> ## 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-4.5

export const GLM45Deployment = () => {
  const options = {
    hardware: {
      name: 'hardware',
      title: 'Hardware Platform',
      items: [{
        id: 'mi300x',
        label: 'MI300X',
        default: true
      }, {
        id: 'mi325x',
        label: 'MI325X',
        default: false
      }, {
        id: 'mi355x',
        label: 'MI355X',
        default: false
      }]
    },
    quantization: {
      name: 'quantization',
      title: 'Quantization',
      items: [{
        id: 'bf16',
        label: 'BF16',
        default: true
      }, {
        id: 'fp8',
        label: 'FP8',
        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 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, quantization, strategy, thinking, toolcall} = values;
    const strategyArray = Array.isArray(strategy) ? strategy : [];
    const modelSuffix = quantization === 'fp8' ? '-FP8' : '';
    const modelName = `zai-org/GLM-4.5${modelSuffix}`;
    let tpValue = 4;
    if (hardware === 'mi355x') {
      tpValue = quantization === 'fp8' ? 2 : 4;
    }
    let cmd = 'python -m sglang.launch_server \\\n';
    cmd += `  --model ${modelName}`;
    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`;
    }
    if (strategyArray.includes('mtp')) {
      cmd = 'SGLANG_ENABLE_SPEC_V2=1 ' + cmd;
      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 glm45`;
    }
    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'}`
  };
  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

[GLM-4.5](https://huggingface.co/zai-org/GLM-4.5) is a powerful language model developed by Zhipu AI, featuring advanced capabilities in reasoning, function calling, and multi-modal understanding.

**Key Features:**

* **Advanced Reasoning**: Built-in reasoning capabilities for complex problem-solving
* **Multiple Quantizations**: BF16 and FP8 variants for different performance/memory trade-offs
* **Hardware Optimization**: Specifically tuned for AMD MI300X/MI325X/MI355X GPUs
* **High Performance**: Optimized for both throughput and latency scenarios

**Available Models:**

* **BF16 (Full precision)**: [zai-org/GLM-4.5](https://huggingface.co/zai-org/GLM-4.5) - Recommended for MI300X/MI325X/MI355X
* **FP8 (8-bit quantized)**: [zai-org/GLM-4.5-FP8](https://huggingface.co/zai-org/GLM-4.5-FP8) - Recommended for MI300X/MI325X/MI355X

**License:**

Please refer to the [official GLM-4.5 model card](https://huggingface.co/zai-org/GLM-4.5) 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.

## 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.

<GLM45Deployment />

### 3.2 Configuration Tips

For more detailed configuration tips, please refer to [GLM-4.5/GLM-4.6 Usage](../../../docs/basic_usage/glm45).

## 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-4.5 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-4.5 \
  --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-4.5",
    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

GLM-4.5 supports tool calling capabilities. Enable the tool call parser:

```shell Command theme={null}
python -m sglang.launch_server \
  --model zai-org/GLM-4.5 \
  --reasoning-parser glm45 \
  --tool-call-parser glm45 \
  --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-4.5",
    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"}
```

## 5. Benchmark

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

### 5.1 Speed Benchmark

**Test Environment:**

* Hardware: AMD MI300X (8x), AMD MI325X (8x), AMD MI355X (8x)
* Model: GLM-4.5
* Tensor Parallelism: 8
* SGLang Version: 0.5.6.post1

**Benchmark Methodology:**

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

#### 5.1.1 Standard Test Scenarios

Three 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>
  </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)

#### 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-4.5 \
  --tp 8
```

* Low Concurrency (Latency-Optimized)

```bash Command theme={null}
python -m sglang.bench_serving \
  --backend sglang \
  --model zai-org/GLM-4.5 \
  --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-4.5 \
  --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-4.5 \
  --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-4.5 \
  --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-4.5 \
  --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-4.5 \
  --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-4.5 \
  --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-4.5 \
  --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-4.5 \
  --dataset-name random \
  --random-input-len 8000 \
  --random-output-len 1000 \
  --num-prompts 320 \
  --max-concurrency 64 \
  --request-rate inf
```

#### 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.
* **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-questions 200 \
  --port 30000
```