> ## 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.

# Intern-S1

export const InternS1Deployment = () => {
  const options = {
    hardware: {
      name: 'hardware',
      title: 'Hardware Platform',
      items: [{
        id: 'b200',
        label: 'B200',
        default: true
      }, {
        id: 'b300',
        label: 'B300',
        default: false
      }, {
        id: 'h100',
        label: 'H100',
        default: false
      }, {
        id: 'h200',
        label: 'H200',
        default: false
      }]
    },
    modelsize: {
      name: 'modelsize',
      title: 'Model Size',
      items: [{
        id: 'S1',
        label: '235B',
        subtitle: 'MoE',
        default: true
      }, {
        id: 'S1-mini',
        label: '8B',
        subtitle: 'Dense',
        default: false
      }]
    },
    quantization: {
      name: 'quantization',
      title: 'Quantization',
      items: [{
        id: 'bf16',
        label: 'BF16',
        default: true
      }, {
        id: 'fp8',
        label: 'FP8',
        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 modelConfigs = {
    S1: {
      baseName: 'S1',
      h100: {
        bf16: {
          tp: 8
        },
        fp8: {
          tp: 8,
          ep: 2
        }
      },
      h200: {
        bf16: {
          tp: 8
        },
        fp8: {
          tp: 8,
          ep: 2
        }
      },
      b200: {
        bf16: {
          tp: 8
        },
        fp8: {
          tp: 8,
          ep: 2
        }
      },
      b300: {
        bf16: {
          tp: 8
        },
        fp8: {
          tp: 8,
          ep: 2
        }
      }
    },
    'S1-mini': {
      baseName: 'S1-mini',
      h100: {
        bf16: {
          tp: 1
        },
        fp8: {
          tp: 1
        }
      },
      h200: {
        bf16: {
          tp: 1
        },
        fp8: {
          tp: 1
        }
      },
      b200: {
        bf16: {
          tp: 1
        },
        fp8: {
          tp: 1
        }
      },
      b300: {
        bf16: {
          tp: 1
        },
        fp8: {
          tp: 1
        }
      }
    }
  };
  const getInitialState = () => {
    const initialState = {};
    Object.entries(options).forEach(([key, option]) => {
      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 generateCommand = () => {
    const {hardware, modelsize, quantization, reasoning, toolcall} = values;
    const modelConfig = modelConfigs[modelsize];
    const hwConfig = modelConfig?.[hardware]?.[quantization];
    if (!hwConfig) {
      return '# Please select a valid hardware and quantization combination';
    }
    const quantSuffix = quantization === 'fp8' ? '-FP8' : '';
    const modelName = `internlm/Intern-${modelConfig.baseName}${quantSuffix}`;
    const flags = [];
    flags.push(`  --model ${modelName}`);
    if (hwConfig.tp > 1) flags.push(`  --tp ${hwConfig.tp}`);
    if (hwConfig.ep) flags.push(`  --ep ${hwConfig.ep}`);
    if (quantization === 'fp8') flags.push(`  --tokenizer-path internlm/Intern-${modelConfig.baseName}`);
    if (reasoning === 'enabled') flags.push('  --reasoning-parser interns1');
    if (toolcall === 'enabled') flags.push('  --tool-call-parser interns1');
    flags.push('  --trust-remote-code');
    if (hardware === 'b300') flags.push('  --attention-backend flashinfer');
    return `python -m sglang.launch_server \\\n${flags.join(' \\\n')}`;
  };
  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 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.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

Intern-S1 includes the large **Intern-S1** MoE model and the smaller **Intern-S1-mini** dense model. The command generator below covers BF16 and FP8 serving on NVIDIA H100/H200/B200/B300 platforms.

## 2. SGLang Installation

Refer to the [official SGLang installation guide](../../../docs/get-started/install), or install from source:

```bash Command theme={null}
uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=python'
```

## 3. Model Deployment

### 3.1 Basic Configuration

<InternS1Deployment />

### 3.2 Configuration Tips

* FP8 checkpoints use the matching BF16 checkpoint as tokenizer path.
* B300 deployments use `--attention-backend flashinfer`.
* Enable `--reasoning-parser interns1` and `--tool-call-parser interns1` when your workload needs structured reasoning or tool-call parsing.