Skip to content

Commit 4c26c72

Browse files
author
dianjixz
committed
[init] StackFlow
1 parent 96d5711 commit 4c26c72

30 files changed

Lines changed: 6328 additions & 0 deletions

‎README.md‎

Lines changed: 91 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,91 @@
1+
# Module-LLM
2+
3+
<div class="product_pic"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/4.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/10.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/15.webp"></div>
4+
5+
## Description
6+
7+
**Module LLM** is an integrated offline Large Language Model (LLM) inference module designed for terminal devices that require efficient and intelligent interaction. Whether for smart homes, voice assistants, or industrial control, Module LLM provides a smooth and natural AI experience without relying on the cloud, ensuring privacy and stability. Integrated with the **StackFlow** framework and **Arduino/UiFlow** libraries, smart features can be easily implemented with just a few lines of code.<br>
8+
Powered by the advanced **AX630C** SoC processor, it integrates a 3.2 TOPs high-efficiency NPU with native support for Transformer models, handling complex AI tasks with ease. Equipped with **4GB LPDDR4** memory (1GB available for user applications, 3GB dedicated to hardware acceleration) and **32GB eMMC** storage, it supports parallel loading and sequential inference of multiple models, ensuring smooth multitasking. The main chip's runtime power consumption of approximately 1.5W, making it highly efficient and suitable for long-term operation.<br>
9+
It features a built-in microphone, speaker, TF storage card, **USB OTG**, and RGB status light, meeting diverse application needs with support for voice interaction and data transfer. The module offers flexible expansion: the onboard SD card slot supports cold/hot firmware upgrades, and the **UART** communication interface simplifies connection and debugging, ensuring continuous optimization and expansion of module functionality. The USB port supports master-slave auto-switching, serving as both a debugging port and allowing connection to additional USB devices like cameras. Users can purchase the LLM debugging kit to add a 100 Mbps Ethernet port and kernel serial port, using it as an SBC.<br>
10+
The module is compatible with multiple models and comes pre-installed with the **Qwen2.5-0.5B** language model. It features **KWS** (wake word), **ASR** (speech recognition), **LLM** (large language model), and **TTS** (text-to-speech) functionalities, with support for standalone calls or **pipeline** automatic transfer for convenient development. Future support includes Qwen2.5-1.5B, Llama3.2-1B, and InternVL2-1B models, allowing hot model updates to keep up with community trends and accommodate various complex AI tasks. Vision recognition capabilities include support for CLIP, YoloWorld, and future updates for DepthAnything, SegmentAnything, and other advanced models to enhance intelligent recognition and analysis.<br>
11+
Plug and play with **M5 hosts**, Module LLM offers an easy-to-use AI interaction experience. Users can quickly integrate it into existing smart devices without complex settings, enabling smart functionality and improving device intelligence. This product is suitable for offline voice assistants, text-to-speech conversion, smart home control, interactive robots, and more.
12+
13+
14+
15+
## Product Features
16+
17+
- Offline inference, 3.2T@INT8 precision computing power
18+
- Integrated KWS (wake word), ASR (speech recognition), LLM (large language model), TTS (text-to-speech generation)
19+
- Multi-model parallel processing
20+
- Onboard 32GB eMMC storage and 4GB LPDDR4 memory
21+
- Onboard microphone and speaker
22+
- Serial communication
23+
- SD card firmware upgrade
24+
- Supports ADB debugging
25+
- RGB indicator light
26+
- Built-in Ubuntu system
27+
- Supports OTG functionality
28+
- Compatible with Arduino/UIFlow
29+
30+
>
31+
32+
## Applications
33+
34+
- Offline voice assistants
35+
- Text-to-speech conversion
36+
- Smart home control
37+
- Interactive robots
38+
39+
## Specifications
40+
41+
| Specification | Parameter |
42+
| ---------------- | ------------------------------------------------------------------------------------------- |
43+
| Processor SoC | AX630C@Dual Cortex A53 1.2 GHz <br> MAX.12.8 TOPS @INT4 and 3.2 TOPS @INT8 |
44+
| Memory | 4GB LPDDR4 (1GB system memory + 3GB dedicated for hardware acceleration) |
45+
| Storage | 32GB eMMC5.1 |
46+
| Communication | Serial communication default baud rate 115200@8N1 (adjustable) |
47+
| Microphone | MSM421A |
48+
| Audio Driver | AW8737 |
49+
| Speaker | 8Ω@1W, Size:2014 cavity speaker |
50+
| Built-in Units | KWS (wake word), ASR (speech recognition), LLM (large language model), TTS (text-to-speech) |
51+
| RGB Light | 3x RGB LED@2020 driven by LP5562 (status indication) |
52+
| Power | Idle: 5V@0.5W, Full load: 5V@1.5W |
53+
| Button | For entering download mode for firmware upgrade |
54+
| Upgrade Port | SD card / Type-C port |
55+
| Working Temp | 0-40°C |
56+
| Product Size | 54*54*13mm |
57+
| Packaging Size | 133*95*16mm |
58+
| Product Weight | 17.4g |
59+
| Packaging Weight | 32.0g |
60+
61+
<div class="product_pic"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/11.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/5.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/12.webp"></div>
62+
63+
<div class="product_pic"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/9.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/14.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/7.webp"></div>
64+
65+
## Related Links
66+
67+
- [AX630C](https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/AX630C.pdf)
68+
69+
## PinMap
70+
71+
| Module LLM | RXD | TXD |
72+
| ------------ | --- | --- |
73+
| Core (Basic) | G16 | G17 |
74+
| Core2 | G13 | G14 |
75+
| CoreS3 | G18 | G17 |
76+
77+
>LLM Module Pin Switching| LLM Module has reserved soldering pads for pin switching. In cases of pin multiplexing conflicts, the PCB trace can be cut and reconnected to other sets of pins.
78+
79+
<img alt="module size" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/03.jpg" width="100%" />
80+
81+
> Taking `CoreS3` as an example, the first column (left green box) is the TX pin for serial communication, where users can choose one out of four options as needed (from top to bottom, the pins are G18, G7, G14, and G10). The default is set to IO18. To switch to a different pin, cut the connection on the solder pad (at the red line) — it’s recommended to use a blade for this — and then connect to one of the three remaining pins below. The second column (right green box) is for RX pin selection, and, as with the TX pin, it also allows a choice of one out of four options.
82+
83+
84+
85+
## Video
86+
87+
- Module LLM product introduction and example showcase [Module_LLM_Video.mp4](https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/Module_LLM_Video.mp4)
88+
89+
## AI Benchmark Comparison
90+
91+
<img alt="compare" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/Benchmark%E5%AF%B9%E6%AF%94.png" width="100%" />

‎README_zh.md‎

Lines changed: 105 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,105 @@
1+
# Module-LLM
2+
3+
<div class="product_pic"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/4.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/10.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/15.webp"></div>
4+
5+
## 描述
6+
7+
**Module LLM**是一款集成化的离线大语言模型 (LLM) 推理模块，专为需要高效，智能交互的终端设备设计，无论是在智能家居，语音助手，还是在工业控制中，Module LLM 都能为您带来流畅，自然的 AI 体验，无需依赖云端，确保隐私安全与稳定性。集成 **StackFlow** 框架，配合 **Arduino/UiFlow** 库，几行代码就可轻松实现端侧智能。<br>
8+
搭载爱芯 **AX630C** SoC 先进处理器，集成 3.2 TOPs 高能效 NPU，原生支持 Transformer 模型，轻松应对复杂 AI 任务。配备 **4GB LPDDR4** 内存（其中1GB供用户使用，3GB专用于硬件加速）和**32GB eMMC**存储，支持多模型并行加载与串联推理，确保多任务处理流畅无阻。运行功耗仅约 1.5W，远低于同类产品，节能高效，适合长时间运行。<br>
9+
集成麦克风，扬声器，TF存储卡，**USB OTG** 及 RGB状态灯，满足多样化应用需求，轻松实现语音交互与数据传输。灵活扩展：板载 SD 卡槽支持固件冷/热升级，**UART** 通信接口简化连接与调试，确保模块功能持续优化与扩展。USB 口支持主从自动切换，既可以做调试口，也可以外接更多 USB 设备如摄像头。搭配 LLM 调试套件，用于扩展百兆以太网口，及内核串口，作为 SBC 使用。<br>
10+
多模型兼容，出厂预装 **Qwen2.5-0.5B** 大语言模型，内置**KWS**（唤醒词），**ASR**（语音识别），**LLM**（大语言模型）及**TTS**（文本转语音）功能，且支持分开调用或 **pipeline** 自动流转，方便开发。后续将支持Qwen2.5-1.5B、Llama3.2-1B及InternVL2-1B等多种端侧LLM/VLM模型，支持热更新模型，紧跟社区潮流，适应不同复杂度的AI任务；视觉识别能力：支持CLIP、YoloWorld等Open world模型，未来将持续更新DepthAnything、SegmentAnything等先进模型，赋能智能识别与分析；<br>
11+
即插即用，搭配**M5主机**，Module LLM 实现即插即用的AI交互体验。用户无需繁琐设置，即可将其集成到现有智能设备中，快速启用智能化功能，提升设备智能水平。该产品适用于离线语音助手，文本语音转换，智能家居控制，互动机器人等领域。
12+
13+
14+
15+
16+
## 产品特性
17+
18+
- 离线推理,3.2T@INT8精度算力
19+
20+
- 集成KWS（唤醒词），ASR（语音识别），LLM（大语言模型），TTS（文本生成语音）
21+
22+
- 多模型并行
23+
24+
- 板载32GB eMMC存储和4GB LPDDR4内存
25+
26+
- 板载麦克风及扬声器
27+
28+
- 串口通信
29+
30+
- SD卡固件升级
31+
32+
- 支持ADB调试
33+
34+
- RGB提示灯
35+
36+
- 内置ubuntu系统
37+
38+
- 支持OTG功能
39+
40+
- 支持Arduino/UIFlow
41+
42+
43+
44+
45+
## 应用
46+
47+
- 离线语音助手
48+
- 文本语音转换
49+
- 智能家居控制
50+
- 互动机器人
51+
52+
## 规格参数
53+
54+
| 规格 | 参数 |
55+
| ------------ | --------------------------------------------------------------------------- |
56+
| 处理器SoC | AX630C@Dual Cortex A53 1.2 GHz <br> MAX.12.8 TOPS @INT4,and 3.2 TOPS @INT8 |
57+
| 内存 | 4GB LPDDR4(1GB系统内存 + 3GB 硬件加速专用内存) |
58+
| 存储 | 32GB eMMC5.1 |
59+
| 通信接口 | 串口通信 波特率默认 115200@8N1（可调） |
60+
| 麦克风 | MSM421A |
61+
| 音频驱动 | AW8737 |
62+
| 扬声器 | 8Ω@1W,尺寸:2014 腔体喇叭 |
63+
| 内置功能单元 | KWS（唤醒词），ASR（语音识别），LLM（大语言模型），TTS（文本生成语音） |
64+
| RGB灯 | 3x RGB LED@2020 由LP5562驱动 (状态指示) |
65+
| 功耗 | 空载：5V@0.5W，满载:5V@1.5W |
66+
| 按键 | 用于升级固件进入下载模式 |
67+
| 升级接口 | SD卡/Type C口 |
68+
| 工作温度 | 0-40°C |
69+
| 产品尺寸 | 54*54*13mm |
70+
| 包装尺寸 | 133*95*16mm |
71+
| 产品重量 | 17.4g |
72+
| 包装重量 | 32.0g |
73+
74+
<div class="product_pic"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/11.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/5.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/12.webp"></div>
75+
76+
<div class="product_pic"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/9.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/14.webp"><img class="pic" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/7.webp"></div>
77+
78+
79+
## 相关链接
80+
81+
- [AX630C](https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/AX630C.pdf)
82+
83+
## PinMap
84+
85+
| Module LLM | RXD | TXD |
86+
| ------------ | --- | --- |
87+
| Core (Basic) | G16 | G17 |
88+
| Core2 | G13 | G14 |
89+
| CoreS3 | G18 | G17 |
90+
91+
>LLM Module引脚切换| LLM Module预留了引脚切换焊盘, 一些出现引脚复用冲突的情况下, 可以通过切割PCB线路然后跳线连接至其他组引脚。
92+
93+
<img alt="module size" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/03.jpg" width="100%" />
94+
95+
> 以`CoreS3`为例子，第一列（左绿色框）是串口通讯的TX引脚，用户根据需要四选一，（从上到下分别代表引脚G18 G7 G14 G10）,默认是IO18引脚，如需要切换其他引脚，切断焊盘连接线（红线处）（建议使用刀片切割），然后连接下面三个引脚之间的一个即可；第二列（右绿色框）是RX引脚切换，如上所述，也是四选一操作
96+
97+
98+
99+
## 视频
100+
101+
- Module LLM 产品介绍以及例子展示 [Module_LLM_Video.mp4](https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/Module_LLM_Video.mp4)
102+
103+
## AI Benchmark 对比
104+
105+
<img alt="compare" src="https://m5stack.oss-cn-shenzhen.aliyuncs.com/resource/docs/products/module/Module%20LLM/Benchmark%E5%AF%B9%E6%AF%94.png" width="100%" />

‎SDK‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
Subproject commit c767769d28ec511b613a24fc8680ec3acd4c769a

0 commit comments

Comments
 (0)