Saltar al contenido principal
Comunicados de prensa

Supermicro Now Shipping Next-Generation Servers Powered by 6th Gen AMD EPYC™ 9006 Series CPUs for Cloud, HPC, and Agentic AI Workloads

  • Supermicro’s latest H15 server portfolio—powered by 6th Gen AMD EPYC 9006 Series processors (formerly codenamed “Venice”)—achieved outstanding benchmark results, setting multiple SPEC CPU world records on the 2U Hyper and CloudDC servers demonstrating generational leaps in performance and speed
  • H15 generation server portfolio delivers up to 33% more cores, 2× PCIe bandwidth, and 1.6 TB/s per socket memory bandwidth for AI inference and HPC workloads
  • Helios and Helion next-gen rack-scale solutions, built on Supermicro DCBBS and powered by AMD EPYC CPUs and AMD Instinct™ GPUs, are optimized for large-scale and agentic AI deployments
More

Supermicro Launches KV Cache Solution with IBM and NVIDIA Demonstrating Significant Inference Performance Benefits

  • The KV (key-value) cache solution integrates Supermicro Petascale storage servers, IBM Storage Scale software, NVIDIA Dynamo inference software, and NVIDIA Spectrum-X Ethernet switches
  • Performance testing shows that the KV cache solution reduces Time-to-First-Token (TTFT) for long-context windows compared to systems with no KV cache
  • Customers can dramatically improve inference efficiency through higher GPU utilization, throughput, and infrastructure scalability
More

Supermicro Introduces the NVIDIA Vera CPU Rack, a 256 CPU, 100% Liquid-Cooled Rack-Scale Solution, Complementing the NVIDIA Vera Rubin Platform, for Agentic AI at Scale

  • Delivers dedicated 256 NVIDIA Vera CPU capacity for agent sandboxes, complementing NVIDIA Vera Rubin NVL72 with common DCBBS infrastructure with third-generation NVIDIA MGX racks and battery backup units
  • Integrates NVIDIA Vera CPUs and BlueField™-4 DPUs with the NVIDIA Open Agent Safety Platform and OpenShell Reference Architecture for secure, high-density agentic AI orchestration and continuous monitoring and policy enforcement
  • Leverages Supermicro DCBBS to deliver a complete, integrated data center solution—from liquid-cooled rack architecture and power infrastructure to networking, cooling, and deployment services—enabling customers to build and scale full AI factories for agentic workloads
More

Supermicro Brings NVIDIA Aerial RAN Computer Solutions to the Network Edge with Nokia to Enable Low-latency AI Services

  • Improve network economics with higher spectral efficiency using AI-RAN platform for 5G today, with software upgradeable path that protects infrastructure investment
  • Unlock AI monetization by enabling low-latency, critical AI services, enterprise edge inferencing, and practical physical AI applications
  • Deploy an integrated AI-RAN stack combining Supermicro infrastructure, NVIDIA accelerated computing, and Nokia RAN software
More
Siguenos en redes
Supermicro en las noticias
Reseñas de productos

160 bahías NVMe SSD Servidor 4U presentado en FMS 2026. Supermicro ASG-4116S-NU160R

By Eric Smith -

At FMS 2026, we saw a really neat system. The Supermicro ASG-4116S-NU160R is a single-socket AMD EPYC server that sports 160x U.2 NVMe drive bays.

Lee esta reseña

Una mirada de cerca a la Supermicro Estación de IA superior GB300

By Ryan Smith -

With NVIDIA announcing multiple new desktop system designs at Computex 2026, NVIDIA’s partners were understandably eager to show off their current and forthcoming wares.

Lee esta reseña

Supermicro Análisis del SYS-112D-36C-FN3P: Un procesador Intel de 36 núcleos. Xeon Servidor SoC de 6 puertos con 2 puertos de 100 GbE

By Patrick Kennedy -

We recently looked at the Supermicro SYS-112D-40C-FN8P, a short-depth Intel Xeon 6 SoC system with eight 25GbE ports. This Supermicro SYS-112D-36C-FN3P is a similar 36-core version, but the bigger change is networking. Instead of 8x 25GbE, this platform gives us 2x QSFP28 100GbE in the same general front-I/O 1U format.

Lee esta reseña

Agentes de IA: Estoy aquí para el avance racional de la humanidad (siempre que pueda ejecutarse localmente).

By Level1Techs -

A lot of you do not like AI, and you have good reasons to be wary of it! But Wendell doesn't believe we should be afraid of the future!

Lee esta reseña

Si la IA es tan decepcionante, ¿por qué el mundo está generando tanto poder para ella?

By Level1Techs -

Wendell thinks 2026 may be the year AI expectations reset for the average person,
and that reset may happen as the world doubles down on AI infrastructure, because the real long-term bet is not just chatbots or LLMs.

Lee esta reseña

¡La IA no tiene por qué requerir centros de datos gigantescos!

By Level1Techs -

Wendell argued that “AI Factory” is a design pattern, not a metaphor.
In this video, he wants to show what it looks like when that design pattern scales down physically.

Lee esta reseña
Kits de prensa
Seminarios web