> ## Documentation Index
> Fetch the complete documentation index at: https://lmsysorg-dsv4-1.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Wan2.2

export const Wan22Deployment = () => {
  const options = {
    hardware: {
      name: 'hardware',
      title: 'Hardware Platform',
      items: [{
        id: 'b200',
        label: 'B200',
        default: true
      }, {
        id: 'b300',
        label: 'B300',
        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
      }, {
        id: 'a2',
        label: 'A2 Series',
        default: false
      }, {
        id: 'a3',
        label: 'A3 Series',
        default: false
      }]
    },
    task: {
      name: 'task',
      title: 'Task Type',
      items: [{
        id: 'i2v',
        label: 'Image-to-Video (I2V)',
        default: false
      }, {
        id: 't2v',
        label: 'Text-to-Video (T2V)',
        default: true
      }, {
        id: 'ti2v',
        label: 'Text/Image-to-Video (TI2V)',
        default: false
      }]
    },
    modelsize: {
      name: 'modelsize',
      title: 'Model Size',
      items: [{
        id: '14b',
        label: 'A14B',
        subtitle: 'Diffusers (A14B)',
        default: true,
        validTasks: ['i2v', 't2v']
      }, {
        id: '5b',
        label: '5B',
        subtitle: 'Diffusers',
        default: false,
        validTasks: ['ti2v']
      }]
    },
    bestPractice: {
      name: 'bestPractice',
      title: 'Optimization',
      items: [{
        id: 'off',
        label: 'Standard',
        default: true
      }, {
        id: 'on',
        label: 'Best Practice',
        default: false
      }]
    }
  };
  const modelConfigs = {
    'i2v-14b': {
      repoId: 'Wan-AI/Wan2.2-I2V-A14B-Diffusers',
      supportedLoras: [{
        id: 'distill',
        path: 'lightx2v/Wan2.2-Distill-Loras'
      }]
    },
    't2v-14b': {
      repoId: 'Wan-AI/Wan2.2-T2V-A14B-Diffusers',
      supportedLoras: [{
        id: 'arcane',
        path: 'Cseti/wan2.2-14B-Arcane_Jinx-lora-v1'
      }]
    },
    'ti2v-5b': {
      repoId: 'Wan-AI/Wan2.2-TI2V-5B-Diffusers',
      supportedLoras: []
    }
  };
  const getInitialState = () => ({
    hardware: 'b200',
    task: 't2v',
    modelsize: '14b',
    bestPractice: 'off',
    selectedLoraPath: 'none'
  });
  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 availableLoras = (() => {
    const configKey = `${values.task}-${values.modelsize}`;
    return modelConfigs[configKey]?.supportedLoras || [];
  })();
  useEffect(() => {
    const isAscend = values.hardware === 'a2' || values.hardware === 'a3';
    const targetTabName = isAscend ? 'Ascend A3 Series' : 'NVIDIA B200';
    const allTabs = document.querySelectorAll('button, [role="tab"]');
    allTabs.forEach(tab => {
      const text = tab.textContent.trim();
      if (text === targetTabName && tab.getAttribute('aria-selected') !== 'true') {
        tab.click();
      }
    });
  }, [values.hardware]);
  const handleRadioChange = (optionName, itemId) => {
    setValues(prev => {
      const next = {
        ...prev,
        [optionName]: itemId
      };
      if (optionName === 'task') {
        next.modelsize = itemId === 'ti2v' ? '5b' : '14b';
      }
      const configKey = `${next.task}-${next.modelsize}`;
      const nextSupported = modelConfigs[configKey]?.supportedLoras || [];
      const isValid = nextSupported.some(lora => lora.path === prev.selectedLoraPath);
      if (!isValid) {
        next.selectedLoraPath = 'none';
      }
      return next;
    });
  };
  const handleLoraToggle = path => {
    setValues(prev => ({
      ...prev,
      selectedLoraPath: prev.selectedLoraPath === path ? 'none' : path
    }));
  };
  const generateCommand = () => {
    const {hardware, task, modelsize, selectedLoraPath, bestPractice} = values;
    const configKey = `${task}-${modelsize}`;
    const config = modelConfigs[configKey];
    if (!config) {
      return '# Error: Invalid configuration';
    }
    if (hardware === 'a2' || hardware === 'a3') {
      const comment = hardware === 'a3' ? '#One A3 Series card has 2 npu chips\n' : '';
      const isBestPractice = bestPractice === 'on';
      let command;
      if (task === 'ti2v') {
        if (isBestPractice) {
          command = `${comment}sglang serve \\
  --model-path ${config.repoId} \\
  --sp-degree 8 \\
  --num-gpus 8`;
        } else if (hardware === 'a2') {
          command = `${comment}sglang serve \\
  --model-path ${config.repoId} \\
  --num-gpus 1`;
        } else {
          command = `${comment}sglang serve \\
  --model-path ${config.repoId} \\
  --tp-size 1 \\
  --sp-degree 2 \\
  --num-gpus 2`;
        }
      } else {
        const spDegree = isBestPractice ? 4 : 1;
        const numGpus = isBestPractice ? 8 : hardware === 'a3' ? 2 : 4;
        command = `${comment}sglang serve \\
  --model-path ${config.repoId} \\
  --tp-size 2 \\
  --sp-degree ${spDegree} \\
  --num-gpus ${numGpus}`;
      }
      if (isBestPractice) {
        command += ` \\\n  --attention-backend laser_attn`;
      }
      if (selectedLoraPath === 'lightx2v/Wan2.2-Distill-Loras' || selectedLoraPath === 'Cseti/wan2.2-14B-Arcane_Jinx-lora-v1') {
        command += ` \\\n  --lora-path ${selectedLoraPath}`;
      }
      return command;
    }
    let command = `sglang serve \\\n  --model-path ${config.repoId} \\\n  --dit-layerwise-offload true`;
    if (bestPractice === 'on') {
      if (hardware === 'b300') {
        command += ` \\\n  --tp-size 2 \\\n  --num-gpus 8 \\\n  --sp-degree 2 \\\n  --ulysses-degree 2 \\\n  --enable-cfg-parallel`;
      } else {
        command += ` \\\n  --num-gpus 4 \\\n  --ulysses-degree 2 \\\n  --enable-cfg-parallel`;
      }
    }
    if (selectedLoraPath && selectedLoraPath !== 'none') {
      command += ` \\\n  --lora-path ${selectedLoraPath}`;
    }
    return command;
  };
  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]) => {
    const itemsToDisplay = key === 'modelsize' ? option.items.filter(item => item.validTasks.includes(values.task)) : option.items;
    return <div key={key} style={cardStyle}>
                <div style={titleStyle}>{option.title}</div>
                <div style={itemsStyle}>
                  {itemsToDisplay.map(item => {
      const isChecked = values[option.name] === item.id;
      return <label key={item.id} style={{
        ...labelBaseStyle,
        ...isChecked ? checkedStyle : {}
      }}>
                        <input type="radio" name={option.name} checked={isChecked} onChange={() => handleRadioChange(key, 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}>Select LoRA Model (Only some of the supported LoRAs are listed here)</div>
            <div style={itemsStyle}>
              {availableLoras.length === 0 && <div style={{
    color: isDark ? '#999' : '#666',
    fontSize: '12px',
    padding: '8px'
  }}>
                  No LoRA models available for this model.
                </div>}
              {availableLoras.map(lora => {
    const isSelected = values.selectedLoraPath === lora.path;
    return <label key={lora.id} style={{
      ...labelBaseStyle,
      ...isSelected ? checkedStyle : {}
    }} onClick={event => {
      event.preventDefault();
      handleLoraToggle(lora.path);
    }}>
                    <input type="radio" name="loraModelSelection" checked={isSelected} readOnly style={{
      display: 'none'
    }} />
                    {lora.id}
                    <small style={{
      ...subtitleStyle,
      color: isSelected ? 'rgba(255,255,255,0.85)' : 'inherit'
    }}>
                      {lora.path}
                    </small>
                  </label>;
  })}
            </div>
          </div>

          <div style={cardStyle}>
            <div style={titleStyle}>Run this Command:</div>
            <pre style={commandDisplayStyle}>{generateCommand()}</pre>
          </div>
        </div>;
};

export const DiffusionModelTags = ({tags = []}) => {
  const normalizedTags = Array.isArray(tags) ? tags : [tags];
  return <div className="not-prose sgd-model-tags">
      {normalizedTags.map(tag => <span key={tag} className="sgd-chip">
          {tag}
        </span>)}
    </div>;
};

<DiffusionModelTags tags={["video", "T2V / I2V / TI2V", "MoE", "720p @ 24 fps", "cinematic motion"]} />

## 1. Model Introduction

[Wan2.2](https://github.com/Wan-Video/Wan2.2) extends the Wan family with timestep-specialized Mixture-of-Experts models and a unified 5B TI2V checkpoint. It targets cinematic composition, lighting, and complex motion while supporting text-to-video, image-to-video, and hybrid text/image conditioning.

Choose the A14B MoE checkpoints for maximum T2V or I2V capacity and the 5B TI2V model for a smaller unified 720p-at-24-fps path. MoE reduces active compute relative to total capacity but does not remove the memory cost of loading expert weights, so hardware selection still matters.

<Warning>
  The Wan2.2 TI2V 5B checkpoint currently has known quality issues when it is used
  for image-to-video generation. Use `Wan-AI/Wan2.2-I2V-A14B-Diffusers` when I2V
  quality is the priority.
</Warning>

## 2. SGLang-diffusion Installation

SGLang-diffusion 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-diffusion installation guide](https://docs.sglang.io/docs/sglang-diffusion/installation) for installation instructions.

## 3. Model Deployment

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

### 3.1 Basic Configuration

The Wan2.2 series offers models in various sizes, architectures and input types, optimized for different hardware platforms. The recommended launch configurations vary by hardware and model size.

**Interactive Command Generator**: Use the configuration selector below to automatically generate the appropriate deployment command for your hardware platform, model size. SGLang supports serving Wan2.2 on NVIDIA B200, H200, AMD MI300X, MI325X, MI355X GPUs and Ascend A2/A3 Series NPUs.

<Wan22Deployment />

### 3.2 Configuration Tips

See [Performance Optimization](/docs/sglang-diffusion/performance-optimization) for acceleration features and their runtime requirements.

* `--vae-path`: Path to a custom VAE model or HuggingFace model ID (e.g., fal/FLUX.2-Tiny-AutoEncoder). If not specified, the VAE will be loaded from the main model path.
* `--num-gpus {NUM_GPUS}`: Number of GPUs to use
* `--tp-size {TP_SIZE}`: Tensor parallelism size (only for the encoder; should not be larger than 1 if text encoder offload is enabled, as layer-wise offload plus prefetch is faster)
* `--sp-degree {SP_SIZE}`: Sequence parallelism size (typically should match the number of GPUs)
* `--ulysses-degree {ULYSSES_DEGREE}`: The degree of DeepSpeed-Ulysses-style SP in USP
* `--ring-degree {RING_DEGREE}`: The degree of ring attention-style SP in USP

## 4. Model Invocation

### 4.1 Basic Usage

For more API usage and request examples, please refer to:
[SGLang Diffusion OpenAI API](/docs/sglang-diffusion/api/openai_api)

#### 4.1.1 Launch a server and then send requests

```shell Command theme={null}
sglang serve --model-path Wan-AI/Wan2.2-T2V-A14B-Diffusers --port 3000

curl http://127.0.0.1:3000/v1/images/generations \
  -o >(jq -r '.data[0].b64_json' | base64 --decode > example.png) \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "model": "Wan-AI/Wan2.2-T2V-A14B-Diffusers",
    "prompt": "A cute baby sea otter",
    "n": 1,
    "size": "1024x1024",
    "response_format": "b64_json"
  }'
```

#### 4.1.2 Generate a video without launching a server

```shell Command theme={null}
SERVER_ARGS=(
  --model-path Wan-AI/Wan2.2-T2V-A14B-Diffusers
  --text-encoder-cpu-offload
  --pin-cpu-memory
  --num-gpus 4
  --ulysses-degree=2
  --enable-cfg-parallel
)

SAMPLING_ARGS=(
  --prompt "A curious raccoon"
  --save-output
  --output-path outputs
  --output-file-name "A curious raccoon.mp4"
)

sglang generate "${SERVER_ARGS[@]}" "${SAMPLING_ARGS[@]}"

```

### 4.2 Advanced Usage

#### 4.2.1 Cache-DiT Acceleration

SGLang integrates [Cache-DiT](https://github.com/vipshop/cache-dit), a caching acceleration engine for Diffusion Transformers (DiT), to achieve up to 7.4x inference speedup with minimal quality loss. You can set `SGLANG_CACHE_DIT_ENABLED=True` to enable it. For more details, please refer to the SGLang Cache-DiT [documentation](/docs/sglang-diffusion/cache_dit).

**Basic Usage**

```shell Command theme={null}
SGLANG_CACHE_DIT_ENABLED=true sglang serve --model-path Wan-AI/Wan2.2-T2V-A14B-Diffusers
```

**Advanced Usage**

* DBCache Parameters: DBCache controls block-level caching behavior:

<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
  <colgroup>
    <col style={{width: "25.0%"}} />

    <col style={{width: "25.0%"}} />

    <col style={{width: "25.0%"}} />

    <col style={{width: "25.0%"}} />
  </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)"}}>Parameter</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Env Variable</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Default</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Description</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Fn</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`SGLANG_CACHE_DIT_FN`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>1</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Number of first blocks to always compute</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Bn</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`SGLANG_CACHE_DIT_BN`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>0</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Number of last blocks to always compute</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>W</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`SGLANG_CACHE_DIT_WARMUP`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>4</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Warmup steps before caching starts</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>R</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`SGLANG_CACHE_DIT_RDT`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>0.24</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Residual difference threshold</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>MC</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`SGLANG_CACHE_DIT_MC`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>3</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Maximum continuous cached steps</td>
    </tr>
  </tbody>
</table>

* TaylorSeer Configuration: TaylorSeer improves caching accuracy using Taylor expansion:

<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
  <colgroup>
    <col style={{width: "25.0%"}} />

    <col style={{width: "25.0%"}} />

    <col style={{width: "25.0%"}} />

    <col style={{width: "25.0%"}} />
  </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)"}}>Parameter</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Env Variable</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.02)"}}>Default</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>Description</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Enable</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`SGLANG_CACHE_DIT_TAYLORSEER`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>false</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Enable TaylorSeer calibrator</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>Order</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>`SGLANG_CACHE_DIT_TS_ORDER`</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.02)"}}>1</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>Taylor expansion order (1 or 2)</td>
    </tr>
  </tbody>
</table>

Combined Configuration Example:

```shell Command theme={null}
SGLANG_CACHE_DIT_ENABLED=true \
SGLANG_CACHE_DIT_FN=2 \
SGLANG_CACHE_DIT_BN=1 \
SGLANG_CACHE_DIT_WARMUP=4 \
SGLANG_CACHE_DIT_RDT=0.4 \
SGLANG_CACHE_DIT_MC=4 \
SGLANG_CACHE_DIT_TAYLORSEER=true \
SGLANG_CACHE_DIT_TS_ORDER=2 \
sglang serve --model-path Wan-AI/Wan2.2-T2V-A14B-Diffusers
```

#### 4.2.2 GPU Optimization

* `--dit-cpu-offload`: Use CPU offload for DiT inference. Enable if run out of memory with FSDP.
* `--text-encoder-cpu-offload`: Use CPU offload for text encoder inference. Enable if run out of memory with FSDP.
* `--image-encoder-cpu-offload`: Use CPU offload for image encoder inference. Enable if run out of memory with FSDP.
* `--vae-cpu-offload`: Use CPU offload for VAE. Enable if run out of memory.
* `--pin-cpu-memory`: Pin memory for CPU offload. Only added as a temp workaround if it throws "CUDA error: invalid argument".

#### 4.2.3 Supported LoRA Registry

<table style={{width: "100%", borderCollapse: "collapse", tableLayout: "fixed"}}>
  <colgroup>
    <col style={{width: "50%"}} />

    <col style={{width: "50%"}} />
  </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)"}}>origin model</th>
      <th style={{textAlign: "left", padding: "10px 12px", fontWeight: 700, whiteSpace: "nowrap", backgroundColor: "rgba(255,255,255,0.05)"}}>supported LoRA</th>
    </tr>
  </thead>

  <tbody>
    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>[Wan-AI/Wan2.2-I2V-A14B-Diffusers](https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>[lightx2v/Wan2.2-Distill-Loras](https://huggingface.co/lightx2v/Wan2.2-Distill-Loras)</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>[Wan-AI/Wan2.2-T2V-A14B-Diffusers](https://huggingface.co/Wan-AI/Wan2.2-T2V-A14B-Diffusers)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>[Cseti/wan2.2-14B-Arcane\_Jinx-lora-v1](https://huggingface.co/Cseti/wan2.2-14B-Arcane_Jinx-lora-v1)</td>
    </tr>
  </tbody>
</table>

**Example**:

```shell Command theme={null}
sglang serve --model-path Wan-AI/Wan2.2-T2V-A14B-Diffusers --port 3000 \
    --lora-path Cseti/wan2.2-14B-Arcane_Jinx-lora-v1
```

## 5. Benchmark

Test Environment:

* Hardware: NVIDIA B200 GPU (1x)
* Model: Wan-AI/Wan2.2-T2V-A14B-Diffusers
* sglang diffusion version: 0.5.6.post2

### 5.1 Speedup Benchmark

### 5.1.1 Generate a video

<Tabs>
  <Tab title="NVIDIA B200">
    **Server Command**:

    ```shell Command theme={null}
    sglang serve --model-path Wan-AI/Wan2.2-T2V-A14B-Diffusers
    ```

    **Benchmark Command**:

    ```shell Command theme={null}
    python3 -m sglang.multimodal_gen.benchmarks.bench_serving \
        --dataset vbench --task text-to-video --num-prompts 1 --max-concurrency 1
    ```

    **Result**:

    ```text Output theme={null}
    ================= Serving Benchmark Result =================
    Model:                                   Wan-AI/Wan2.2-T2V-A14B-Diffusers
    Dataset:                                 vbench
    Task:                                    text-to-video
    --------------------------------------------------
    Benchmark duration (s):                  630.43
    Request rate:                            inf
    Max request concurrency:                 1
    Successful requests:                     1/1
    --------------------------------------------------
    Request throughput (req/s):              0.00
    Latency Mean (s):                        630.4277
    Latency Median (s):                      630.4277
    Latency P99 (s):                         630.4277
    --------------------------------------------------
    Peak Memory Max (MB):                    62627.41
    Peak Memory Mean (MB):                   62627.41
    Peak Memory Median (MB):                 62627.41

    ============================================================
    ```
  </Tab>

  <Tab title="Ascend A3 Series">
    **Server Command**:

    ```shell Command theme={null}
    #One A3 Series card has 2 npu chips. Using four A3 Series cards in benchmarking
    sglang serve \
      --model-path /models/Wan-AI/Wan2.2-T2V-A14B-Diffusers/ \
      --tp-size 2 \
      --sp-degree 4 \
      --num-gpus 8 \
      --attention-backend laser_attn
    ```

    **Benchmark Command**:

    ```shell Command theme={null}
    python -m sglang.multimodal_gen.benchmarks.bench_serving \
      --dataset vbench \
      --task text-to-video \
      --num-prompts 1 \
      --max-concurrency 1
    ```

    **Result**:

    ```text Output theme={null}
    ================= Serving Benchmark Result =================
    Task:                                         text-to-video
    Model:                                        Wan-AI/Wan2.2-T2V-A14B-Diffusers/
    Dataset:                                      vbench
    --------------------------------------------------
    Benchmark duration (s):                       214.50
    Request rate:                                 inf
    Max request concurrency:                      1
    Successful requests:                          1/1
    Completed outputs:                            1
    Outputs per prompt:                           1
    --------------------------------------------------
    Request throughput (req/s):                   0.00
    Output throughput (outputs/s):                0.00
    Latency Mean (s):                             214.50
    Latency Median (s):                           214.50
    Latency P90 (s):                              214.50
    Latency P95 (s):                              214.50
    Latency P99 (s):                              214.50
    --------------------------------------------------
    Peak Memory Max (MB):                         46692.00
    Peak Memory Mean (MB):                        46692.00
    Peak Memory Median (MB):                      46692.00
    ------------------------------------------------------------
    ```
  </Tab>
</Tabs>

#### 5.1.2 Generate videos with high concurrency

<Tabs>
  <Tab title="NVIDIA B200">
    **Server Command**:

    ```shell Command theme={null}
    SGLANG_CACHE_DIT_ENABLED=true \
    SGLANG_CACHE_DIT_FN=2 \
    SGLANG_CACHE_DIT_BN=1 \
    SGLANG_CACHE_DIT_WARMUP=4 \
    SGLANG_CACHE_DIT_RDT=0.4 \
    SGLANG_CACHE_DIT_MC=4 \
    SGLANG_CACHE_DIT_TAYLORSEER=true \
    SGLANG_CACHE_DIT_TS_ORDER=2 \
    sglang serve --model-path Wan-AI/Wan2.2-T2V-A14B-Diffusers
    ```

    **Benchmark Command**:

    ```shell Command theme={null}
    python3 -m sglang.multimodal_gen.benchmarks.bench_serving \
        --dataset vbench --task text-to-video --num-prompts 20 --max-concurrency 20
    ```

    **Result**:

    ```text Output theme={null}
    ================= Serving Benchmark Result =================
    Model:                                   Wan-AI/Wan2.2-T2V-A14B-Diffusers
    Dataset:                                 vbench
    Task:                                    text-to-video
    --------------------------------------------------
    Benchmark duration (s):                  5163.21
    Request rate:                            inf
    Max request concurrency:                 20
    Successful requests:                     20/20
    --------------------------------------------------
    Request throughput (req/s):              0.00
    Latency Mean (s):                        2739.7695
    Latency Median (s):                      2742.0673
    Latency P99 (s):                         5121.6331
    --------------------------------------------------
    Peak Memory Max (MB):                    72523.56
    Peak Memory Mean (MB):                   70253.34
    Peak Memory Median (MB):                 70824.46

    ============================================================
    ```
  </Tab>

  <Tab title="Ascend A3 Series">
    **Server Command**:

    ```shell Command theme={null}
    #One A3 Series card has 2 npu chips. Using four A3 Series cards in benchmarking
    SGLANG_CACHE_DIT_FN=2 \
    SGLANG_CACHE_DIT_BN=1 \
    SGLANG_CACHE_DIT_WARMUP=4 \
    SGLANG_CACHE_DIT_RDT=0.4 \
    SGLANG_CACHE_DIT_MC=4 \
    SGLANG_CACHE_DIT_TAYLORSEER=true \
    SGLANG_CACHE_DIT_TS_ORDER=2 \
    SGLANG_CACHE_DIT_ENABLED=true sglang serve \
      --model-path /models/Wan-AI/Wan2.2-T2V-A14B-Diffusers/ \
      --tp-size 2 \
      --sp-degree 4 \
      --num-gpus 8 \
      --attention-backend laser_attn
    ```

    **Benchmark Command**:

    ```shell Command theme={null}
    python -m sglang.multimodal_gen.benchmarks.bench_serving \
      --dataset vbench \
      --task text-to-video \
      --num-prompts 20 \
      --max-concurrency 20
    ```

    **Result**:

    ```text Output theme={null}
    ================= Serving Benchmark Result =================
    Task:                                         text-to-video
    Model:                                        Wan-AI/Wan2.2-T2V-A14B-Diffusers/
    Dataset:                                      vbench
    --------------------------------------------------
    Benchmark duration (s):                       4384.65
    Request rate:                                 inf
    Max request concurrency:                      20
    Successful requests:                          20/20
    Completed outputs:                            20
    Outputs per prompt:                           1
    --------------------------------------------------
    Request throughput (req/s):                   0.00
    Output throughput (outputs/s):                0.00
    Latency Mean (s):                             2304.17
    Latency Median (s):                           2297.69
    Latency P90 (s):                              3972.32
    Latency P95 (s):                              4178.99
    Latency P99 (s):                              4343.52
    --------------------------------------------------
    Peak Memory Max (MB):                         46692.00
    Peak Memory Mean (MB):                        46691.90
    Peak Memory Median (MB):                      46692.00
    ------------------------------------------------------------
    ```
  </Tab>
</Tabs>