惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

P
Proofpoint News Feed
Martin Fowler
Martin Fowler
The GitHub Blog
The GitHub Blog
B
Blog RSS Feed
U
Unit 42
阮一峰的网络日志
阮一峰的网络日志
量子位
GbyAI
GbyAI
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
云风的 BLOG
云风的 BLOG
小众软件
小众软件
博客园 - 三生石上(FineUI控件)
L
LangChain Blog
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
博客园_首页
IT之家
IT之家
V
Visual Studio Blog
Y
Y Combinator Blog
Blog — PlanetScale
Blog — PlanetScale
宝玉的分享
宝玉的分享
Apple Machine Learning Research
Apple Machine Learning Research
I
InfoQ
D
Docker
V
V2EX

AI demand is so high, AWS customers are trying to buy out its entire capacity | Network World

Cisco: Latest news and insights 2026 network outage report and internet health check Selector targets the network visibility gap in multi-cloud infrastructure AI reshapes cybersecurity workforce priorities as IT teams brace for new risks Top network and data center events of 2026 How AI is transforming network incident response (and where it still falls short) Google opens TPUs to enterprises beyond its own cloud via Blackstone JV AI, cybersecurity skills top IT pay premiums Startup Bolt Graphics promises 5x performance over Nvidia’s best GPU Wireless security is a battle of AI vs. AI NetOps teams look to AI to automate Day 2 operations Digital twins reshape network and data center management Network outages, power failures strain data center resiliency Five takeaways from Cisco's blowout quarter and what it means to customers Cisco to cut nearly 4,000 jobs despite strong growth in AI, enterprise networking Startup SPAN teams with Nvidia to put data center nodes in your backyard Hard drive shortage affecting enterprise storage needs Wi-Fi 8 is closer than you think. Here’s what you need to know Cisco open-sources agentic AI security spec HPE revamps private cloud stack for enterprises rethinking VMware Versa takes aim at fragmented enterprise security with CSPM, orchestration update, and AI agent controls Red Hat opens Ansible to AI agents, within limits Red Hat offers endless Linux support — for a fee Red Hat: Sovereignty is more than just compliance Tech job postings hit three-year high as AI demand fuels hiring rebound HPE memory server targets compute-heavy and agentic AI workloads PCI group begins work on new spec to support bandwidth-hungry apps like AI, HPC Q&A: Quantum physicist Sonia Fernández-Vidal on why classical computing isn't going anywhere OpenAI-led consortium seeks to address AI processing bottlenecks AWS hit by US-East-1 outage after data center thermal event
AMD launches AI-targeted PCIe cards for current servers
2026-05-08 · via AI demand is so high, AWS customers are trying to buy out its entire capacity | Network World

AMD has launched the latest in its Instinct enterprise GPU accelerators, the MI350, which are designed to fit the data center infrastructure customers already own.

Targeted at agentic AI, Instinct MI350P PCIe cards are dual-slot drop-in cards for standard air-cooled servers. They are built to deploy inference on premises within customer’s current data center  power, cooling, and rack infrastructure.

The MI350P is AMD’s first PCIe-based Instinct accelerator in four years. It has traditionally made Instinct GPUs available as server-mounted OAM modules in a bundle of eight GPUs. This is a full height, full length PCIe card that can go in any 2U or larger design. It lets an enterprise customer gradually experiment with AI using just one card rather than eight GPUs, which is how AMD offers them typically.

Instinct MI350P PCIe cards are available in air-cooled systems with up to eight accelerator cards, which makes them ideal for small, medium, and large AI models for inference and RAG pipelines. It has 144GB of high bandwidth memory 3e (HBM3E) running at up to 4TB/s.

Performance is estimated at 2,299 teraflops (TFLOPS) and up to 4,600 peak TFLOPS at MXFP4, which AMD says is the highest performance currently available in an enterprise PCIe card. It offers native support for lower-precision MXFP6 and MXFP4, which deliver high throughput as well as acceleration through sparsity support for most mainstream 8- and 16-bit precisions.

The MI350P card supports technology called sparsity, where zero values in data sets and matrixes are ignored, thus reducing the processing time. Support for sparsity means higher precision formats, like INT8 and BF16, deliver efficient performance, according to AMD.

AMD says the Instinct MI350P is capable of handling around 200 to 250 billion parameter large language models per GPU and with support for up to eight GPUs per node, it can cover SLM / MLM / LLM inference / RAG workloads. It also supports all of the common ROCm open source software stack AMD offers with the other Instinct and Radeon products.

AMD did not give a launch date or a price for the MI350P.

SUBSCRIBE TO OUR NEWSLETTER

From our editors straight to your inbox

Get started by entering your email address below.