> ## 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.

# Wan2.1

export const Wan21Deployment = () => {
  const MODELSIZE_DEFS = [{
    id: '14b',
    label: '14B',
    subtitle: 'High-quality, 480P/720P',
    default: true,
    validTasks: ['t2v', 'i2v']
  }, {
    id: '1_3b',
    label: '1.3B',
    subtitle: 'Lightweight, 480P',
    default: false,
    validTasks: ['t2v']
  }];
  const modelConfigs = {
    't2v-14b': {
      repoId: 'Wan-AI/Wan2.1-T2V-14B-Diffusers',
      supportedLoras: [{
        id: 'general',
        label: 'General Wan2.1 LoRA',
        path: 'NIVEDAN/wan2.1-lora'
      }]
    },
    't2v-1_3b': {
      repoId: 'Wan-AI/Wan2.1-T2V-1.3B-Diffusers',
      supportedLoras: []
    },
    'i2v-14b': {
      repoId: 'Wan-AI/Wan2.1-I2V-14B-720P-Diffusers',
      supportedLoras: [{
        id: 'fight',
        label: 'Fight Style LoRA',
        path: 'valiantcat/Wan2.1-Fight-LoRA'
      }]
    }
  };
  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: 'h100',
        label: 'H100',
        default: false
      }, {
        id: 'mi300x',
        label: 'MI300X',
        default: false
      }, {
        id: 'mi325x',
        label: 'MI325X',
        default: false
      }, {
        id: 'mi355x',
        label: 'MI355X',
        default: false
      }, {
        id: 'a2',
        label: 'A2',
        default: false
      }, {
        id: 'a3',
        label: 'A3',
        default: false
      }]
    },
    task: {
      name: 'task',
      title: 'Task Type',
      items: [{
        id: 't2v',
        label: 'Text-to-Video (T2V)',
        default: true
      }, {
        id: 'i2v',
        label: 'Image-to-Video (I2V)',
        default: false
      }]
    },
    modelsize: {
      name: 'modelsize',
      title: 'Model Variant',
      items: MODELSIZE_DEFS.map(({validTasks, ...rest}) => rest)
    },
    bestPractice: {
      name: 'bestPractice',
      title: 'Optimization',
      items: [{
        id: 'off',
        label: 'Standard',
        default: true
      }, {
        id: 'on',
        label: 'Best Practice',
        default: false
      }]
    }
  };
  function modelSizeItemsForTask(task) {
    return MODELSIZE_DEFS.filter(item => item.validTasks.includes(task)).map(({validTasks, ...rest}) => rest);
  }
  const getInitialState = () => {
    const task = 't2v';
    const sizes = modelSizeItemsForTask(task);
    const modelsize = sizes.find(size => size.default)?.id || sizes[0].id;
    const configKey = `${task}-${modelsize}`;
    const supported = modelConfigs[configKey]?.supportedLoras || [];
    return {
      hardware: 'b200',
      task,
      modelsize,
      bestPractice: 'off',
      selectedLoraPath: supported[0]?.path ?? ''
    };
  };
  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();
  }, []);
  useEffect(() => {
    const isAscend = values.hardware === 'a2' || values.hardware === 'a3';
    const targetTabName = isAscend ? 'Ascend A3' : '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 => {
      let next = {
        ...prev,
        [optionName]: itemId
      };
      if (optionName === 'task') {
        const sizes = modelSizeItemsForTask(itemId);
        if (!sizes.some(size => size.id === next.modelsize)) {
          next.modelsize = sizes.find(size => size.default)?.id || sizes[0].id;
        }
      }
      if (optionName === 'task' || optionName === 'modelsize') {
        const configKey = `${next.task}-${next.modelsize}`;
        const supported = modelConfigs[configKey]?.supportedLoras || [];
        if (supported.length === 0) {
          next.selectedLoraPath = '';
        } else if (next.selectedLoraPath && !supported.some(lora => lora.path === next.selectedLoraPath)) {
          next.selectedLoraPath = supported[0].path;
        }
      }
      return next;
    });
  };
  const handleLoraToggle = path => {
    setValues(prev => ({
      ...prev,
      selectedLoraPath: prev.selectedLoraPath === path ? '' : path
    }));
  };
  const handleTextChange = (optionName, value) => {
    setValues(prev => ({
      ...prev,
      [optionName]: value
    }));
  };
  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 card has 2 npu chips\n' : '';
      const isBestPractice = bestPractice === 'on';
      let command;
      if (task === 't2v' && modelsize === '1_3b' && hardware === 'a2' && !isBestPractice) {
        command = `${comment}sglang serve \\
  --model-path ${config.repoId} \\
  --num-gpus 1`;
      } else {
        const tpSize = modelsize === '1_3b' ? isBestPractice ? 4 : 1 : 2;
        const spDegree = modelsize === '14b' && isBestPractice ? 4 : 1;
        const numGpus = isBestPractice ? 8 : hardware === 'a3' ? 2 : 4;
        command = `${comment}sglang serve \\
  --model-path ${config.repoId} \\
  --tp-size ${tpSize} \\
  --sp-degree ${spDegree} \\
  --num-gpus ${numGpus}`;
      }
      if (isBestPractice) {
        command += ` \\\n  --attention-backend laser_attn`;
      }
      if (selectedLoraPath === 'NIVEDAN/wan2.1-lora' || selectedLoraPath === 'valiantcat/Wan2.1-Fight-LoRA') {
        command += ` \\\n  --lora-path ${selectedLoraPath}`;
      }
      return command;
    }
    let command = `sglang serve \\\n  --model-path ${config.repoId} \\\n  --dit-layerwise-offload true`;
    if (bestPractice === 'on') {
      command += ` \\\n  --num-gpus 4 \\\n  --ulysses-degree 2 \\\n  --enable-cfg-parallel`;
    }
    if (selectedLoraPath) {
      command += ` \\\n  --lora-path ${selectedLoraPath}`;
    }
    return command;
  };
  const modelSizeItems = modelSizeItemsForTask(values.task);
  const loraConfigKey = `${values.task}-${values.modelsize}`;
  const availableLoras = modelConfigs[loraConfigKey]?.supportedLoras || [];
  const command = generateCommand();
  const containerStyle = {
    maxWidth: '900px',
    margin: '0 auto',
    display: 'flex',
    flexDirection: 'column',
    gap: '4px'
  };
  const cardStyle = {
    padding: '8px 12px',
    border: `1px solid ${isDark ? '#374151' : '#e5e7eb'}`,
    borderLeft: `3px solid ${isDark ? '#E85D4D' : '#D45D44'}`,
    borderRadius: '4px',
    display: 'flex',
    alignItems: 'center',
    gap: '12px',
    background: isDark ? '#1f2937' : '#fff'
  };
  const titleStyle = {
    fontSize: '13px',
    fontWeight: '600',
    minWidth: '140px',
    flexShrink: 0,
    color: isDark ? '#e5e7eb' : 'inherit'
  };
  const itemsStyle = {
    display: 'flex',
    rowGap: '2px',
    columnGap: '6px',
    flexWrap: 'wrap',
    alignItems: 'center',
    flex: 1
  };
  const labelBaseStyle = {
    padding: '4px 10px',
    border: `1px solid ${isDark ? '#9ca3af' : '#d1d5db'}`,
    borderRadius: '3px',
    cursor: 'pointer',
    display: 'inline-flex',
    flexDirection: 'column',
    alignItems: 'center',
    justifyContent: 'center',
    fontWeight: '500',
    fontSize: '13px',
    transition: 'all 0.2s',
    userSelect: 'none',
    minWidth: '45px',
    textAlign: 'center',
    flex: 1,
    background: isDark ? '#374151' : '#fff',
    color: isDark ? '#e5e7eb' : 'inherit'
  };
  const checkedStyle = {
    background: '#D45D44',
    color: 'white',
    borderColor: '#D45D44'
  };
  const disabledStyle = {
    cursor: 'not-allowed',
    opacity: 0.5
  };
  const subtitleStyle = {
    display: 'block',
    fontSize: '9px',
    marginTop: '1px',
    lineHeight: '1.1',
    opacity: 0.7
  };
  const textInputStyle = {
    flex: 1,
    padding: '8px 10px',
    borderRadius: '4px',
    border: `1px solid ${isDark ? '#4b5563' : '#d1d5db'}`,
    background: isDark ? '#111827' : '#fff',
    color: isDark ? '#e5e7eb' : '#111827',
    fontSize: '13px'
  };
  const commandDisplayStyle = {
    flex: 1,
    padding: '12px 16px',
    background: isDark ? '#111827' : '#f5f5f5',
    borderRadius: '6px',
    fontFamily: "'Menlo', 'Monaco', 'Courier New', monospace",
    fontSize: '12px',
    lineHeight: '1.5',
    color: isDark ? '#e5e7eb' : '#374151',
    whiteSpace: 'pre-wrap',
    overflowX: 'auto',
    margin: 0,
    border: `1px solid ${isDark ? '#374151' : '#e5e7eb'}`
  };
  return <div style={containerStyle} className="not-prose">
      {Object.entries(options).map(([key, option]) => <div key={key} style={cardStyle}>
          <div style={titleStyle}>{option.title}</div>
          <div style={itemsStyle}>
            {(key === 'modelsize' ? modelSizeItems : 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>)}

      {availableLoras.length > 0 && <div style={cardStyle}>
          <div style={titleStyle}>Select LoRA Model (Only some of the supported LoRAs are listed here)</div>
          <div style={itemsStyle}>
            {availableLoras.map(lora => {
    const isChecked = values.selectedLoraPath === lora.path;
    return <label key={lora.id} style={{
      ...labelBaseStyle,
      ...isChecked ? checkedStyle : {}
    }} onClick={event => {
      event.preventDefault();
      handleLoraToggle(lora.path);
    }}>
                  <input type="radio" name="selectedLoraPath" value={lora.path} checked={isChecked} readOnly style={{
      display: 'none'
    }} />
                  {lora.label}
                  <small style={{
      ...subtitleStyle,
      color: isChecked ? '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}>{command}</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", "text-to-video", "image-to-video", "LoRA", "text rendering"]} />

## 1. Model Introduction

[Wan2.1 series](https://github.com/Wan-Video/Wan2.1) is an open and advanced suite of large-scale video generative models from Wan-AI.

Key characteristics:

* **State-of-the-art video quality**: Consistently outperforms many open-source and commercial video models on internal and public benchmarks, especially for motion richness and temporal consistency.
* **Consumer GPU friendly**: The T2V-1.3B variant can generate 5-second 480P videos on consumer GPUs with modest VRAM requirements.
* **Multi-capability suite**: Supports Text-to-Video (T2V), Image-to-Video (I2V), video editing, text-to-image, and video-to-audio generation.
* **Robust text rendering**: First-generation Wan model capable of generating both Chinese and English text in videos with strong readability.
* **Powerful Wan-VAE**: A 3D causal VAE that encodes/decodes long 1080P videos while preserving temporal information, enabling efficient high-resolution video generation.

For more details, refer to the official Wan2.1 resources:

* **GitHub**: [Wan-Video/Wan2.1](https://github.com/Wan-Video/Wan2.1)
* **Hugging Face collection**: [Wan-AI Wan2.1](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B)

## 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](../../../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 Wan2.1 series offers models in multiple sizes and resolutions. SGLang supports Wan2.1 deployment on NVIDIA B200, B300, H200, H100, and AMD MI300X, MI325X, MI355X GPUs and Ascend A2, A3 NPUs. The recommended launch configurations vary by hardware, model size, and memory headroom.

**Interactive Command Generator**: Use the configuration selector below to automatically generate an appropriate deployment command for your model variant and options.

<Wan21Deployment />

### 3.2 Configuration Tips

Current supported optimization options are listed in the [SGLang diffusion support matrix](../../../docs/sglang-diffusion/attention_backends#platform-support-matrix).

* `--vae-path`: Path to a custom VAE model or HuggingFace model ID. 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 (for the encoder/DiT; keep (\leq 1) if relying heavily on CPU offload).
* `--sp-degree {SP_SIZE}`: Sequence parallelism degree.
* `--ulysses-degree {ULYSSES_DEGREE}`: Degree of DeepSpeed-Ulysses-style SP in USP.
* `--ring-degree {RING_DEGREE}`: Degree of ring attention-style SP in USP.
* `--text-encoder-cpu-offload`, `--dit-cpu-offload`, `--vae-cpu-offload`: Use CPU offload to reduce peak GPU memory when needed.

## 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

```bash Command theme={null}
sglang serve --model-path Wan-AI/Wan2.1-T2V-14B-Diffusers --port 30000

curl http://127.0.0.1:30000/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/Wan2.1-T2V-14B-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

```bash Command theme={null}
SERVER_ARGS=(
  --model-path Wan-AI/Wan2.1-T2V-14B-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 significant inference speedups 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**

```bash Command theme={null}
SGLANG_CACHE_DIT_ENABLED=true sglang serve --model-path Wan-AI/Wan2.1-T2V-14B-Diffusers
```

**Advanced Usage**

Combined Configuration Example:

```bash 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/Wan2.1-T2V-14B-Diffusers
```

#### 4.2.2 GPU Optimization

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

#### 4.2.3 Supported LoRA Registry

SGLang supports applying Wan2.1 LoRA adapters on top of base models:

<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/Wan2.1-T2V-14B](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>[NIVEDAN/wan2.1-lora](https://huggingface.co/NIVEDAN/wan2.1-lora)</td>
    </tr>

    <tr>
      <td style={{padding: "9px 12px", fontWeight: 500, backgroundColor: "rgba(255,255,255,0.02)"}}>[Wan-AI/Wan2.1-I2V-14B-720P](https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P)</td>
      <td style={{padding: "9px 12px", backgroundColor: "rgba(255,255,255,0.05)"}}>[valiantcat/Wan2.1-Fight-LoRA](https://huggingface.co/valiantcat/Wan2.1-Fight-LoRA)</td>
    </tr>
  </tbody>
</table>

**Example**:

```bash Command theme={null}
sglang serve --model-path Wan-AI/Wan2.1-T2V-14B-Diffusers --port 30000 \
    --lora-path NIVEDAN/wan2.1-lora
```

## 5. Reference Benchmark

The following benchmark is a point-in-time reference for one model, hardware platform, SGLang image, and parameter set. It is not a complete hardware support matrix.

Test Environment:

* Hardware: AMD MI300X GPU (1x)
* Model: Wan-AI/Wan2.1-T2V-14B-Diffusers
* SGLang Docker Image Version: 0.5.9

### 5.1 How to Run Benchmarks with SGLang

You can use the built-in SGLang diffusion benchmark script to evaluate Wan2.1 performance on your hardware.

#### 5.1.1 Generate a single video

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

    ```bash Command theme={null}
    sglang serve --model-path Wan-AI/Wan2.1-T2V-14B-Diffusers
    ```

    **Benchmark Command**:

    ```bash 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 =================
    Task:                                    text-to-video
    Model:                                   Wan-AI/Wan2.1-T2V-14B-Diffusers
    Dataset:                                 vbench
    --------------------------------------------------
    Benchmark duration (s):                  1958.41
    Request rate:                            inf
    Max request concurrency:                 1
    Successful requests:                     1/1
    --------------------------------------------------
    Request throughput (req/s):              0.00
    Latency Mean (s):                        1958.4059
    Latency Median (s):                      1958.4059
    Latency P99 (s):                         1958.4059
    --------------------------------------------------
    Peak Memory Max (MB):                    59662.00
    Peak Memory Mean (MB):                   59662.00
    Peak Memory Median (MB):                 59662.00
    ============================================================
    ```
  </Tab>

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

    ```bash Command theme={null}
    #One A3 card has 2 npu chips. Benchmark was did with two A3 cards
    sglang serve \
      --model-path /models/Wan-AI/Wan2.1-T2V-14B-Diffusers/ \
      --tp-size 2 \
      --sp-degree 2 \
      --num-gpus 4 \
      --attention-backend laser_attn
    ```

    **Benchmark Command**:

    ```bash 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/Wan2.1-T2V-14B-Diffusers/
    Dataset:                                      vbench
    --------------------------------------------------
    Benchmark duration (s):                       1282.90
    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):                             1282.90
    Latency Median (s):                           1282.90
    Latency P90 (s):                              1282.90
    Latency P95 (s):                              1282.90
    Latency P99 (s):                              1282.90
    --------------------------------------------------
    Peak Memory Max (MB):                         31938.00
    Peak Memory Mean (MB):                        31938.00
    Peak Memory Median (MB):                      31938.00
    ============================================================
    ```
  </Tab>
</Tabs>

#### 5.1.2 Generate videos with Cache-DiT acceleration

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

    ```bash 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/Wan2.1-T2V-14B-Diffusers
    ```

    **Benchmark Command**:

    ```bash 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 =================
    Task:                                    text-to-video
    Model:                                   Wan-AI/Wan2.1-T2V-14B-Diffusers
    Dataset:                                 vbench
    --------------------------------------------------
    Benchmark duration (s):                  556.99
    Request rate:                            inf
    Max request concurrency:                 1
    Successful requests:                     1/1
    --------------------------------------------------
    Request throughput (req/s):              0.00
    Latency Mean (s):                        556.9885
    Latency Median (s):                      556.9885
    Latency P99 (s):                         556.9885
    --------------------------------------------------
    Peak Memory Max (MB):                    69306.00
    Peak Memory Mean (MB):                   69306.00
    Peak Memory Median (MB):                 69306.00
    ============================================================
    ```
  </Tab>

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

    ```bash Command theme={null}
    #One A3 card has 2 npu chips. Benchmark was did with two Atlas 3 cards
    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/Wan2.1-T2V-14B-Diffusers/ \
      --tp-size 2 \
      --sp-degree 2 \
      --num-gpus 4 \
      --attention-backend laser_attn
    ```

    **Benchmark Command**:

    ```bash 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/Wan2.1-T2V-14B-Diffusers/
    Dataset:                                      vbench
    --------------------------------------------------
    Benchmark duration (s):                       413.88
    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):                             413.88
    Latency Median (s):                           413.88
    Latency P90 (s):                              413.88
    Latency P95 (s):                              413.88
    Latency P99 (s):                              413.88
    --------------------------------------------------
    Peak Memory Max (MB):                         32782.00
    Peak Memory Mean (MB):                        32782.00
    Peak Memory Median (MB):                      32782.00
    ============================================================
    ```
  </Tab>
</Tabs>