> ## Documentation Index
> Fetch the complete documentation index at: https://docs.sglang.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Devstral 2 (Mistral)

export const Devstral2Deployment = () => {
  const options = {
    hardware: {
      name: 'hardware',
      title: 'Hardware Platform',
      items: [{
        id: 'b200',
        label: 'B200',
        default: true
      }, {
        id: 'h200',
        label: 'H200',
        default: false
      }, {
        id: 'h100',
        label: 'H100',
        default: false
      }, {
        id: 'mi300x',
        label: 'MI300X',
        default: false
      }, {
        id: 'mi325x',
        label: 'MI325X',
        default: false
      }, {
        id: 'mi355x',
        label: 'MI355X',
        default: false
      }]
    },
    model: {
      name: 'model',
      title: 'Model',
      items: [{
        id: 'small',
        label: 'Devstral Small 2 (24B)',
        default: true
      }, {
        id: 'large',
        label: 'Devstral 2 (123B)',
        default: false
      }]
    },
    weights: {
      name: 'weights',
      title: 'Weights / Precision',
      items: [{
        id: 'fp8',
        label: 'FP8',
        default: true
      }]
    },
    toolcall: {
      name: 'toolcall',
      title: 'Tool Call Parser',
      items: [{
        id: 'disabled',
        label: 'Disabled',
        default: true
      }, {
        id: 'enabled',
        label: 'Enabled',
        default: false
      }]
    }
  };
  const modelConfigs = {
    small: {
      modelId: 'mistralai/Devstral-Small-2-24B-Instruct-2512',
      tpByHardware: {
        h100: 1,
        h200: 1,
        b200: 1,
        mi300x: 1,
        mi325x: 1,
        mi355x: 1
      },
      allowedWeights: ['fp8']
    },
    large: {
      modelId: 'mistralai/Devstral-2-123B-Instruct-2512',
      tpByHardware: {
        h100: 4,
        h200: 2,
        b200: 2,
        mi300x: 2,
        mi325x: 2,
        mi355x: 2
      },
      allowedWeights: ['fp8']
    }
  };
  const getInitialState = () => {
    const initialState = {};
    Object.entries(options).forEach(([key, option]) => {
      if (option.type === 'checkbox') {
        initialState[key] = option.items.filter(item => item.default).map(item => item.id);
      } else {
        const defaultItem = option.items.find(item => item.default);
        initialState[key] = defaultItem ? defaultItem.id : option.items[0].id;
      }
    });
    return initialState;
  };
  const [values, setValues] = useState(getInitialState);
  const [isDark, setIsDark] = useState(false);
  useEffect(() => {
    const checkDarkMode = () => {
      const html = document.documentElement;
      const isDarkMode = html.classList.contains('dark') || html.getAttribute('data-theme') === 'dark' || html.style.colorScheme === 'dark';
      setIsDark(isDarkMode);
    };
    checkDarkMode();
    const observer = new MutationObserver(checkDarkMode);
    observer.observe(document.documentElement, {
      attributes: true,
      attributeFilter: ['class', 'data-theme', 'style']
    });
    return () => observer.disconnect();
  }, []);
  const handleRadioChange = (optionName, value) => {
    setValues(prev => ({
      ...prev,
      [optionName]: value
    }));
  };
  const handleCheckboxChange = (optionName, itemId, isChecked) => {
    setValues(prev => {
      const currentValues = prev[optionName] || [];
      if (isChecked) {
        return {
          ...prev,
          [optionName]: [...currentValues, itemId]
        };
      } else {
        return {
          ...prev,
          [optionName]: currentValues.filter(id => id !== itemId)
        };
      }
    });
  };
  const generateCommand = () => {
    const {hardware, model, weights, toolcall} = values;
    const modelCfg = modelConfigs[model];
    if (!modelCfg) return `# Error: Unknown model selection: ${model}`;
    if (!modelCfg.allowedWeights.includes(weights)) {
      const allowed = modelCfg.allowedWeights.map(w => w.toUpperCase()).join(', ');
      return `# Error: ${modelCfg.modelId} only supports: ${allowed}\n# Please change "Weights / Precision" to a supported value.`;
    }
    const tp = modelCfg.tpByHardware[hardware];
    if (!tp) return `# Error: Unknown hardware platform: ${hardware}`;
    let cmd = 'python -m sglang.launch_server \\\n';
    cmd += `  --model ${modelCfg.modelId}`;
    if (tp > 1) {
      cmd += ` \\\n  --tp ${tp}`;
    }
    if (toolcall === 'enabled') {
      cmd += ` \\\n  --tool-call-parser mistral`;
    }
    return cmd;
  };
  const containerStyle = {
    maxWidth: '900px',
    margin: '0 auto',
    display: 'flex',
    flexDirection: 'column',
    gap: '4px'
  };
  const cardStyle = {
    padding: '8px 12px',
    border: `1px solid ${isDark ? '#374151' : '#e5e7eb'}`,
    borderLeft: `3px solid ${isDark ? '#E85D4D' : '#D45D44'}`,
    borderRadius: '4px',
    display: 'flex',
    alignItems: 'center',
    gap: '12px',
    background: isDark ? '#1f2937' : '#fff'
  };
  const titleStyle = {
    fontSize: '13px',
    fontWeight: '600',
    minWidth: '140px',
    flexShrink: 0,
    color: isDark ? '#e5e7eb' : 'inherit'
  };
  const itemsStyle = {
    display: 'flex',
    rowGap: '2px',
    columnGap: '6px',
    flexWrap: 'wrap',
    alignItems: 'center',
    flex: 1
  };
  const labelBaseStyle = {
    padding: '4px 10px',
    border: `1px solid ${isDark ? '#9ca3af' : '#d1d5db'}`,
    borderRadius: '3px',
    cursor: 'pointer',
    display: 'inline-flex',
    flexDirection: 'column',
    alignItems: 'center',
    justifyContent: 'center',
    fontWeight: '500',
    fontSize: '13px',
    transition: 'all 0.2s',
    userSelect: 'none',
    minWidth: '45px',
    textAlign: 'center',
    flex: 1,
    background: isDark ? '#374151' : '#fff',
    color: isDark ? '#e5e7eb' : 'inherit'
  };
  const checkedStyle = {
    background: '#D45D44',
    color: 'white',
    borderColor: '#D45D44'
  };
  const disabledStyle = {
    cursor: 'not-allowed',
    opacity: 0.5
  };
  const subtitleStyle = {
    display: 'block',
    fontSize: '9px',
    marginTop: '1px',
    lineHeight: '1.1',
    opacity: 0.7
  };
  const commandDisplayStyle = {
    flex: 1,
    padding: '12px 16px',
    background: isDark ? '#111827' : '#f5f5f5',
    borderRadius: '6px',
    fontFamily: "'Menlo', 'Monaco', 'Courier New', monospace",
    fontSize: '12px',
    lineHeight: '1.5',
    color: isDark ? '#e5e7eb' : '#374151',
    whiteSpace: 'pre-wrap',
    overflowX: 'auto',
    margin: 0,
    border: `1px solid ${isDark ? '#374151' : '#e5e7eb'}`
  };
  return <div style={containerStyle} className="not-prose">
      {Object.entries(options).map(([key, option]) => <div key={key} style={cardStyle}>
          <div style={titleStyle}>{option.title}</div>
          <div style={itemsStyle}>
            {option.type === 'checkbox' ? option.items.map(item => {
    const isChecked = (values[option.name] || []).includes(item.id);
    const isDisabled = item.required;
    return <label key={item.id} style={{
      ...labelBaseStyle,
      ...isChecked ? checkedStyle : {},
      ...isDisabled ? disabledStyle : {}
    }}>
                    <input type="checkbox" checked={isChecked} disabled={isDisabled} onChange={e => handleCheckboxChange(option.name, item.id, e.target.checked)} style={{
      display: 'none'
    }} />
                    {item.label}
                    {item.subtitle && <small style={{
      ...subtitleStyle,
      color: isChecked ? 'rgba(255,255,255,0.85)' : 'inherit'
    }}>{item.subtitle}</small>}
                  </label>;
  }) : option.items.map(item => {
    const isChecked = values[option.name] === item.id;
    return <label key={item.id} style={{
      ...labelBaseStyle,
      ...isChecked ? checkedStyle : {}
    }}>
                    <input type="radio" name={option.name} value={item.id} checked={isChecked} onChange={() => handleRadioChange(option.name, item.id)} style={{
      display: 'none'
    }} />
                    {item.label}
                    {item.subtitle && <small style={{
      ...subtitleStyle,
      color: isChecked ? 'rgba(255,255,255,0.85)' : 'inherit'
    }}>{item.subtitle}</small>}
                  </label>;
  })}
          </div>
        </div>)}
      <div style={cardStyle}>
        <div style={titleStyle}>Run this Command:</div>
        <pre style={commandDisplayStyle}>{generateCommand()}</pre>
      </div>
    </div>;
};

## 1. Model Introduction

**Devstral 2** is an agentic LLM family for software engineering tasks. It is designed for agentic workflows such as tool use, codebase exploration, and multi-file edits, and achieves strong performance on **SWE-bench**.

The **Devstral 2 Instruct** checkpoints are instruction-tuned **FP8** models, making them a good fit for chat, tool-using agents, and instruction-following SWE workloads.

**Key Features:**

* **Agentic coding**: Optimized for tool-driven coding and software engineering agents
* **Improved performance**: A step up compared to earlier Devstral models
* **Better generalization**: More robust across diverse prompts and coding environments
* **Long context**: Up to a **256K** context window

**Use Cases:**
AI code assistants, agentic coding, and software engineering tasks that require deep codebase understanding and tool integration.

For enterprises requiring specialized capabilities (increased context, domain-specific knowledge, etc.), please reach out to Mistral.

**Models:**

* **Collection**: [mistralai/devstral-2 (Hugging Face)](https://huggingface.co/collections/mistralai/devstral-2)
* **FP8 Instruct**:
  * **[mistralai/Devstral-2-123B-Instruct-2512](https://huggingface.co/mistralai/Devstral-2-123B-Instruct-2512)**
  * **[mistralai/Devstral-Small-2-24B-Instruct-2512](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512)**

***

## 2. SGLang Installation

SGLang offers multiple installation methods. You can choose the most suitable installation method based on your hardware platform and requirements.

Please refer to the [official SGLang installation guide](../../../docs/get-started/install) for installation instructions.

<Warning title="Transformers version requirement">
  Devstral 2 requires a recent `transformers`. Please verify `transformers >= 5.0.0.rc`:

  ```shell Command theme={null}
  python -c "import transformers; print(transformers.__version__)"
  ```

  If your version is lower, upgrade:

  ```shell Command theme={null}
  pip install -U --pre "transformers>=5.0.0rc0"
  ```
</Warning>

***

## 3. Model Deployment

### 3.1 Basic configuration

**Interactive Command Generator**: Use the configuration selector below to generate a launch command for Devstral Small 2 (24B) or Devstral 2 (123B).

<Note>
  The TP size is set to the minimum required for the selected model size.
</Note>

<Devstral2Deployment />

### 3.2 Configuration tips

* **Context length vs memory**: Devstral 2 advertises a long context window; if you are memory-constrained, start by lowering `--context-length` (for example `32768`) and increase once things are stable.
* **FP8 checkpoints**: Both Devstral Small 2 and Devstral 2 are published as **FP8** weights. If you hit kernel / dtype issues, try a newer SGLang build and recent CUDA drivers.

***

## 4. Model Invocation

### 4.1 Basic Usage (OpenAI-Compatible API)

SGLang exposes an OpenAI-compatible endpoint. Example:

```python Example theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY",
)

resp = client.chat.completions.create(
    model="mistralai/Devstral-Small-2-24B-Instruct-2512",
    messages=[
        {"role": "system", "content": "You are a helpful coding assistant."},
        {"role": "user", "content": "Write a Python function that retries a request with exponential backoff."},
    ],
    temperature=0.2,
    max_tokens=512,
)

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

**Output Example:**

````text Output theme={null}
  Here's a Python function that implements exponential backoff for retrying a request. This function uses the `requests` library to make HTTP requests and includes error handling for common HTTP and connection errors.

  ```python
  import time
  import requests
  from requests.exceptions import RequestException

  def retry_with_exponential_backoff(
      url,
      max_retries=3,
      initial_delay=1,
      backoff_factor=2,
      method="GET",
      **kwargs
  ):
      """
      Retry a request with exponential backoff.

      Parameters:
      - url: The URL to request.
      - max_retries: Maximum number of retry attempts (default: 3).
      - initial_delay: Initial delay in seconds (default: 1).
      - backoff_factor: Multiplier for the delay between retries (default: 2).
      - method: HTTP method to use (default: "GET").
      - **kwargs: Additional arguments to pass to the request function (e.g., headers, data, etc.).

      Returns:
      - Response object if the request succeeds.
      - Raises an exception if all retries fail.
      """
      retry_count = 0
      delay = initial_delay

      while retry_count < max_retries:
          try:
              response = requests.request(method, url, **kwargs)
              # Check if the response status code indicates success
              if response.status_code < 400:
                  return response
              else:
                  raise RequestException(f"HTTP {response.status_code}: {response.text}")

          except RequestException as e:
              if retry_count == max_retries - 1:
                  raise Exception(f"All retries failed. Last error: {e}")

              print(f"Attempt {retry_count + 1} failed. Retrying in {delay} seconds...")
              time.sleep(delay)
...
````

### 4.2 Tool calling (optional)

Devstral 2 supports tool calling capabilities. Enable the tool call parser:

```shell Command theme={null}
python -m sglang.launch_server \
  --model mistralai/Devstral-2-123B-Instruct-2512 \
  --tp 2 \
  --tool-call-parser mistral
```

**Python Example (with Thinking Process):**

```python Example theme={null}
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:30000/v1",
    api_key="EMPTY"
)

# Define available tools
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get the current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "The city name"
                    },
                    "unit": {
                        "type": "string",
                        "enum": ["celsius", "fahrenheit"],
                        "description": "Temperature unit"
                    }
                },
                "required": ["location"]
            }
        }
    }
]

# Make request with streaming to see thinking process
response = client.chat.completions.create(
    model="mistralai/Devstral-2-123B-Instruct-2512",
    messages=[
        {"role": "user", "content": "What's the weather in Beijing?"}
    ],
    tools=tools,
    temperature=0.7,
    stream=True
)

# Process streaming response
thinking_started = False
has_thinking = False
tool_calls_accumulator = {}

for chunk in response:
    if chunk.choices and len(chunk.choices) > 0:
        delta = chunk.choices[0].delta

        # Accumulate tool calls
        if hasattr(delta, 'tool_calls') and delta.tool_calls:
            # Close thinking section if needed
            if has_thinking and thinking_started:
                print("\n=============== Content =================\n", flush=True)
                thinking_started = False

            for tool_call in delta.tool_calls:
                index = tool_call.index
                if index not in tool_calls_accumulator:
                    tool_calls_accumulator[index] = {
                        'name': None,
                        'arguments': ''
                    }

                if tool_call.function:
                    if tool_call.function.name:
                        tool_calls_accumulator[index]['name'] = tool_call.function.name
                    if tool_call.function.arguments:
                        tool_calls_accumulator[index]['arguments'] += tool_call.function.arguments

        # Print content
        if delta.content:
            print(delta.content, end="", flush=True)

# Print accumulated tool calls
for index, tool_call in sorted(tool_calls_accumulator.items()):
    print(f"🔧 Tool Call: {tool_call['name']}")
    print(f"   Arguments: {tool_call['arguments']}")

print()
```

**Output Example:**

```text Output theme={null}
🔧 Tool Call: get_weather
   Arguments: {"location": "Beijing"}
```

## AMD GPU Support

## 1. Model Deployment

This section provides deployment configurations optimized for different hardware platforms and use cases.

### 1.1 Basic Usage

For basic API usage and request examples, please refer to:

* [SGLang Basic Usage Guide](../../../docs/basic_usage/send_request)

### 1.2 Advanced Usage

```shell Command theme={null}
python3 -m sglang.launch_server \
  --model-path mistralai/Devstral-2-123B-Instruct-2512 \
  --tp 8 \
  --trust-remote-code \
  --port 8888
```

## 2.Benchmark

### 5.1 Benchmark Commands

**Scenario 1: Chat (1K/1K) - Most Important**

* **Model Deployment**

```bash Command theme={null}
python3 -m sglang.launch_server \
  --model-path mistralai/Devstral-2-123B-Instruct-2512 \
  --tp 8 \
  --trust-remote-code \
  --port 8888
```

* Low Concurrency (Latency-Optimized)

```bash Command theme={null}
python3 -m sglang.bench_serving \
  --backend sglang \
  --model mistralai/Devstral-2-123B-Instruct-2512 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 10 \
  --max-concurrency 1 \
  --request-rate inf \
  --port 8888
```

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 1
Successful requests:                     10
Benchmark duration (s):                  94.30
Total input tokens:                      6101
Total input text tokens:                 6101
Total input vision tokens:               0
Total generated tokens:                  4220
Total generated tokens (retokenized):    4206
Request throughput (req/s):              0.11
Input token throughput (tok/s):          64.70
Output token throughput (tok/s):         44.75
Peak output token throughput (tok/s):    82.00
Peak concurrent requests:                2
Total token throughput (tok/s):          109.44
Concurrency:                             1.00
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   9427.59
Median E2E Latency (ms):                 5637.23
---------------Time to First Token----------------
Mean TTFT (ms):                          4253.85
Median TTFT (ms):                        116.95
P99 TTFT (ms):                           37764.48
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          12.28
Median TPOT (ms):                        12.29
P99 TPOT (ms):                           12.30
---------------Inter-Token Latency----------------
Mean ITL (ms):                           12.29
Median ITL (ms):                         12.29
P95 ITL (ms):                            12.38
P99 ITL (ms):                            12.42
Max ITL (ms):                            12.90
==================================================
```

* Medium Concurrency (Balanced)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model mistralai/Devstral-2-123B-Instruct-2512 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 80 \
  --max-concurrency 16 \
  --request-rate inf \
  --port 8888
```

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 16
Successful requests:                     80
Benchmark duration (s):                  52.11
Total input tokens:                      39668
Total input text tokens:                 39668
Total input vision tokens:               0
Total generated tokens:                  40805
Total generated tokens (retokenized):    40761
Request throughput (req/s):              1.54
Input token throughput (tok/s):          761.31
Output token throughput (tok/s):         783.13
Peak output token throughput (tok/s):    1120.00
Peak concurrent requests:                20
Total token throughput (tok/s):          1544.44
Concurrency:                             13.60
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   8856.19
Median E2E Latency (ms):                 9314.71
---------------Time to First Token----------------
Mean TTFT (ms):                          398.80
Median TTFT (ms):                        127.81
P99 TTFT (ms):                           1500.32
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          17.32
Median TPOT (ms):                        16.90
P99 TPOT (ms):                           32.78
---------------Inter-Token Latency----------------
Mean ITL (ms):                           16.61
Median ITL (ms):                         14.26
P95 ITL (ms):                            15.07
P99 ITL (ms):                            114.46
Max ITL (ms):                            1224.45
==================================================
```

* High Concurrency (Throughput-Optimized)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model mistralai/Devstral-2-123B-Instruct-2512 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 500 \
  --max-concurrency 100 \
  --request-rate inf \
  --port 8888
```

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 100
Successful requests:                     500
Benchmark duration (s):                  116.08
Total input tokens:                      249831
Total input text tokens:                 249831
Total input vision tokens:               0
Total generated tokens:                  252662
Total generated tokens (retokenized):    252523
Request throughput (req/s):              4.31
Input token throughput (tok/s):          2152.21
Output token throughput (tok/s):         2176.60
Peak output token throughput (tok/s):    3600.00
Peak concurrent requests:                107
Total token throughput (tok/s):          4328.81
Concurrency:                             92.42
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   21456.71
Median E2E Latency (ms):                 20126.82
---------------Time to First Token----------------
Mean TTFT (ms):                          291.60
Median TTFT (ms):                        199.24
P99 TTFT (ms):                           866.02
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          42.42
Median TPOT (ms):                        45.18
P99 TPOT (ms):                           53.32
---------------Inter-Token Latency----------------
Mean ITL (ms):                           41.97
Median ITL (ms):                         27.59
P95 ITL (ms):                            130.43
P99 ITL (ms):                            137.87
Max ITL (ms):                            616.73
==================================================
```

#### 5.2 Understanding the Results

**Key Metrics:**

* **Request Throughput (req/s)**: Number of requests processed per second
* **Output Token Throughput (tok/s)**: Total tokens generated per second
* **Mean TTFT (ms)**: Time to First Token - measures responsiveness
* **Mean TPOT (ms)**: Time Per Output Token - measures generation speed
* **Mean ITL (ms)**: Inter-Token Latency - measures streaming consistency

**Why These Configurations Matter:**

* **1K/1K (Chat)**: Represents the most common conversational AI workload. This is the highest priority scenario for most deployments.
* **1K/8K (Reasoning)**: Tests long-form generation capabilities crucial for complex reasoning, code generation, and detailed explanations.
* **8K/1K (Summarization)**: Evaluates performance with large context inputs, essential for RAG systems, document Q\&A, and summarization tasks.
* **Variable Concurrency**: Captures the Pareto frontier - the optimal trade-off between throughput and latency at different load levels. Low concurrency shows best-case latency, high concurrency shows maximum throughput.

**Interpreting Results:**

* Compare your results against baseline numbers for your hardware
* Higher throughput at same latency = better performance
* Lower TTFT = more responsive user experience
* Lower TPOT = faster generation speed

### 5.3 Accuracy Benchmark

Document model accuracy on standard benchmarks:

#### 5.3.1 GSM8K Benchmark

* Benchmark Command

```bash Command theme={null}
python3 benchmark/gsm8k/bench_sglang.py \
  --num-shots 8 \
  --num-questions 1316 \
  --parallel 1316 \
  --port 8888
```

**Test Results:**

```text Output theme={null}
Accuracy: 0.922
Invalid: 0.000
Latency: 35.800 s
Output throughput: 4507.697 token/s
```