From b0018ad0158cfd9f82fd827b0335cd0b94cd81ba Mon Sep 17 00:00:00 2001 From: zijiexia <37504505+zijiexia@users.noreply.github.com> Date: Tue, 12 May 2026 22:26:18 -0700 Subject: [PATCH] [Doc]: refactor Intern-S2-Preview cookbook with interactive command generator (#25134) Co-authored-by: Claude Opus 4.7 (1M context) --- .../InternLM/Intern-S2-Preview.mdx | 90 ++++----- docs_new/cookbook/autoregressive/intro.mdx | 1 - docs_new/docs.json | 4 +- .../intern-s2-preview-deployment.jsx | 179 ++++++++++++++++++ 4 files changed, 222 insertions(+), 52 deletions(-) create mode 100644 docs_new/src/snippets/autoregressive/intern-s2-preview-deployment.jsx diff --git a/docs_new/cookbook/autoregressive/InternLM/Intern-S2-Preview.mdx b/docs_new/cookbook/autoregressive/InternLM/Intern-S2-Preview.mdx index 86f3a31bd..bcac878ac 100644 --- a/docs_new/cookbook/autoregressive/InternLM/Intern-S2-Preview.mdx +++ b/docs_new/cookbook/autoregressive/InternLM/Intern-S2-Preview.mdx @@ -2,13 +2,20 @@ title: Intern-S2-Preview metatags: description: "Deploy Intern-S2-Preview with SGLang" +tag: NEW --- -## 1. Model introduction +## 1. Model Introduction -[Intern-S2-Preview](https://huggingface.co/internLM/Intern-S2-Preview) is an efficient 35B scientific multimodal foundation model. Beyond conventional parameter and data scaling, Intern-S2-Preview explores task scaling: increasing the difficulty, diversity, and coverage of scientific tasks to further unlock model capabilities. +**Intern-S2-Preview** is an efficient 35B scientific multimodal foundation model. Beyond conventional parameter and data scaling, Intern-S2-Preview explores task scaling: increasing the difficulty, diversity, and coverage of scientific tasks to further unlock model capabilities. -## 2. SGLang installation +**Resources:** + +- HuggingFace: [internLM/Intern-S2-Preview](https://huggingface.co/internLM/Intern-S2-Preview) + +## 2. SGLang Installation + +SGLang offers multiple installation methods. Please refer to the [official SGLang installation guide](../../../docs/get-started/install) for installation instructions. Install SGLang from source or use an NVIDIA Docker image: @@ -19,63 +26,48 @@ uv pip install 'git+https://github.com/sgl-project/sglang.git#subdirectory=pytho # Or use Docker for NVIDIA GPUs docker pull lmsysorg/sglang:latest ``` +For how to actually launch a docker image, see [Install → Method 3: Using Docker](../../../docs/get-started/install#method-3-using-docker). A minimal example (substitute the inner `sglang serve ...` with whatever the [command generator](#3-model-deployment) below produces): -For full installation details, see the [SGLang installation guide](/docs/get-started/install). - -## 3. Model deployment - - -**NVIDIA:** - -Deploy internLM/Intern-S2-Preview with the following commands: - -### Standard Version - -```shell Command -sglang serve \ - --model-path internLM/Intern-S2-Preview \ - --tp 8 \ - --reasoning-parser qwen3 \ - --tool-call-parser qwen3_coder \ - --mem-fraction-static 0.8 \ - --host 0.0.0.0 \ - --port 30000 +```bash Command +docker run --gpus all \ + --shm-size 32g \ + -p 30000:30000 \ + -v ~/.cache/huggingface:/root/.cache/huggingface \ + --env "HF_TOKEN=" \ + --ipc=host \ + lmsysorg/sglang:latest \ + sglang serve ``` -### Multi-Token Prediction (MTP) +## 3. Model Deployment -```shell Command -SGLANG_ENABLE_SPEC_V2=1 \ -sglang serve \ - --model-path internLM/Intern-S2-Preview \ - --tp 8 \ - --reasoning-parser qwen3 \ - --tool-call-parser qwen3_coder \ - --mamba-scheduler-strategy extra_buffer \ - --speculative-algo 'NEXTN' \ - --speculative-eagle-topk 1 \ - --speculative-num-steps 3 \ - --speculative-num-draft-tokens 4 \ - --mem-fraction-static 0.8 \ - --host 0.0.0.0 \ - --port 30000 -``` +### 3.1 Basic Configuration -### Configuration tips +**Interactive Command Generator**: Use the selector below to generate the deployment command for your hardware and parser configuration. + +import { InternS2PreviewDeployment } from "/src/snippets/autoregressive/intern-s2-preview-deployment.jsx"; + + + +### 3.2 Configuration Tips - Use `tp>=2` for the NVIDIA deployment commands. - Use `--reasoning-parser qwen3` to separate reasoning content from final content in streaming responses. - Use `--tool-call-parser qwen3_coder` when serving tool-calling workloads. -- Add `--mamba-scheduler-strategy extra_buffer with `--speculative-algo 'NEXTN'` to enable MTP. -- If weight loading is slow, add `--model-loader-extra-config='{"enable_multithread_load": "true","num_threads": 64}'`. +- Add `--mamba-scheduler-strategy extra_buffer` with `--speculative-algo 'NEXTN'` to enable MTP. +- If weight loading is slow, add `--model-loader-extra-config='{"enable_multithread_load": "true", "num_threads": 64}'`. -## 4. Model invocation +## 4. Model Invocation -### 4.1 Basic usage +### 4.1 Basic Usage -For basic API usage and request examples, see the [SGLang basic usage guide](/docs/basic_usage/send_request). +For basic API usage and request examples, see: -### 4.2 Vision input +- [Basic API Usage](../../../docs/basic_usage/send_request) + +### 4.2 Advanced Usage + +#### 4.2.1 Vision Input Intern-S2-Preview supports image inputs. Here is an example with an image: @@ -134,7 +126,7 @@ for chunk in response: print() ``` -### 4.3 Reasoning parser +#### 4.2.2 Reasoning Parser Enable streaming to read reasoning content separately from the final answer: @@ -179,7 +171,7 @@ for chunk in response: print() ``` -### 4.4 Tool calling +#### 4.2.3 Tool Calling Serve with `--tool-call-parser qwen3_coder` enabled, then send OpenAI-compatible tool requests: diff --git a/docs_new/cookbook/autoregressive/intro.mdx b/docs_new/cookbook/autoregressive/intro.mdx index 8af197470..6941c8c56 100644 --- a/docs_new/cookbook/autoregressive/intro.mdx +++ b/docs_new/cookbook/autoregressive/intro.mdx @@ -82,7 +82,6 @@ metatags: diff --git a/docs_new/docs.json b/docs_new/docs.json index 7e36ff1f9..ce1d86d41 100644 --- a/docs_new/docs.json +++ b/docs_new/docs.json @@ -1042,8 +1042,8 @@ { "group": "InternLM", "pages": [ - "cookbook/autoregressive/InternLM/Intern-S1", - "cookbook/autoregressive/InternLM/Intern-S2-Preview" + "cookbook/autoregressive/InternLM/Intern-S2-Preview", + "cookbook/autoregressive/InternLM/Intern-S1" ] }, { diff --git a/docs_new/src/snippets/autoregressive/intern-s2-preview-deployment.jsx b/docs_new/src/snippets/autoregressive/intern-s2-preview-deployment.jsx new file mode 100644 index 000000000..9045d40d7 --- /dev/null +++ b/docs_new/src/snippets/autoregressive/intern-s2-preview-deployment.jsx @@ -0,0 +1,179 @@ +export const InternS2PreviewDeployment = () => { + const options = { + hardware: { + name: 'hardware', + title: 'Hardware Platform', + items: [ + { id: 'h200', label: 'H200', default: true }, + ], + }, + reasoning: { + name: 'reasoning', + title: 'Reasoning Parser', + items: [ + { id: 'disabled', label: 'Disabled', default: false }, + { id: 'enabled', label: 'Enabled', default: true }, + ], + }, + toolcall: { + name: 'toolcall', + title: 'Tool Call Parser', + items: [ + { id: 'disabled', label: 'Disabled', default: false }, + { id: 'enabled', label: 'Enabled', default: true }, + ], + }, + mtp: { + name: 'mtp', + title: 'Multi-Token Prediction', + items: [ + { id: 'disabled', label: 'Disabled', default: true }, + { id: 'enabled', label: 'Enabled', default: false }, + ], + }, + }; + + 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 { reasoning, toolcall, mtp } = values; + const tpValue = 8; + + const flags = []; + flags.push(' --model-path internLM/Intern-S2-Preview'); + flags.push(` --tp ${tpValue}`); + if (reasoning === 'enabled') flags.push(' --reasoning-parser qwen3'); + if (toolcall === 'enabled') flags.push(' --tool-call-parser qwen3_coder'); + if (mtp === 'enabled') { + flags.push(' --mamba-scheduler-strategy extra_buffer'); + flags.push(" --speculative-algo 'NEXTN'"); + flags.push(' --speculative-eagle-topk 1'); + flags.push(' --speculative-num-steps 3'); + flags.push(' --speculative-num-draft-tokens 4'); + } + flags.push(' --mem-fraction-static 0.8'); + flags.push(' --host 0.0.0.0'); + flags.push(' --port 30000'); + + const envPrefix = mtp === 'enabled' ? 'SGLANG_ENABLE_SPEC_V2=1 \\\n' : ''; + return `${envPrefix}sglang serve \\\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 ( +
+ {Object.entries(options).map(([key, option]) => ( +
+
{option.title}
+
+ {option.items.map((item) => { + const isChecked = values[option.name] === item.id; + return ( + + ); + })} +
+
+ ))} +
+
Run this Command:
+ 
{generateCommand()}
+
+
+ ); +};