160 TOPS
Computing Power
Private Deployment
of Large Models
Secure and High-Speed
Network Communication
Supports Multiple
Deep Learning Frameworks
CSB1-N10S1688 system is capable of accommodating a maximum of 10 computing nodes, each featuring an SOPHON BM1688
processor with a top speed of 1.6GHz.With a total computing power of up to 160 TOPS, it provides robust computational support
for artificial intelligence and deep learning applications.
Supports the private deployment of expansive parameter models based on the Transformer framework, including substantial
language models like Gemma-2B, ChatGLM3-6B and Qwen1.5-1.8B.
With BMC remote management system, it easily
achieves real-time monitoring, software
configuration, hardware management, remote
operations,maintenance,while also offering
capabilities for secondary development.
The server consolidates compute modules, storage, USB
interfaces, network controllers, power management, and
sensors into a streamlined system, minimizing the
acquisition, development, and operational expenses
for users.
Provides the one-stop SDK for deep learning
development, which includes a suite of software tools
such as underlying driver environments, compilers, and
tools for inference and deployment. It supports the
development of mainstream network models and custom
operators, as well as Docker containerization for the
rapid deployment of algorithmic applications.
CSB1-N10S1688 | ||
Technical Specifications
|
Server form |
1U rack-mounted computing power server |
Framework |
ARM architecture |
|
Number of nodes |
10 distributed computing nodes (up to 80 ARM cores) + 1 control node |
|
Compute nodes |
Octa-core 64-bit processor BM1688, main frequency up to 1.6GHz |
|
Control nodes |
Octa-core 64-bit processor RK3588, main frequency up to 2.4GHz, the highest computing power is 6TOPS |
|
AI computing power |
160TOPS (INT8) |
|
RAM |
8GB LPDDR4 × 10 (Number of compute nodes)(Optional: 4GB/8GB/16GB) |
|
Storage |
32GB eMMC × 10 (Number of compute nodes)(Optional: 16GB/32GB/64GB/128GB/256GB) |
|
Storage Expansion |
3.5-inch/2.5-inch SATA3.0/SSD hard drive slot × 1 (BMC can directly operate the hard drive, and computing child nodes can indirectly access the hard drive through the network sharing method provided by BMC) |
|
Power |
550W AC power supply (Input: 90V AC~264V AC, 47 Hz~63 Hz, 8A) (Hot swappable not supported) |
|
Fan module |
6 high-speed cooling fans |
|
Physical Specifications
|
Size |
420.0mm(L) × 421.3mm(W) × 44.4mm(H) |
Installation requirements |
IEC 297 Universal Cabinet Installation: 19 inches wide and 800 mm deep and above Retractable slideway installation: The distance between the front and rear holes of the cabinet is 543.5mm~848.5mm |
|
Full weight |
Server net weight: 8.1kg, total weight with packaging: 10.3kg |
|
Environment |
Operating Temperature: 0ºC ~ 45ºC, Storage Temperature: -40ºC ~ 60ºC, Operating Humidity: 5% ~ 90%RH(non-condensing) |
|
Software Specifications
|
BMC |
The BMC management system is integrated with the web-based management interface, supporting Redfish, VNC, NTP, monitoring advanced and virtual media, and the BMC management system can be redeveloped |
Large model |
Support the privatization deployment of ultra-large-scale parametric models under the Transformer architecture, such as Gemma-2B, LlaMa2-7B, ChatGLM3-6B, Qwen1.5-1.8B and other large language models |
|
Deep learning |
Traditional network architectures such as CNN, RNN, and LSTM; a variety of deep learning frameworks, including TensorFlow, PyTorch, PaddlePaddle, Caffe and ONNX, as well as custom operator development |
|
Interface Specifications
|
Internet |
2 × 10G Ethernet (SFP+), 2 × Gigabit Ethernet (RJ45), 1 × Gigabit Ethernet (RJ45, MGNT is used as BMC management network) |
Console |
1 × Console (RJ45, BMC debug serial port, baud rate 115200) |
|
Display |
1 × VGA (maximum resolution 1080P, BMC management display) |
|
USB |
2 × USB3.0 (The lower USB is USB3.0 OTG, and the BMC can be upgraded OTG by using a USB flash drive) |
|
Button |
1 × Reset, 1 × UID, 1 × Power button |
|
Other interfaces |
1 × RS232 (DB9, baud rate 115200),1 × RS485 (DB9, baud rate 115200) |