G2L4-SD4-LA08

即將推出

HPC/AI Server - Intel® Xeon® 6700/6500-Series Processors - 2U, DP, NVIDIA HGX™ Rubin NVL8, DLC
  • Liquid-cooled NVIDIA HGX™ Rubin NVL8
  • CPU+GPU direct liquid cooling solution with leak detection
  • 8 x 800 Gb/s OSFP InfiniBand or Ethernet GPU networking ports via 8 x single-port NVIDIA ConnectX®-9 VPI
  • 3 TB/s GPU-to-GPU bandwidth with NVIDIA NVLink™ and NVIDIA NVLink™ Switch
  • Dual Intel® Xeon® 6700/6500-Series Processors
  • 8-Channel liquid-cooled DDR5 RDIMM/MRDIMM per CPU with 32 x DIMMs
  • 1 x 1 Gb/s LAN ports via Intel® I210-AT
  • 2 x M.2 slots with PCIe Gen6 x4
  • 8 x liquid-cooled E1.S Gen5 NVMe hot-swap bays
  • 1 x liquid-cooled FHHL PCIe x16 slots with Gen6 x16 lanes for NVIDIA BlueField®-4 DPU
  • 54 V DC Bus Bar power solution
儲存
此產品已儲存至最愛清單
我的收藏產品
詢價清單

NVIDIA HGX Rubin NVL8

Agentic AI doesn't just compute, it reasons, coordinates, and remembers across every step of a long-running task, passing context between models and agents in real time. That demands a system built for exactly that job. The NVIDIA HGX Rubin NVL8 platform answers the call, with eight NVIDIA Rubin GPUs working as one, linked by sixth-generation NVIDIA NVLink™ so agents can share information instantly instead of waiting for it. A multi-agent engine and dedicated reinforcement learning engine keep reasoning workflows fast and memory optimized, even as workloads scale from training through post-training and inference. The result is a system built from the ground up for the way intelligent agents actually think and act at enterprise scale.
Content Image
GPU8x NVIDIA Rubin GPUs
Total GPU Memory | Bandwidth2.3 TB | 176 TB/s
CPU2x Intel® Xeon® 6 processors
NVIDIA NVLink Switch System4x
NVIDIA NVLink Bandwidth28.8 TB/s total bandwidth
Networking

8x OSFP ports serving 8x single-port NVIDIA ConnectX®-9 VPI

- up to 800 Gb/s NVIDIA InfiniBand and Ethernet

2x 400G QSP112 NVIDIA BlueField®-4 DPUs

- up to 800 Gb/s NVIDIA InfiniBand and Ethernet

Boosting Individual Applications with On-Point Features

Intel® Xeon® 6 is a new generation of processors that has tailored its CPU lineup to target all uses cases such as Cloud Computing, AI, Analytics, and Edge & IOT. Whether it's high compute density that is dependent on core count and power efficiency or AI/HPC applications that heavily rely on strong single-core performance, this new platform covers them all with its Performance cores (P-cores) and Efficient-cores (E-cores). Along with flexible I/O options, integrated accelerators, and support for CXL 2.0 devices, Intel Xeon 6 fulfills customer needs across the broadest range of data center workloads, segments, and deployment models.
Content Image

Core Technology Aligned with Aspirations

Accelerators
built-in*
Incredible performance and efficiency improvements with the easy adoption of on-chip accelerators
8 or 12
Channels
Increased memory frequency and throughput with DDR5 RDIMM support
PCIe 5.0
lanes
Up to 136 lanes for 1S designs, supporting all the latest drives and accelerators
CXL 2.0
support**
Flexible support between PCIe and CXL, utilizing DDR5 and CXL memory as one unified region
Up to 288
E-cores per CPU
Core dense and optimized efficiency for cloud-native and hyperscale workloads
Intel Xeon 6 Processors with E-cores
Up to 128
P-cores per CPU
Greater core performance with improved TCO, accelerating AI and compute intensive workloads
Intel Xeon 6 Processors with P-cores
MRDIMM
support
Unprecedented frequency on the advanced MRDIMM, boosting memory-intensive application to a whole new level
Intel Xeon 6 Processors with P-cores
* Different on-chip accelerators are supported depending on CPU SKUs, and they require a one-time activation. Please visit Intel's official website or contact technical support for details.

** CXL peripheral support varies by product. Please refer to the QVL list for validated configurations.