

client = openai.OpenAI(
    base_url="http://localhost:8080/v1",
    api_key="not-needed"
)

response = client.chat.completions.create(
    model="llama-3.1-8b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is machine learning?"}
    ],
    temperature=0.7,
    max_tokens=500
)

print(response.choices[0].message.content)
```

### Streaming

```python
stream = client.chat.completions.create(
    model="llama-3.1-8b",
    messages=[{"role": "user", "content": "Write a story"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
```

### Text Completion

```python
response = client.completions.create(
    model="llama-3.1-8b",
    prompt="The future of AI is",
    max_tokens=100,
    temperature=0.8
)

print(response.choices[0].text)
```

### Embeddings

```python
response = client.embeddings.create(
    model="llama-3.1-8b",
    input="Hello, world!"
)

print(f"Embedding: {response.data[0].embedding[:5]}...")
```

## cURL Examples

### Chat

```bash
curl http://localhost:8080/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
        "model": "llama-3.1-8b",
        "messages": [
            {"role": "user", "content": "Hello!"}
        ]
    }'
```

### Completion

```bash
curl http://localhost:8080/completion \
    -H "Content-Type: application/json" \
    -d '{
        "prompt": "Building a website requires",
        "n_predict": 128,
        "temperature": 0.7
    }'
```

### Health Check

```bash
curl http://localhost:8080/health
```

### Metrics

```bash
curl http://localhost:8080/metrics
```

## Multi-GPU

```bash

# Split across GPUs
./llama-server \
    -m model.gguf \
    -ngl 99 \
    --tensor-split 0.5,0.5 \  # Split between 2 GPUs
    --main-gpu 0              # Primary GPU
```

## Memory Optimization

### For Limited VRAM

```bash

# Partial offload
./llama-server -m model.gguf -ngl 20 -c 2048

# Use smaller quantization

# Download Q2_K or Q3_K instead of Q4_K
```

### For Maximum Speed

```bash
./llama-server \
    -m model.gguf \
    -ngl 99 \
    --flash-attn \
    --cont-batching \
    --parallel 8 \
    -b 1024
```

## Model-Specific Templates

### Llama 2 Chat

```bash
./llama-server -m Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf \
    --chat-template llama2
```

### Mistral Instruct

```bash
./llama-server -m mistral-7b-instruct.gguf \
    --chat-template mistral
```

### ChatML (Many Models)

```bash
./llama-server -m model.gguf \
    --chat-template chatml
```

## Python Server Wrapper

```python
import subprocess
import requests
import time

class LlamaCppServer:
    def __init__(self, model_path, port=8080, gpu_layers=35):
        self.port = port
        self.process = subprocess.Popen([
            "./llama-server",
            "-m", model_path,
            "--host", "0.0.0.0",
            "--port", str(port),
            "-ngl", str(gpu_layers),
            "-c", "4096"
        ])
        self._wait_for_ready()

    def _wait_for_ready(self, timeout=60):
        start = time.time()
        while time.time() - start < timeout:
            try:
                r = requests.get(f"http://localhost:{self.port}/health")
                if r.status_code == 200:
                    return
            except:
                pass
            time.sleep(1)
        raise TimeoutError("Server didn't start")

    def chat(self, messages, **kwargs):
        response = requests.post(
            f"http://localhost:{self.port}/v1/chat/completions",
            json={"messages": messages, **kwargs}
        )
        return response.json()

    def stop(self):
        self.process.terminate()

# Usage
server = LlamaCppServer("llama-3.1-8b.gguf")
result = server.chat([{"role": "user", "content": "Hello!"}])
print(result["choices"][0]["message"]["content"])
server.stop()
```

## Benchmarking

```bash

# Built-in benchmark
./llama-bench -m model.gguf -ngl 99

# Output includes:

# - Tokens per second

# - Memory usage

# - Load time
```

## Performance Comparison

| Model        | GPU      | Quantization | Tokens/sec |
| ------------ | -------- | ------------ | ---------- |
| Llama 3.1 8B | RTX 3090 | Q4\_K\_M     | \~100      |
| Llama 3.1 8B | RTX 4090 | Q4\_K\_M     | \~150      |
| Llama 3.1 8B | RTX 3090 | Q4\_K\_M     | \~60       |
| Mistral 7B   | RTX 3090 | Q4\_K\_M     | \~110      |
| Mixtral 8x7B | A100     | Q4\_K\_M     | \~50       |

## Troubleshooting

### CUDA Not Detected

```bash

# Rebuild with CUDA
make clean
make LLAMA_CUDA=1

# Check CUDA
nvidia-smi
```

### Out of Memory

```bash

# Reduce GPU layers
-ngl 20  # Instead of 99

# Reduce context
-c 2048  # Instead of 4096

# Use smaller quant

# Q4_K_S instead of Q4_K_M
```

### Slow Generation

```bash

# Increase batch size
-b 1024

# Enable flash attention
--flash-attn

# Enable continuous batching
--cont-batching
```

## Production Setup

### Systemd Service

```ini

# /etc/systemd/system/llama.service
[Unit]
Description=Llama.cpp Server
After=network.target

[Service]
Type=simple
ExecStart=/opt/llama.cpp/llama-server -m /models/model.gguf -ngl 99 --host 0.0.0.0 --port 8080
Restart=always

[Install]
WantedBy=multi-user.target
```

### With nginx

```nginx
upstream llama {
    server localhost:8080;
}

server {
    listen 80;

    location / {
        proxy_pass http://llama;
        proxy_http_version 1.1;
        proxy_set_header Connection "";
    }
}
```

## Cost Estimate

Typical CLORE.AI marketplace rates (as of 2024):

| GPU       | Hourly Rate | Daily Rate | 4-Hour Session |
| --------- | ----------- | ---------- | -------------- |
| RTX 3060  | \~$0.03     | \~$0.70    | \~$0.12        |
| RTX 3090  | \~$0.06     | \~$1.50    | \~$0.25        |
| RTX 4090  | \~$0.10     | \~$2.30    | \~$0.40        |
| A100 40GB | \~$0.17     | \~$4.00    | \~$0.70        |
| A100 80GB | \~$0.25     | \~$6.00    | \~$1.00        |

*Prices vary by provider and demand. Check* [*CLORE.AI Marketplace*](https://clore.ai/marketplace) *for current rates.*

**Save money:**

* Use **Spot** market for flexible workloads (often 30-50% cheaper)
* Pay with **CLORE** tokens
* Compare prices across different providers

## Next Steps

* vLLM Inference - Higher throughput
* [ExLlamaV2](https://docs.clore.ai/guides/language-models/exllamav2-fast) - Faster inference
* [Text Generation WebUI](https://docs.clore.ai/guides/language-models/text-generation-webui) - Web interface