> ## 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. # DeepSeek-OCR export const DeepSeekOCRDeployment = () => { 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: 'fp16', label: 'FP16', default: true }] }, 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 }] } }; 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} = values; const strategyArray = Array.isArray(strategy) ? strategy : []; if (hardware === 'mi300x' && quantization !== 'fp16') { return '# Error: MI300X + DeepSeek-OCR only supports FP16 quantization\n# Please select FP16 quantization'; } let modelPath = 'deepseek-ai/DeepSeek-OCR'; let cmd = 'python3 -m sglang.launch_server \\\n'; cmd += ` --model-path ${modelPath}`; cmd += ` \\\n --dtype float16`; if (strategyArray.includes('tp')) { cmd += ` \\\n --tp 1`; } if (strategyArray.includes('dp')) { cmd += ` \\\n --dp 1 \\\n --enable-dp-attention`; } if (strategyArray.includes('ep')) { cmd += ` \\\n --ep 1`; } cmd += ` \\\n --enable-symm-mem # Optional: improves performance, but may be unstable`; 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
{Object.entries(options).map(([key, option]) =>
{option.title}
{option.type === 'checkbox' ? option.items.map(item => { const isChecked = (values[option.name] || []).includes(item.id); const isDisabled = item.required; return ; }) : option.items.map(item => { const isChecked = values[option.name] === item.id; return ; })}
)}
Run this Command:
{generateCommand()}
; }; ## 1. Model Introduction [DeepSeek-OCR](https://github.com/deepseek-ai/DeepSeek-OCR) is DeepSeek's advanced OCR (Optical Character Recognition) model designed for high-accuracy text extraction from images. The model is optimized for various document processing and image-to-text conversion tasks. **Key Features:** * **Advanced OCR**: High-accuracy text recognition from images and documents * **Multi-Modality**: Supports various image formats and document types **Available Models:** * **Base Model**: [deepseek-ai/DeepSeek-OCR](https://huggingface.co/deepseek-ai/DeepSeek-OCR) - Recommended for OCR tasks **License:** To use DeepSeek-OCR, you must agree to DeepSeek's Community License. See [LICENSE](https://huggingface.co/deepseek-ai/DeepSeek-OCR/blob/main/LICENSE) for details. For more details, please refer to the [official DeepSeek-OCR repository](https://github.com/deepseek-ai/DeepSeek-OCR). ## 2. SGLang Installation 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, and deployment strategy. ### 3.2 Configuration Tips For more detailed configuration tips, please refer to [DeepSeek V3/V3.1/R1 Usage](../../../docs/basic_usage/deepseek_v3). ## 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) ## 5. Benchmark ### 5.1 Speed Benchmark **Test Environment:** * Hardware: AMD MI300X GPU (1x) * Model: DeepSeek-OCR * Tensor Parallelism: 1 * sglang version: 0.5.7 We use SGLang's built-in benchmarking tool to conduct performance evaluation on the [ShareGPT\_Vicuna\_unfiltered](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) dataset. This dataset contains real conversation data and can better reflect performance in actual use scenarios. To simulate real-world usage patterns, we configure each request with 1024 input tokens and 1024 output tokens, representing typical medium-length conversations with detailed responses. #### 5.1.1 Latency-Sensitive Benchmark * Model Deployment Command: ```shell Command theme={null} python3 -m sglang.launch_server \ --model-path deepseek-ai/DeepSeek-OCR \ --tp 1 \ --dtype float16 \ --host 0.0.0.0 \ --port 8000 ``` * Benchmark Command: ```shell Command theme={null} python3 -m sglang.bench_serving \ --backend sglang \ --host 127.0.0.1 \ --port 8000 \ --model deepseek-ai/DeepSeek-OCR \ --random-input-len 1024 \ --random-output-len 1024 \ --num-prompts 10 \ --max-concurrency 1 ``` * **Test Results:** ```text Output theme={null} ============ Serving Benchmark Result ============ Backend: sglang Traffic request rate: inf Max request concurrency: 1 Successful requests: 10 Benchmark duration (s): 4.45 Total input tokens: 1972 Total input text tokens: 1972 Total input vision tokens: 0 Total generated tokens: 2784 Total generated tokens (retokenized): 2770 Request throughput (req/s): 2.25 Input token throughput (tok/s): 442.89 Output token throughput (tok/s): 625.26 Peak output token throughput (tok/s): 635.00 Peak concurrent requests: 4 Total token throughput (tok/s): 1068.16 Concurrency: 1.00 ----------------End-to-End Latency---------------- Mean E2E Latency (ms): 443.32 Median E2E Latency (ms): 493.29 ---------------Time to First Token---------------- Mean TTFT (ms): 21.59 Median TTFT (ms): 20.89 P99 TTFT (ms): 24.81 -----Time per Output Token (excl. 1st token)------ Mean TPOT (ms): 1.47 Median TPOT (ms): 1.52 P99 TPOT (ms): 1.53 ---------------Inter-Token Latency---------------- Mean ITL (ms): 1.52 Median ITL (ms): 1.51 P95 ITL (ms): 1.76 P99 ITL (ms): 1.93 Max ITL (ms): 8.28 ================================================== ``` #### 5.1.2 Throughput-Sensitive Benchmark * Model Deployment Command: ```shell Command theme={null} python3 -m sglang.launch_server \ --model-path deepseek-ai/DeepSeek-OCR \ --tp 1 \ --ep 1 \ --dp 1 \ --enable-dp-attention \ --dtype float16 \ --host 0.0.0.0 \ --port 8000 ``` * Benchmark Command: ```shell Command theme={null} python3 -m sglang.bench_serving \ --backend sglang \ --host 127.0.0.1 \ --port 8000 \ --model deepseek-ai/DeepSeek-OCR \ --random-input-len 1024 \ --random-output-len 1024 \ --num-prompts 1000 \ --max-concurrency 100 ``` * **Test Results:** ```text Output theme={null} ============ Serving Benchmark Result ============ Backend: sglang Traffic request rate: inf Max request concurrency: 100 Successful requests: 1000 Benchmark duration (s): 16.24 Total input tokens: 301698 Total input text tokens: 301698 Total input vision tokens: 0 Total generated tokens: 188375 Total generated tokens (retokenized): 186927 Request throughput (req/s): 61.59 Input token throughput (tok/s): 18582.90 Output token throughput (tok/s): 11602.84 Peak output token throughput (tok/s): 15479.00 Peak concurrent requests: 179 Total token throughput (tok/s): 30185.75 Concurrency: 85.53 ----------------End-to-End Latency---------------- Mean E2E Latency (ms): 1388.60 Median E2E Latency (ms): 901.43 ---------------Time to First Token---------------- Mean TTFT (ms): 73.36 Median TTFT (ms): 50.21 P99 TTFT (ms): 349.53 -----Time per Output Token (excl. 1st token)------ Mean TPOT (ms): 7.42 Median TPOT (ms): 7.31 P99 TPOT (ms): 27.99 ---------------Inter-Token Latency---------------- Mean ITL (ms): 7.04 Median ITL (ms): 4.62 P95 ITL (ms): 21.11 P99 ITL (ms): 36.92 Max ITL (ms): 172.15 ================================================== ```