KR4268V2
-
8x NVIDIA A100 GPUs
-
2x 3rd Gen Intel® Xeon® Scalable
-
600GB/s bandwidth GPU interconnect via NVLink
-
Up to 5 petaFLOPS maximum performance
KR4268V2
KR4268V2 With 4th Gen Intel® Xeon® Scalable Processors Is A Powerful 4U AI Server With The Latest PCIe Gen 5.0 Architecture, Supporting 8 FHFL PCIe GPU Cards. Its Flexible Configurations And Topologies Support A Variety Of Advanced AI Applications Including AI Cloud, IVA, Video Processing, And More.
Enhanced Architecture
-
PCIe 5.0 Architecture Supports Up To 600W Power Consumption
-
Latest CXL1.1 Interconnect Technology Supports Storage-Level Memory Space Expansion
-
Supports Latest 400G NDR Infiniband Network And 400G OCP 3.0
Flexible Configuration
-
Modular Design Concept Supports Flexible Component-Level Configuration
-
4 CPU-GPU Topologies For Various AI Application Scenarios
-
Compatible With The Latest AI Accelerators In The Ecosystem
Advanced Performance
-
Supports NVIDIA L40S, H100, And A100 GPUs
-
Supports 2x 4th Gen Intel® Xeon® Scalable Processors, TDP 350W
-
Built-In 8TB System Memory And 300TB Local High-Speed Storage For Improved Data Access Speed
Tools For Developers
-
Leading Deep Learning Frameworks, TensorFlow, PyTorch, Paddle -Paddle, Etc.
-
AIStation Resource Platform, Algorithm Platform And Application Optimization Service
TECH SPECS & CUSTOMIZATION
0KR4268-X2-A0-R0-00
Form Factor 4U Rack Server
GPU
8x FHFL Double-Widtd PCIe 5.0 GPU Cards
Supports Additional 2x FL Double-Widtd PCIe GPU, 1x FL Single-Widtd PCIe GPU Supports L40S, H100, A100
CPU
2x 4td Gen Intel® Xeon® Scalable Processors, Up To 350W
Memory 32x DDR5 4800MT/S RDIMMs
Expansion Slots 11x PCIe 5.0 X16 Slots
I/O
Front: 1x USB 3.0, 1x USB 2.0，1x VGA, 1x Type-C
Rear: 2x USB3.0, 1x RJ45, 1x MicroUSB, 1x VGA
OCP
1x OCP 3.0 SFF, Support NCSI
Management Aspeed 2600
Security
TPM 2.0 (Trusted Platform Module)
Storage
24x 2.5” SSD, Up To 16x NVMe U.2.
2x NVMe/SATA M.2
PSU 4x 12V 3000W, 2+2
Dimensions