> ## 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.

# Kimi-K2

export const KimiK2Deployment = () => {
  const modelFamily = 'moonshotai';
  const options = {
    hardware: {
      name: 'hardware',
      title: 'Hardware Platform',
      items: [{
        id: 'h200',
        label: 'H200',
        default: true
      }, {
        id: 'b200',
        label: 'B200',
        default: false
      }, {
        id: 'mi300x',
        label: 'MI300X',
        default: false
      }, {
        id: 'mi325x',
        label: 'MI325X',
        default: false
      }, {
        id: 'mi355x',
        label: 'MI355X',
        default: false
      }]
    },
    modelname: {
      name: 'modelname',
      title: 'Model Name',
      items: [{
        id: 'instruct',
        label: 'Kimi-K2-Instruct',
        default: true
      }, {
        id: 'thinking',
        label: 'Kimi-K2-Thinking',
        default: false
      }]
    },
    strategy: {
      name: 'strategy',
      title: 'Deployment Strategy',
      type: 'checkbox',
      items: [{
        id: 'tp',
        label: 'TP',
        default: true,
        required: true
      }, {
        id: 'dp',
        label: 'DP attention',
        default: false
      }, {
        id: 'ep',
        label: 'EP',
        default: false
      }]
    },
    reasoning: {
      name: 'reasoning',
      title: 'Reasoning Parser',
      items: [{
        id: 'disabled',
        label: 'Disabled',
        default: true
      }, {
        id: 'enabled',
        label: 'Enabled',
        default: false
      }]
    },
    toolcall: {
      name: 'toolcall',
      title: 'Tool Call Parser',
      items: [{
        id: 'disabled',
        label: 'Disabled',
        default: true
      }, {
        id: 'enabled',
        label: 'Enabled',
        default: false
      }]
    }
  };
  const generateCommand = values => {
    const {hardware, modelname, strategy, reasoning, toolcall} = values;
    if (modelname === 'instruct' && reasoning === 'enabled') {
      return `# Error: Kimi-K2-Instruct doesn't support reasoning parser\n# Please select "Disabled" for Reasoning Parser or choose Kimi-K2-Thinking model`;
    }
    const modelMap = {
      'instruct': 'Kimi-K2-Instruct',
      'thinking': 'Kimi-K2-Thinking'
    };
    const modelName = `${modelFamily}/${modelMap[modelname]}`;
    let cmd = 'python3 -m sglang.launch_server \\\n';
    if (hardware === 'mi300x' || hardware === 'mi325x' || hardware === 'mi355x') {
      cmd = 'SGLANG_ROCM_FUSED_DECODE_MLA=0 ' + cmd;
    }
    cmd += `  --model-path ${modelName}`;
    const strategyArray = Array.isArray(strategy) ? strategy : [];
    cmd += ` \\\n  --tp 8`;
    if (strategyArray.includes('dp')) {
      cmd += ` \\\n  --dp 4 \\\n  --enable-dp-attention`;
    }
    if (strategyArray.includes('ep')) {
      cmd += ` \\\n  --ep 4`;
    }
    cmd += ` \\\n  --trust-remote-code`;
    if (toolcall === 'enabled') {
      cmd += ` \\\n  --tool-call-parser kimi_k2`;
    }
    if (reasoning === 'enabled') {
      cmd += ` \\\n  --reasoning-parser kimi_k2`;
    }
    return cmd;
  };
  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);
        return;
      }
      if (option.type === 'text') {
        initialState[key] = option.default || '';
        return;
      }
      let items = option.items || [];
      if (option.getDynamicItems) {
        const defaultValues = {};
        Object.entries(options).forEach(([innerKey, innerOption]) => {
          if (innerOption.type === 'checkbox') {
            defaultValues[innerKey] = (innerOption.items || []).filter(item => item.default).map(item => item.id);
          } else if (innerOption.type === 'text') {
            defaultValues[innerKey] = innerOption.default || '';
          } else if (innerOption.items && innerOption.items.length > 0) {
            const defaultItem = innerOption.items.find(item => item.default);
            defaultValues[innerKey] = defaultItem ? defaultItem.id : innerOption.items[0].id;
          }
        });
        items = option.getDynamicItems(defaultValues);
      }
      const defaultItem = items && items.find(item => item.default);
      initialState[key] = defaultItem ? defaultItem.id : items && items[0] ? 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]
        };
      }
      return {
        ...prev,
        [optionName]: currentValues.filter(id => id !== itemId)
      };
    });
  };
  const handleTextChange = (optionName, value) => {
    setValues(prev => ({
      ...prev,
      [optionName]: value
    }));
  };
  const command = generateCommand(values);
  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 textInputStyle = {
    flex: 1,
    padding: '8px 10px',
    borderRadius: '4px',
    border: `1px solid ${isDark ? '#4b5563' : '#d1d5db'}`,
    background: isDark ? '#111827' : '#fff',
    color: isDark ? '#e5e7eb' : '#111827',
    fontSize: '13px'
  };
  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]) => {
    if (option.condition && !option.condition(values)) {
      return null;
    }
    const items = option.getDynamicItems ? option.getDynamicItems(values) : option.items || [];
    return <div key={key} style={cardStyle}>
            <div style={titleStyle}>{option.title}</div>
            <div style={itemsStyle}>
              {option.type === 'text' ? <input type="text" value={values[option.name] || ''} placeholder={option.placeholder || ''} onChange={event => handleTextChange(option.name, event.target.value)} style={textInputStyle} /> : option.type === 'checkbox' ? (option.items || []).map(item => {
      const isChecked = (values[option.name] || []).includes(item.id);
      const isDisabled = item.required || typeof item.disabledWhen === 'function' && item.disabledWhen(values);
      return <label key={item.id} title={item.disabledReason || ''} style={{
        ...labelBaseStyle,
        ...isChecked ? checkedStyle : {},
        ...isDisabled ? disabledStyle : {}
      }}>
                      <input type="checkbox" checked={isChecked} disabled={isDisabled} onChange={event => handleCheckboxChange(option.name, item.id, event.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>;
    }) : items.map(item => {
      const isChecked = values[option.name] === item.id;
      const isDisabled = Boolean(item.disabled);
      return <label key={item.id} title={item.disabledReason || ''} style={{
        ...labelBaseStyle,
        ...isChecked ? checkedStyle : {},
        ...isDisabled ? disabledStyle : {}
      }}>
                      <input type="radio" name={option.name} value={item.id} checked={isChecked} disabled={isDisabled} onChange={() => !isDisabled && 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}>{command}</pre>
      </div>
    </div>;
};

## 1. Model Introduction

[Kimi-K2](https://moonshotai.github.io/Kimi-K2/) is a state-of-the-art MoE language model by Moonshot AI with 32B activated parameters and 1T total parameters.

**Model Variants:**

* **[Kimi-K2-Instruct](https://huggingface.co/moonshotai/Kimi-K2-Instruct)**: Post-trained model optimized for general-purpose chat and agentic tasks. Compatible with vLLM, SGLang, KTransformers, and TensorRT-LLM.
* **[Kimi-K2-Thinking](https://huggingface.co/moonshotai/Kimi-K2-Thinking)**: Advanced thinking model with step-by-step reasoning and tool calling. Native INT4 quantization with 256k context window. Ideal for complex reasoning and multi-step tool use.
* **ROCm Support**: Compatible with AMD MI300X GPUs via SGLang (verified).

For details, see [official documentation](https://github.com/MoonshotAI/Kimi-K2) and [technical report](https://www.arxiv.org/abs/2507.20534).

## 2. SGLang Installation

Refer to the [official SGLang installation guide](../../../docs/get-started/install).

## 3. Model Deployment

This section provides a progressive guide from quick deployment to performance optimization, suitable for users at different levels.

### 3.1 Basic Configuration

**Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your hardware platform, model variant, deployment strategy, and capabilities.

<KimiK2Deployment />

### 3.2 Configuration Tips

* **Memory**: Requires 8 GPUs with ≥140GB each (H200/B200). Use `--context-length 128000` to conserve memory.
* **Expert Parallelism (EP)**: Use `--ep` for better MoE throughput. See [EP docs](../../../docs/advanced_features/expert_parallelism).
* **Data Parallel (DP)**: Enable with `--dp 4 --enable-dp-attention` for production throughput.
* **KV Cache**: Use `--kv-cache-dtype fp8_e4m3` to reduce memory by 50% (CUDA 11.8+).
* **Reasoning Parser**: Add `--reasoning-parser kimi_k2` for Kimi-K2-Thinking to separate thinking and content.
* **Tool Call Parser**: Add `--tool-call-parser kimi_k2` for structured tool calls.
* **AMD GPU**: Set `SGLANG_ROCM_FUSED_DECODE_MLA=0` before launching AMD GPU.

## 4. Model Invocation

### 4.1 Basic Usage

See [Basic API Usage](../../../docs/get-started/quickstart).

### 4.2 Advanced Usage

#### 4.2.1 Reasoning Parser

Enable reasoning parser for Kimi-K2-Thinking:

```shell Command theme={null}
python -m sglang.launch_server \
  --model moonshotai/Kimi-K2-Thinking \
  --reasoning-parser kimi_k2 \
  --tp 8 \
  --host 0.0.0.0 \
  --port 8000
```

**Example:**

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

client = OpenAI(
    base_url="http://localhost:8000/v1",
    api_key="EMPTY"
)

# Enable streaming to see the thinking process in real-time
response = client.chat.completions.create(
    model="moonshotai/Kimi-K2-Thinking",
    messages=[
        {"role": "user", "content": "Solve this problem step by step: What is 15% of 240?"}
    ],
    temperature=0.6,
    max_tokens=2048,
    stream=True
)

# Process the stream
has_thinking = False
has_answer = False
thinking_started = False

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

        # Print thinking process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content:
            if not thinking_started:
                print("=============== Thinking =================", flush=True)
                thinking_started = True
            has_thinking = True
            print(delta.reasoning_content, end="", flush=True)

        # Print answer content
        if delta.content:
            # Close thinking section and add content header
            if has_thinking and not has_answer:
                print("\n=============== Content =================", flush=True)
                has_answer = True
            print(delta.content, end="", flush=True)

print()
```

**Output Example:**

```text Output theme={null}
=============== Thinking =================
  The user asks: "What is 15% of 240?" This is a straightforward percentage calculation problem. I need to solve it step by step.

Step 1: Understand what "percent" means.
- "Percent" means "per hundred". So 15% means 15 per 100, or 15/100, or 0.15.

Step 2: Convert the percentage to a decimal.
- 15% = 15 / 100 = 0.15

Step 3: Multiply the decimal by the number.
- 0.15 * 240

Step 4: Perform the multiplication.
- 0.15 * 240 = (15/100) * 240
- = 15 * 240 / 100
- = 3600 / 100
- = 36

Alternatively, I can calculate it directly:
- 0.15 * 240
- 15 * 240 = 3600
- 3600 / 100 = 36

Or, break it down:
- 10% of 240 = 24
- 5% of 240 = half of 10% = 12
- 15% of 240 = 10% + 5% = 24 + 12 = 36

I should present the solution clearly with steps. The most standard method is converting to decimal and multiplying.

Let me structure the answer:
1. Convert the percentage to a decimal.
2. Multiply the decimal by the number.
3. Show the calculation.
4. State the final answer.

This is simple and easy to follow.
=============== Content =================
 Here is the step-by-step solution:

**Step 1: Convert the percentage to a decimal**
15% means 15 per 100, which is 15 ÷ 100 = **0.15**

**Step 2: Multiply the decimal by the number**
0.15 × 240

**Step 3: Calculate the result**
0.15 × 240 = **36**

**Answer:** 15% of 240 is **36**.
```

**Note:** The reasoning parser captures the model's step-by-step thinking process, allowing you to see how the model arrives at its conclusions.

#### 4.2.2 Tool Calling

Kimi-K2-Instruct and Kimi-K2-Thinking support tool calling capabilities. Enable the tool call parser during deployment:

**Deployment Command:**

```shell Command theme={null}
python -m sglang.launch_server \
  --model moonshotai/Kimi-K2-Instruct \
  --tool-call-parser kimi_k2 \
  --tp 8 \
  --trust-remote-code \
  --host 0.0.0.0 \
  --port 8000
```

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

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

client = OpenAI(
    base_url="http://localhost:8000/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="moonshotai/Kimi-K2-Thinking",
    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

        # Print thinking process
        if hasattr(delta, 'reasoning_content') and delta.reasoning_content:
            if not thinking_started:
                print("=============== Thinking =================", flush=True)
                thinking_started = True
            has_thinking = True
            print(delta.reasoning_content, end="", flush=True)

        # 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}
=============== Thinking =================
  The user is asking about the weather in Beijing. I need to use the get_weather function to retrieve this information. Beijing is a major city in China, so I should be able to get weather data for it. The location parameter is required, but the unit parameter is optional. Since the user didn't specify a temperature unit, I can just provide the location and let the function use its default. I'll check the weather in Beijing for you.
=============== Content =================

  🔧 Tool Call: get_weather
   Arguments: {"location":"Beijing"}
```

**Note:**

* The reasoning parser shows how the model decides to use a tool
* Tool calls are clearly marked with the function name and arguments
* You can then execute the function and send the result back to continue the conversation

**Handling Tool Call Results:**

```python Example theme={null}
# After getting the tool call, execute the function
def get_weather(location, unit="celsius"):
    # Your actual weather API call here
    return f"The weather in {location} is 22°{unit[0].upper()} and sunny."

# Send tool result back to the model
messages = [
    {"role": "user", "content": "What's the weather in Beijing?"},
    {
        "role": "assistant",
        "content": None,
        "tool_calls": [{
            "id": "call_123",
            "type": "function",
            "function": {
                "name": "get_weather",
                "arguments": '{"location": "Beijing", "unit": "celsius"}'
            }
        }]
    },
    {
        "role": "tool",
        "tool_call_id": "call_123",
        "content": get_weather("Beijing", "celsius")
    }
]

final_response = client.chat.completions.create(
    model="moonshotai/Kimi-K2-Thinking",
    messages=messages,
    temperature=0.7
)

print(final_response.choices[0].message.content)
# Output: "The weather in Beijing is currently 22°C and sunny."
```

## 5. Benchmark

### 5.1 Speed Benchmark

**Test Environment:**

* Hardware: NVIDIA B200 GPU (8x)
* Model: Kimi-K2-Instruct
* sglang version: 0.5.6.post1

We use SGLang's built-in benchmarking tool to conduct performance evaluation on the [ShareGPT\_Vicuna\_unfiltered](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) dataset. This dataset contains real conversation data and can better reflect performance in actual use scenarios.

#### 5.1.1 Latency-Sensitive Benchmark

* Model Deployment Command:

```shell Command theme={null}
python3 -m sglang.launch_server \
    --model-path moonshotai/Kimi-K2-Instruct \
    --tp 8 \
    --dp 4 \
    --enable-dp-attention \
    --trust-remote-code \
    --host 0.0.0.0 \
    --port 8000
```

* Benchmark Command:

```shell Command theme={null}
python3 -m sglang.bench_serving \
  --backend sglang \
  --host 127.0.0.1 \
  --port 8000 \
  --model moonshotai/Kimi-K2-Instruct\
  --num-prompts 10 \
  --max-concurrency 1
```

* **Test Results**:

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 1
Successful requests:                     10
Benchmark duration (s):                  44.93
Total input tokens:                      1951
Total input text tokens:                 1951
Total input vision tokens:               0
Total generated tokens:                  2755
Total generated tokens (retokenized):    2748
Request throughput (req/s):              0.22
Input token throughput (tok/s):          43.42
Output token throughput (tok/s):         61.32
Peak output token throughput (tok/s):    64.00
Peak concurrent requests:                3
Total token throughput (tok/s):          104.74
Concurrency:                             1.00
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   4489.56
Median E2E Latency (ms):                 4994.53
---------------Time to First Token----------------
Mean TTFT (ms):                          141.22
Median TTFT (ms):                        158.28
P99 TTFT (ms):                           166.90
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          18.40
Median TPOT (ms):                        15.63
P99 TPOT (ms):                           39.88
---------------Inter-Token Latency----------------
Mean ITL (ms):                           15.78
Median ITL (ms):                         15.76
P95 ITL (ms):                            16.36
P99 ITL (ms):                            16.59
Max ITL (ms):                            19.94
==================================================
```

#### 5.1.2 Throughput-Sensitive Benchmark

* Model Deployment Command:

```shell Command theme={null}
python3 -m sglang.launch_server \
    --model-path moonshotai/Kimi-K2-Instruct \
    --tp 8 \
    --dp 4 \
    --ep 4 \
    --enable-dp-attention \
    --trust-remote-code \
    --host 0.0.0.0 \
    --port 8000
```

* Benchmark Command:

```shell Command theme={null}
python3 -m sglang.bench_serving \
  --backend sglang \
  --host 127.0.0.1 \
  --port 8000 \
  --model moonshotai/Kimi-K2-Instruct\
  --num-prompts 1000 \
  --max-concurrency 100
```

* **Test Results**:

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Traffic request rate:                    inf
Max request concurrency:                 100
Successful requests:                     1000
Benchmark duration (s):                  174.11
Total input tokens:                      296642
Total input text tokens:                 296642
Total input vision tokens:               0
Total generated tokens:                  193831
Total generated tokens (retokenized):    168687
Request throughput (req/s):              5.74
Input token throughput (tok/s):          1703.73
Output token throughput (tok/s):         1113.25
Peak output token throughput (tok/s):    2383.00
Peak concurrent requests:                112
Total token throughput (tok/s):          2816.97
Concurrency:                             89.60
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   15601.09
Median E2E Latency (ms):                 10780.52
---------------Time to First Token----------------
Mean TTFT (ms):                          457.42
Median TTFT (ms):                        221.62
P99 TTFT (ms):                           2475.32
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          97.23
Median TPOT (ms):                        85.61
P99 TPOT (ms):                           435.95
---------------Inter-Token Latency----------------
Mean ITL (ms):                           78.61
Median ITL (ms):                         43.66
P95 ITL (ms):                            169.53
P99 ITL (ms):                            260.91
Max ITL (ms):                            1703.21
==================================================
```

### 5.2 Accuracy Benchmark

#### 5.2.1 GSM8K Benchmark

* Server Command

```shell Command theme={null}
python3 -m sglang.launch_server \
    --model-path moonshotai/Kimi-K2-Instruct \
    --tp 8 \
    --dp 4 \
    --trust-remote-code  \
    --host 0.0.0.0 \
    --port 8000
```

* Benchmark Command

```shell Command theme={null}
python3 -m sglang.test.few_shot_gsm8k --num-questions 200 --port 8000
```

* **Result**:

```text Output theme={null}
Accuracy: 0.960
Invalid: 0.000
Latency: 15.956 s
Output throughput: 1231.699 token/s
```