Difference between revisions of "ALPHA-One"
Jump to navigation
Jump to search
| (10 intermediate revisions by the same user not shown) | |||
| Line 3: | Line 3: | ||
The '''ALPHA-One''' is a Generative 7b LLM AI Agent based on StarPro64 board RISC-V based Single Board Computer with 20TOPS(int 8) NPU capability, and preinstalled 64G eMMC module contains 7b Deepseek/Owen LLM build in docker form. | The '''ALPHA-One''' is a Generative 7b LLM AI Agent based on StarPro64 board RISC-V based Single Board Computer with 20TOPS(int 8) NPU capability, and preinstalled 64G eMMC module contains 7b Deepseek/Owen LLM build in docker form. | ||
== Software releases == | |||
This is the production release build 20250627 | |||
DD image for 64GB eMMC module | |||
* This build contains 7b QWen2 LLM | |||
* Web ui access link http://alpha-one.local:8000/ | |||
* [https://files.pine64.org/os/StarPro64/Alpha-ONE%20image-20250627.img.gz Direct download from PINE64 file server] | |||
** MD5 (GZip file): d62eeb1645c7b496a0815c4590f798c7 | |||
** File Size: 18.10GB | |||
{| class="wikitable" | |||
!colspan="2" style="background: #a7d7f9;"| Default credentials | |||
|- | |||
! Super user | |||
| <code>eswin/eswin</code> | |||
|} | |||
This is the early test build that contains both 7b Deepseek and QWen2 LLM build, OS based on ROCKOS. | |||
DD image for 32GB eMMC module and above | |||
* for larger than 32GB eMMC, please use gpart to extend the file partition. | |||
* [https://files.pine64.org/SDK/StarPro64/Alpha-ONE_OS_build_32GB-20250420.img.gz Direct download from PINE64 file server] | |||
** MD5 (GZip file): 6669a436104e97e2ad90679e06f62d78 | |||
** File Size: 18.21GB | |||
{| class="wikitable" | |||
!colspan="2" style="background: #a7d7f9;"| Default credentials | |||
|- | |||
! Super user | |||
| <code>eswin/eswin</code> | |||
|} | |||
To explore LLM, use terminal program and execute below command lines: | |||
deepseek 7bLLM command line： | |||
sudo /opt/eswin/sample-code/npu_sample/qwen_sample/bin/es_qwen2 /opt/eswin/sample-code/npu_sample/qwen_sample/src/deepseek_r1_distill_qwen_7b/config.json | |||
qwen2 7bLLM command line： | |||
sudo /opt/eswin/sample-code/npu_sample/qwen_sample/bin/es_qwen2 /opt/eswin/sample-code/npu_sample/qwen_sample/src/qwen2_7b/config.json | |||
qwen2 0.5bLLM command line： | |||
sudo /opt/eswin/sample-code/npu_sample/qwen_sample/bin/es_qwen2 /opt/eswin/sample-code/npu_sample/qwen_sample/src/qwen2_0_5b/config.json | |||
== SDK releases == | == SDK releases == | ||
* SDK document (some in Chinese): https://files.pine64.org/SDK/StarPro64/docs.7z | * SDK document (some in Chinese): https://files.pine64.org/SDK/StarPro64/docs.7z | ||
** MD5 (7Zip file): 8ee9b660c336d9979191d212e9826226 | |||
** File Size: 34MB | |||
* SDK Release: | * SDK Release: | ||
** 20250228: https://files.pine64.org/SDK/StarPro64/EIC7x_AI_Release_20250228.7z | ** 20250228: https://files.pine64.org/SDK/StarPro64/EIC7x_AI_Release_20250228.7z | ||
** MD5 (7Zip file): f9171ec8b30e5d4d8eda1185f72af5e4 | |||
** File Size: 1.932GB | |||
** 20250330: https://files.pine64.org/SDK/StarPro64/EIC7x_AI_Release_20250330.7z | |||
** MD5 (7Zip file): 8ddc861755ed26785e67674aad8db87c | |||
** File Size: 1.946GB | |||
* LLM and tools release: | * LLM and tools release: | ||
** LLM 20250228: https://files.pine64.org/SDK/StarPro64/deepseek&qwen-v0228.7z | ** LLM 20250228: https://files.pine64.org/SDK/StarPro64/deepseek&qwen-v0228.7z | ||
** MD5 (7Zip file): b8ee72ee6a8912afefac3fa43a18be87 | |||
** File Size: 722MB | |||
** Tools 20250228: https://files.pine64.org/SDK/StarPro64/EIC7x_nn-tools_Release_20250228.7z | ** Tools 20250228: https://files.pine64.org/SDK/StarPro64/EIC7x_nn-tools_Release_20250228.7z | ||
** MD5 (7Zip file): 868434b274412e173c3e264118dcb336 | |||
** File Size: 6.625GB | |||
| Line 21: | Line 80: | ||
[[File:EIC7700X_Block_Diagram.png|800px]] | [[File:EIC7700X_Block_Diagram.png|800px]] | ||
== Features == | |||
=== System Memory === | === System Memory === | ||
| Line 26: | Line 88: | ||
* 64GB eMMC preintsalled with 7b Deepseek/Qwen LLM | * 64GB eMMC preintsalled with 7b Deepseek/Qwen LLM | ||
== | === Case === | ||
* CNC from single Aluminum block | |||
* Passive cooling, built-in heat pipe that directly contact with SoC | |||
=== Network === | === Network === | ||
* Dual 10/100/1000Mbps Ethernet | * Dual 10/100/1000Mbps Ethernet | ||
* 2.4GHz/ | * 2.4GHz/5GHz MIMO WiFi 802.11 b/g/n/ac/ax with Bluetooth 5.3 | ||
=== Expansion Ports === | === Expansion Ports === | ||
| Line 38: | Line 101: | ||
* Digital Video output up to 4K@60Hz | * Digital Video output up to 4K@60Hz | ||
* 3.5mm audio Jack with mic in | * 3.5mm audio Jack with mic in | ||
== Certifications == | == Certifications == | ||
| Line 43: | Line 107: | ||
== Potential Improvement == | |||
* Current 7bLLM throughput is around 3.5 tokens/second using docker form, potential improve upto 10 tokens/second when operates LLM in native mode. | |||
* Potential increase LLM capability from 7b to 15b with system software optimization | |||
* If ALPHA-One proven its potential, consider release ALPHA-Two which can host up to 30b LLM | |||
Latest revision as of 21:07, 29 June 2025
The ALPHA-One is a Generative 7b LLM AI Agent based on StarPro64 board RISC-V based Single Board Computer with 20TOPS(int 8) NPU capability, and preinstalled 64G eMMC module contains 7b Deepseek/Owen LLM build in docker form.
Software releases
This is the production release build 20250627
DD image for 64GB eMMC module
- This build contains 7b QWen2 LLM
- Web ui access link http://alpha-one.local:8000/
- Direct download from PINE64 file server
- MD5 (GZip file): d62eeb1645c7b496a0815c4590f798c7
- File Size: 18.10GB
| Default credentials | |
|---|---|
| Super user | eswin/eswin
|
This is the early test build that contains both 7b Deepseek and QWen2 LLM build, OS based on ROCKOS.
DD image for 32GB eMMC module and above
- for larger than 32GB eMMC, please use gpart to extend the file partition.
- Direct download from PINE64 file server
- MD5 (GZip file): 6669a436104e97e2ad90679e06f62d78
- File Size: 18.21GB
| Default credentials | |
|---|---|
| Super user | eswin/eswin
|
To explore LLM, use terminal program and execute below command lines:
deepseek 7bLLM command line： sudo /opt/eswin/sample-code/npu_sample/qwen_sample/bin/es_qwen2 /opt/eswin/sample-code/npu_sample/qwen_sample/src/deepseek_r1_distill_qwen_7b/config.json
qwen2 7bLLM command line： sudo /opt/eswin/sample-code/npu_sample/qwen_sample/bin/es_qwen2 /opt/eswin/sample-code/npu_sample/qwen_sample/src/qwen2_7b/config.json
qwen2 0.5bLLM command line： sudo /opt/eswin/sample-code/npu_sample/qwen_sample/bin/es_qwen2 /opt/eswin/sample-code/npu_sample/qwen_sample/src/qwen2_0_5b/config.json
SDK releases
- SDK document (some in Chinese): https://files.pine64.org/SDK/StarPro64/docs.7z
- MD5 (7Zip file): 8ee9b660c336d9979191d212e9826226
- File Size: 34MB
- SDK Release:
- 20250228: https://files.pine64.org/SDK/StarPro64/EIC7x_AI_Release_20250228.7z
- MD5 (7Zip file): f9171ec8b30e5d4d8eda1185f72af5e4
- File Size: 1.932GB
- 20250330: https://files.pine64.org/SDK/StarPro64/EIC7x_AI_Release_20250330.7z
- MD5 (7Zip file): 8ddc861755ed26785e67674aad8db87c
- File Size: 1.946GB
- LLM and tools release:
- LLM 20250228: https://files.pine64.org/SDK/StarPro64/deepseek&qwen-v0228.7z
- MD5 (7Zip file): b8ee72ee6a8912afefac3fa43a18be87
- File Size: 722MB
- Tools 20250228: https://files.pine64.org/SDK/StarPro64/EIC7x_nn-tools_Release_20250228.7z
- MD5 (7Zip file): 868434b274412e173c3e264118dcb336
- File Size: 6.625GB
Main Board and SoC Specification
- Based on StarPro64 Single Board Computer wiki page
- Based on ESWIN EIC7700X SoC
Features
System Memory
- 32GB 64bits LPDDR5@6400MHz RAM Memory.
- 64GB eMMC preintsalled with 7b Deepseek/Qwen LLM
Case
- CNC from single Aluminum block
- Passive cooling, built-in heat pipe that directly contact with SoC
Network
- Dual 10/100/1000Mbps Ethernet
- 2.4GHz/5GHz MIMO WiFi 802.11 b/g/n/ac/ax with Bluetooth 5.3
Expansion Ports
- 2× USB3.0 Dedicated Host port
- 2× USB2.0 Shared Host port
- Digital Video output up to 4K@60Hz
- 3.5mm audio Jack with mic in
Certifications
- Not yet available
Potential Improvement
- Current 7bLLM throughput is around 3.5 tokens/second using docker form, potential improve upto 10 tokens/second when operates LLM in native mode.
- Potential increase LLM capability from 7b to 15b with system software optimization
- If ALPHA-One proven its potential, consider release ALPHA-Two which can host up to 30b LLM