> ## 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.

# GLM-4.7

export const GLM47Deployment = () => {
  const options = {
    hardware: {
      name: 'hardware',
      title: 'Hardware Platform',
      items: [{
        id: 'b200',
        label: 'B200',
        default: true
      }, {
        id: 'gb200',
        label: 'GB200',
        default: false
      }, {
        id: 'h200',
        label: 'H200',
        default: false
      }, {
        id: 'mi300x',
        label: 'MI300X',
        default: false
      }, {
        id: 'mi325x',
        label: 'MI325X',
        default: false
      }, {
        id: 'mi355x',
        label: 'MI355X',
        default: false
      }]
    },
    quantization: {
      name: 'quantization',
      title: 'Quantization',
      items: [{
        id: 'nvfp4',
        label: 'NVFP4',
        default: true
      }, {
        id: 'fp8',
        label: 'FP8',
        default: false
      }, {
        id: 'bf16',
        label: 'BF16',
        default: false
      }]
    },
    gpus: {
      name: 'gpus',
      title: 'Number of GPUs',
      items: [{
        id: '2',
        label: '2',
        default: false
      }, {
        id: '4',
        label: '4',
        default: true
      }, {
        id: '8',
        label: '8',
        default: false
      }]
    },
    strategy: {
      name: 'strategy',
      title: 'Deployment Strategy',
      type: 'checkbox',
      items: [{
        id: 'tp',
        label: 'TP',
        subtitle: 'Tensor Parallel',
        default: true,
        required: true
      }, {
        id: 'dp',
        label: 'DP',
        subtitle: 'Data Parallel',
        default: false
      }, {
        id: 'ep',
        label: 'EP',
        subtitle: 'Expert Parallel',
        default: false
      }, {
        id: 'mtp',
        label: 'MTP',
        subtitle: 'Multi-token Prediction',
        default: false
      }]
    },
    thinking: {
      name: 'thinking',
      title: 'Thinking Capabilities',
      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 SUPPORT = {
    b200: {
      nvfp4: [2, 4, 8],
      fp8: [4, 8],
      bf16: [8]
    },
    gb200: {
      nvfp4: [2, 4],
      fp8: [4]
    },
    h200: {
      fp8: [8],
      bf16: [8]
    },
    mi300x: {
      fp8: [2, 4, 8],
      bf16: [4, 8]
    },
    mi325x: {
      fp8: [2, 4, 8],
      bf16: [4, 8]
    },
    mi355x: {
      fp8: [2, 4, 8],
      bf16: [4, 8]
    }
  };
  const quantSupported = (hw, q) => Boolean(SUPPORT[hw] && SUPPORT[hw][q]);
  const allowedTps = (hw, q) => SUPPORT[hw] && SUPPORT[hw][q] || [];
  const firstSupportedQuant = hw => Object.keys(SUPPORT[hw] || ({}))[0] || '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 => {
      const next = {
        ...prev,
        [optionName]: value
      };
      if (optionName === 'hardware' || optionName === 'quantization') {
        if (!quantSupported(next.hardware, next.quantization)) {
          next.quantization = firstSupportedQuant(next.hardware);
        }
        const tps = allowedTps(next.hardware, next.quantization);
        if (tps.length && !tps.includes(parseInt(next.gpus, 10))) {
          next.gpus = String(tps.includes(4) ? 4 : tps[0]);
        }
      }
      return next;
    });
  };
  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, quantization, gpus, strategy, thinking, toolcall} = values;
    const strategyArray = Array.isArray(strategy) ? strategy : [];
    const isNvidiaBlackwell = hardware === 'b200' || hardware === 'gb200';
    const isAMD = hardware === 'mi300x' || hardware === 'mi325x' || hardware === 'mi355x';
    if (!quantSupported(hardware, quantization)) {
      return `# ${quantization.toUpperCase()} is not supported on ${hardware.toUpperCase()} per the §3.2 matrix.\n` + `# Pick a highlighted weight type above.`;
    }
    let modelName = 'zai-org/GLM-4.7';
    if (quantization === 'nvfp4') {
      modelName = 'nvidia/GLM-4.7-NVFP4';
    } else if (quantization === 'fp8') {
      modelName = 'zai-org/GLM-4.7-FP8';
    }
    let cmd = 'python -m sglang.launch_server \\\n';
    cmd += `  --model ${modelName}`;
    if (isAMD) {
      let tpValue = 4;
      if (hardware === 'mi355x') {
        tpValue = quantization === 'fp8' ? 2 : 4;
      }
      cmd += ` \\\n  --tp ${tpValue}`;
      if ((hardware === 'mi300x' || hardware === 'mi325x') && quantization === 'bf16') {
        cmd += ` \\\n  --max-context-length 8192 \\\n  --mem-fraction-static 0.9`;
      }
      if (strategyArray.includes('dp')) {
        cmd += ` \\\n  --dp 8 \\\n  --enable-dp-attention`;
      }
      if (strategyArray.includes('ep')) {
        cmd += ` \\\n  --ep 8`;
      }
    } else {
      const tps = allowedTps(hardware, quantization);
      let tpValue = parseInt(gpus, 10) || tps[0];
      if (!tps.includes(tpValue)) {
        tpValue = tps.includes(4) ? 4 : tps[0];
      }
      cmd += ` \\\n  --tp-size ${tpValue}`;
      if (isNvidiaBlackwell && quantization === 'nvfp4' && strategyArray.includes('ep')) {
        cmd += ` \\\n  --ep ${tpValue}`;
      }
      if (isNvidiaBlackwell && quantization === 'nvfp4') {
        cmd += ` \\\n  --mem-fraction-static 0.85`;
      }
    }
    if (strategyArray.includes('mtp')) {
      cmd += ` \\\n  --speculative-algorithm EAGLE \\\n  --speculative-num-steps 3 \\\n  --speculative-eagle-topk 1 \\\n  --speculative-num-draft-tokens 4`;
    }
    if (toolcall === 'enabled') {
      cmd += ` \\\n  --tool-call-parser glm47`;
    }
    if (thinking === 'enabled') {
      cmd += ` \\\n  --reasoning-parser glm45`;
    }
    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'}`
  };
  const hwSel = values.hardware;
  const isAMDSel = hwSel === 'mi300x' || hwSel === 'mi325x' || hwSel === 'mi355x';
  const isBlackwellSel = hwSel === 'b200' || hwSel === 'gb200';
  const strategyApplies = id => {
    if (id === 'dp') return isAMDSel;
    if (id === 'ep') return isAMDSel || isBlackwellSel && values.quantization === 'nvfp4';
    return true;
  };
  return <div style={containerStyle} className="not-prose">
      {Object.entries(options).map(([key, option]) => {
    const gpusGroupAMD = key === 'gpus' && isAMDSel;
    return <div key={key} style={cardStyle}>
          <div style={titleStyle}>{option.title}{gpusGroupAMD ? ' (N/A for AMD)' : ''}</div>
          <div style={itemsStyle}>
            {option.type === 'checkbox' ? option.items.map(item => {
      const isChecked = (values[option.name] || []).includes(item.id);
      const isDisabled = item.required || key === 'strategy' && !strategyApplies(item.id);
      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;
      const isDisabled = key === 'gpus' && (gpusGroupAMD || !allowedTps(values.hardware, values.quantization).includes(parseInt(item.id, 10))) || key === 'quantization' && !quantSupported(values.hardware, item.id);
      return <label key={item.id} 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}>{generateCommand()}</pre>
      </div>
    </div>;
};

## 1. Model Introduction

[GLM-4.7](https://huggingface.co/zai-org/GLM-4.7) is a powerful language model developed by Zhipu AI, featuring advanced capabilities in reasoning, function calling, and agent workflows.

GLM-4.7 brings improvements across all major domains:

* **Extended Context Window**: Expanded context window supporting even longer documents and complex multi-turn conversations
* **Enhanced Reasoning**: Improved reasoning capabilities with better chain-of-thought processing
* **Superior Coding**: Significantly improved code generation and understanding, with better real-world application performance
* **Advanced Tool Use**: More robust tool calling and agent capabilities for complex workflows
* **Optimized Performance**: Better throughput and latency characteristics across all hardware platforms

For more details, please refer to the [official GLM-4.7 documentation](https://docs.z.ai/guides/llm/glm-4.7).

**Key Features:**

* **State-of-the-Art Reasoning**: Enhanced reasoning capabilities for the most complex problem-solving tasks
* **Multiple Quantizations**: BF16, FP8, and NVFP4 variants for different performance/memory trade-offs
* **Hardware Optimization**: Tuned for NVIDIA Blackwell (B200, GB200) and AMD MI300X/MI325X/MI355X GPUs
* **High Performance**: Optimized for both throughput and latency scenarios

**Available Models:**

* **BF16 (Full precision)**: [zai-org/GLM-4.7](https://huggingface.co/zai-org/GLM-4.7)
* **FP8 (8-bit quantized)**: [zai-org/GLM-4.7-FP8](https://huggingface.co/zai-org/GLM-4.7-FP8)
* **NVFP4 (4-bit, NVIDIA Blackwell)**: [nvidia/GLM-4.7-NVFP4](https://huggingface.co/nvidia/GLM-4.7-NVFP4)

**License:**

Please refer to the [official GLM-4.7 model card](https://huggingface.co/zai-org/GLM-4.7) for license details.

## 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.

**Docker Images by Hardware Platform:**

<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
  <thead>
    <tr style={{borderBottom: "2px solid #d55816"}}>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Hardware Platform</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Docker Image</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>NVIDIA H100 / H200 / B200</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`lmsysorg/sglang:v0.5.12`</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>NVIDIA GB200 / B300 / GB300 (aarch64)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`lmsysorg/sglang:v0.5.12-cu130`</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>AMD MI300X / MI325X</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`lmsysorg/sglang:v0.5.12-rocm720-mi30x`</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>AMD MI355X</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`lmsysorg/sglang:v0.5.12-rocm720-mi35x`</td>
    </tr>
  </tbody>
</table>

## 3. Model Deployment

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

### 3.1 Basic Configuration

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

<GLM47Deployment />

### 3.2 Configuration Tips

Pick a weight format by hardware: **NVFP4** on NVIDIA Blackwell (B200, GB200), **FP8** on H100/H200/AMD, **BF16** as the full-precision fallback. The recommended tensor-parallel size per platform:

<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
  <thead>
    <tr style={{borderBottom: "2px solid #d55816"}}>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Hardware</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>NVFP4</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>FP8</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>BF16</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>B200 (8×, single node)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>tp=2 / 4 / 8</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>tp=4 / 8</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>tp=8</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>GB200 (NVL72, 4× per tray)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>tp=2 / 4</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>tp=4</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>—</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>H200 (8×)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>—</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>tp=8</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>tp=8</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>AMD MI300X / MI325X / MI355X</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>—</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>tp=2 / 4 / 8</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>tp=4 / 8</td>
    </tr>
  </tbody>
</table>

* **EAGLE Speculative Decoding:** Supported for GLM-4.7. Add `--speculative-algorithm EAGLE --speculative-num-steps 3 --speculative-eagle-topk 1 --speculative-num-draft-tokens 4`. The spec-v2 overlap scheduler is enabled by default; pass `--disable-overlap-schedule` to disable. Enable via the interactive command generator above.
* **Thinking Budget:** Use `--enable-custom-logit-processor` flag and pass `Glm4MoeThinkingBudgetLogitProcessor` in requests to cap the model's thinking token count (see section 4.2.3).

For general GLM-4.x family launch guidance (AMD ROCm notes and more), see [Launch GLM-4.5 / GLM-4.6 / GLM-4.7 with SGLang](/cookbook/autoregressive/GLM/GLM-4.5). Per-hardware bench commands and flags are inline in §5.1 below.

## 4. Model Invocation

### 4.1 Basic Usage

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

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

### 4.2 Advanced Usage

#### 4.2.1 Reasoning Parser

GLM-4.7 supports Thinking mode by default. Enable the reasoning parser during deployment to separate the thinking and the content sections:

```shell Command theme={null}
python -m sglang.launch_server \
  --model zai-org/GLM-4.7 \
  --reasoning-parser glm45 \
  --tp 8 \
  --host 0.0.0.0 \
  --port 8000
```

**Streaming with Thinking Process:**

```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="zai-org/GLM-4.7",
    messages=[
        {"role": "user", "content": "Solve this problem step by step: What is 15% of 240?"}
    ],
    temperature=0.7,
    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 =================
To solve this problem, I need to calculate 15% of 240.
Step 1: Convert 15% to decimal: 15% = 0.15
Step 2: Multiply 240 by 0.15
Step 3: 240 × 0.15 = 36
=============== Content =================

The answer is 36. To find 15% of 240, we multiply 240 by 0.15, which equals 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

<Note>
  **Parser names by model:** GLM-4.5 and GLM-4.6 use `--tool-call-parser glm45`. GLM-4.7 and GLM-4.7-Flash use `--tool-call-parser glm47`. All GLM models use `--reasoning-parser glm45` regardless of generation.
</Note>

GLM-4.7 supports tool calling capabilities. Enable the tool call parser:

```shell Command theme={null}
python -m sglang.launch_server \
  --model zai-org/GLM-4.7 \
  --reasoning-parser glm45 \
  --tool-call-parser glm47 \
  --tp 8 \
  --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="zai-org/GLM-4.7",
    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

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 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 =================", flush=True)
                thinking_started = False

            for tool_call in delta.tool_calls:
                if tool_call.function:
                    print(f"Tool Call: {tool_call.function.name}")
                    print(f"   Arguments: {tool_call.function.arguments}")

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

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.
I should call the function with location="Beijing".
=============== Content =================

Tool Call: get_weather
   Arguments: {"location": "Beijing", "unit": "celsius"}
```

**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="zai-org/GLM-4.7",
    messages=messages,
    temperature=0.7
)

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

#### 4.2.3 Thinking Budget

Limit the number of thinking tokens using `CustomLogitProcessor`. Launch with `--enable-custom-logit-processor`:

```python Example theme={null}
import openai
from sglang.srt.sampling.custom_logit_processor import Glm4MoeThinkingBudgetLogitProcessor

client = openai.Client(base_url="http://127.0.0.1:30000/v1", api_key="*")
response = client.chat.completions.create(
    model="zai-org/GLM-4.7",
    messages=[{"role": "user", "content": "Is Paris the Capital of France?"}],
    max_tokens=1024,
    extra_body={
        "custom_logit_processor": Glm4MoeThinkingBudgetLogitProcessor().to_str(),
        "custom_params": {"thinking_budget": 512},
    },
)
print(response)
```

## 5. Benchmark

This section uses **industry-standard configurations** for comparable benchmark results.

### 5.1 Speed Benchmark

**Test Environment:**

* Hardware: NVIDIA B200, NVIDIA GB200, AMD MI300X/MI325X/MI355X (8x)
* Model: GLM-4.7-NVFP4 on NVIDIA Blackwell; GLM-4.7-FP8 or GLM-4.7 (BF16) on AMD
* SGLang Version: 0.5.12 (NVIDIA Blackwell), 0.5.6.post1 (AMD)
* Best per-GPU throughput config on B200: **TP=2 NVFP4 bf16-KV** (NVFP4 weights, no EP). Numbers below come from this config.

**Benchmark Methodology:**

We use industry-standard benchmark configurations to ensure results are comparable across frameworks and hardware platforms.

#### 5.1.1 Standard Test Scenarios

Four core scenarios reflect real-world usage patterns:

<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
  <colgroup>
    <col style={{width: "25%"}} />

    <col style={{width: "25%"}} />

    <col style={{width: "25%"}} />

    <col style={{width: "25%"}} />
  </colgroup>

  <thead>
    <tr style={{borderBottom: "2px solid #d55816"}}>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Scenario</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Input Length</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Output Length</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Use Case</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>**Chat**</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>1K</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>1K</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Most common conversational AI workload</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>**Reasoning**</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>1K</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>8K</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Long-form generation, complex reasoning tasks</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>**Summarization**</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>8K</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>1K</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Document summarization, RAG retrieval</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>**Throughput**</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>4K</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>1K</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Mixed RAG / agent / multi-turn conversation (used for the inline B200 / GB200 results below)</td>
    </tr>
  </tbody>
</table>

#### 5.1.2 Concurrency Levels

Test each scenario at three concurrency levels to capture the throughput vs. latency tradeoff (Pareto frontier):

* **Low Concurrency**: `--max-concurrency 1` (Latency-optimized)
* **Medium Concurrency**: `--max-concurrency 16` (Balanced)
* **High Concurrency**: `--max-concurrency 100` (Throughput-optimized) — the Throughput (4K/1K) scenario uses `--max-concurrency 128` to match the inline B200/GB200 results below.

#### 5.1.3 Number of Prompts

For each concurrency level, configure `num_prompts` to simulate realistic user loads:

* **Quick Test**: `num_prompts = concurrency × 1` (minimal test)
* **Recommended**: `num_prompts = concurrency × 5` (standard benchmark)
* **Stable Measurements**: `num_prompts = concurrency × 10` (production-grade)

***

#### 5.1.4 Benchmark Commands

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

* **Model Deployment**

```bash Command theme={null}
python -m sglang.launch_server \
  --model zai-org/GLM-4.7 \
  --tp 8
```

* Low Concurrency (Latency-Optimized)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-4.7 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 10 \
  --max-concurrency 1 \
  --request-rate inf
```

* Medium Concurrency (Balanced)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-4.7 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 80 \
  --max-concurrency 16 \
  --request-rate inf
```

* High Concurrency (Throughput-Optimized)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-4.7 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 1000 \
  --num-prompts 500 \
  --max-concurrency 100 \
  --request-rate inf
```

**Scenario 2: Reasoning (1K/8K)**

* Low Concurrency

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-4.7 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 8000 \
  --num-prompts 10 \
  --max-concurrency 1 \
  --request-rate inf
```

* Medium Concurrency

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-4.7 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 8000 \
  --num-prompts 80 \
  --max-concurrency 16 \
  --request-rate inf
```

* High Concurrency

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-4.7 \
  --dataset-name random \
  --random-input-len 1000 \
  --random-output-len 8000 \
  --num-prompts 320 \
  --max-concurrency 64 \
  --request-rate inf
```

**Scenario 3: Summarization (8K/1K)**

* Low Concurrency

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-4.7 \
  --dataset-name random \
  --random-input-len 8000 \
  --random-output-len 1000 \
  --num-prompts 10 \
  --max-concurrency 1 \
  --request-rate inf
```

* Medium Concurrency

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-4.7 \
  --dataset-name random \
  --random-input-len 8000 \
  --random-output-len 1000 \
  --num-prompts 80 \
  --max-concurrency 16 \
  --request-rate inf
```

* High Concurrency

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-4.7 \
  --dataset-name random \
  --random-input-len 8000 \
  --random-output-len 1000 \
  --num-prompts 320 \
  --max-concurrency 64 \
  --request-rate inf
```

**Scenario 4: Throughput (4K/1K) — NVIDIA Blackwell with NVFP4**

The remaining sub-sections (§5.1.4.1 NVIDIA B200, §5.1.4.2 NVIDIA GB200) measure this scenario with `nvidia/GLM-4.7-NVFP4` weights and report the full `bench_serving` output verbatim. The same commands apply to other NVIDIA hardware after substituting the deployment line from §3.1.

> **Note**: These runs use EOS-enabled generation (no `--disable-ignore-eos`), so generated-token counts reflect natural model behavior rather than a strict fixed-OSL pin. Compare against other EOS-enabled runs at the same workload, not against fixed-output-length benchmarks.

#### 5.1.4.1 NVIDIA B200

**Model Deployment (NVIDIA B200, TP=2 NVFP4 — max tok/s/gpu config):**

```bash Command theme={null}
python -m sglang.launch_server \
  --model nvidia/GLM-4.7-NVFP4 \
  --tp-size 2 \
  --mem-fraction-static 0.85 \
  --reasoning-parser glm45 \
  --tool-call-parser glm47
```

* Low Concurrency (Latency-Optimized)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model nvidia/GLM-4.7-NVFP4 \
  --dataset-name random \
  --random-input-len 4096 \
  --random-output-len 1024 \
  --num-prompts 5 \
  --max-concurrency 1 \
  --request-rate inf
```

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Max request concurrency:                 1
Successful requests:                     5
Benchmark duration (s):                  25.07
Total input tokens:                      8105
Total generated tokens:                  2674
Request throughput (req/s):              0.20
Input token throughput (tok/s):          323.25
Output token throughput (tok/s):         106.65
Total token throughput (tok/s):          429.90
Concurrency:                             1.00
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   5011.93
Median E2E Latency (ms):                 6441.44
---------------Time to First Token----------------
Mean TTFT (ms):                          179.61
Median TTFT (ms):                        169.05
P99 TTFT (ms):                           238.01
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          9.05
Median TPOT (ms):                        9.03
P99 TPOT (ms):                           9.16
---------------Inter-Token Latency----------------
Mean ITL (ms):                           9.05
Median ITL (ms):                         9.05
==================================================
```

* Medium Concurrency (Balanced)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model nvidia/GLM-4.7-NVFP4 \
  --dataset-name random \
  --random-input-len 4096 \
  --random-output-len 1024 \
  --num-prompts 80 \
  --max-concurrency 16 \
  --request-rate inf
```

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Max request concurrency:                 16
Successful requests:                     80
Benchmark duration (s):                  60.60
Total input tokens:                      179772
Total generated tokens:                  39657
Request throughput (req/s):              1.32
Input token throughput (tok/s):          2966.39
Output token throughput (tok/s):         654.37
Total token throughput (tok/s):          3620.76
Concurrency:                             14.01
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   10615.87
Median E2E Latency (ms):                 9985.45
---------------Time to First Token----------------
Mean TTFT (ms):                          267.39
Median TTFT (ms):                        177.26
P99 TTFT (ms):                           584.29
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          20.98
Median TPOT (ms):                        21.06
P99 TPOT (ms):                           24.88
---------------Inter-Token Latency----------------
Mean ITL (ms):                           20.92
Median ITL (ms):                         17.93
==================================================
```

* High Concurrency (Throughput-Optimized)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model nvidia/GLM-4.7-NVFP4 \
  --dataset-name random \
  --random-input-len 4096 \
  --random-output-len 1024 \
  --num-prompts 640 \
  --max-concurrency 128 \
  --request-rate inf
```

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Max request concurrency:                 128
Successful requests:                     640
Benchmark duration (s):                  172.95
Total input tokens:                      1453591
Total generated tokens:                  308740
Request throughput (req/s):              3.70
Input token throughput (tok/s):          8404.67
Output token throughput (tok/s):         1785.14
Total token throughput (tok/s):          10189.80
Concurrency:                             117.85
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   31848.20
Median E2E Latency (ms):                 28554.42
---------------Time to First Token----------------
Mean TTFT (ms):                          1598.40
Median TTFT (ms):                        298.88
P99 TTFT (ms):                           11015.96
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          65.94
Median TPOT (ms):                        65.81
P99 TPOT (ms):                           137.73
---------------Inter-Token Latency----------------
Mean ITL (ms):                           62.99
Median ITL (ms):                         35.44
==================================================
```

#### 5.1.4.2 NVIDIA GB200

**Model Deployment (NVIDIA GB200, TP=2 NVFP4 — max tok/s/gpu config):**

```bash Command theme={null}
python -m sglang.launch_server \
  --model nvidia/GLM-4.7-NVFP4 \
  --tp-size 2 \
  --mem-fraction-static 0.85 \
  --reasoning-parser glm45 \
  --tool-call-parser glm47
```

* Low Concurrency (Latency-Optimized)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model nvidia/GLM-4.7-NVFP4 \
  --dataset-name random \
  --random-input-len 4096 \
  --random-output-len 1024 \
  --num-prompts 5 \
  --max-concurrency 1 \
  --request-rate inf
```

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Max request concurrency:                 1
Successful requests:                     5
Benchmark duration (s):                  24.74
Total input tokens:                      8105
Total generated tokens:                  2674
Request throughput (req/s):              0.20
Input token throughput (tok/s):          327.65
Output token throughput (tok/s):         108.10
Total token throughput (tok/s):          435.75
Concurrency:                             1.00
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   4944.47
Median E2E Latency (ms):                 6347.31
---------------Time to First Token----------------
Mean TTFT (ms):                          211.41
Median TTFT (ms):                        207.25
P99 TTFT (ms):                           226.46
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          8.86
Median TPOT (ms):                        8.84
P99 TPOT (ms):                           8.96
---------------Inter-Token Latency----------------
Mean ITL (ms):                           8.87
Median ITL (ms):                         8.85
==================================================
```

* Medium Concurrency (Balanced)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model nvidia/GLM-4.7-NVFP4 \
  --dataset-name random \
  --random-input-len 4096 \
  --random-output-len 1024 \
  --num-prompts 80 \
  --max-concurrency 16 \
  --request-rate inf
```

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Max request concurrency:                 16
Successful requests:                     80
Benchmark duration (s):                  60.40
Total input tokens:                      179772
Total generated tokens:                  39657
Request throughput (req/s):              1.32
Input token throughput (tok/s):          2976.52
Output token throughput (tok/s):         656.61
Total token throughput (tok/s):          3633.13
Concurrency:                             13.97
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   10611.51
Median E2E Latency (ms):                 9956.84
---------------Time to First Token----------------
Mean TTFT (ms):                          338.14
Median TTFT (ms):                        215.25
P99 TTFT (ms):                           915.40
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          20.87
Median TPOT (ms):                        21.36
P99 TPOT (ms):                           27.05
---------------Inter-Token Latency----------------
Mean ITL (ms):                           20.77
Median ITL (ms):                         16.53
==================================================
```

* High Concurrency (Throughput-Optimized)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model nvidia/GLM-4.7-NVFP4 \
  --dataset-name random \
  --random-input-len 4096 \
  --random-output-len 1024 \
  --num-prompts 640 \
  --max-concurrency 128 \
  --request-rate inf
```

```text Output theme={null}
============ Serving Benchmark Result ============
Backend:                                 sglang
Max request concurrency:                 128
Successful requests:                     640
Benchmark duration (s):                  181.89
Total input tokens:                      1453591
Total generated tokens:                  309221
Request throughput (req/s):              3.52
Input token throughput (tok/s):          7991.59
Output token throughput (tok/s):         1700.04
Total token throughput (tok/s):          9691.63
Concurrency:                             118.86
----------------End-to-End Latency----------------
Mean E2E Latency (ms):                   33690.47
Median E2E Latency (ms):                 30421.55
---------------Time to First Token----------------
Mean TTFT (ms):                          1353.16
Median TTFT (ms):                        383.52
P99 TTFT (ms):                           8940.53
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          69.88
Median TPOT (ms):                        71.77
P99 TPOT (ms):                           131.75
---------------Inter-Token Latency----------------
Mean ITL (ms):                           67.23
Median ITL (ms):                         33.46
==================================================
```

#### 5.1.5 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.
* **4K/1K (Throughput)**: Realistic mixed workload typical of production deployments (RAG context + medium response). Long enough input that prefill matters, long enough output that decode steady-state dominates. Used for the inline B200 / GB200 results above.
* **Variable Concurrency**: Captures the Pareto frontier - the optimal tradeoff 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

### 5.2 Accuracy Benchmark

Document model accuracy on standard benchmarks:

#### 5.2.1 GSM8K Benchmark

* Benchmark Command

```bash Command theme={null}
python -m sglang.test.few_shot_gsm8k \
  --num-shots 5 \
  --num-questions 1319 \
  --port 30000
```

* Test Result (NVIDIA B200, TP=2 NVFP4)

```text Output theme={null}
Accuracy: 0.946
Latency: 178.284 s
Output throughput: 769.204 token/s
```

* Test Result (NVIDIA GB200, TP=2 NVFP4)

```text Output theme={null}
Accuracy: 0.951
Latency: 175.190 s
Invalid: 0.000
```