28 posts
The agentic AI moment has arrived, but delivering on its promise requires more than good models. It also takes fast hardware, secure runtimes, a responsive data layer and models tuned for long-running reasoning. NVIDIA and Microsoft are bringing that full stack to developers across Windows devices, Azure cloud and local deployments. At Microsoft Build, NVIDIA […]
We investigated why firmware updates were causing our core servers to take four hours to reboot. By diving into UEFI data structures and iPXE automation, we eliminated unnecessary timeouts and cut boot times back down to minutes.
We investigated a bug where CUBIC's congestion window became pinned at its minimum floor, causing a performance to plummet. The fix involved correctly measuring idle periods to distinguish RTT wait times from actual application idleness.
I’ve been approached more times than I can count by organizations on LinkedIn, all of them claiming to be impressed by my background and eager to feature my story in their publication. After doing my research, the pattern became clear. Your name gets listed in a booklet for free, but your photo, your story, your […] The post The Visibility…
The race to build the world’s most powerful AI factories demands networking that keeps pace with the ambitions of AI itself. NVIDIA Spectrum-X Ethernet scale-out infrastructure stands at the forefront of that race as the most advanced AI networking technology available today, deployed by industry leaders who can’t afford to compromise on performance, resilience or […]
The Problem: Legacy Tooling and Its Limitations Currently, Slack utilizes a hybrid approach to network measurement, incorporating both internal (such as traffic between AWS Availability Zones) and external (monitoring traffic from the public internet into Slack’s infrastructure) solutions. These tools comprise a combination of commercial SaaS offerings and custom-built network testing solutions developed by our…
The NVIDIA Blackwell platform has been widely adopted by leading inference providers such as Baseten, DeepInfra, Fireworks AI and Together AI to reduce cost per token by up to 10x. Now, the NVIDIA Blackwell Ultra platform is taking this momentum further for agentic AI. AI agents and coding assistants are driving explosive growth in software-programming-related […]
AI is powering breakthroughs across industries, helping enterprises operate with greater intelligence and speed. As AI factories scale, the next generation of enterprise AI depends on infrastructure that can efficiently manage data, secure every stage of the pipeline and accelerate the core services that move, protect and process information alongside AI workloads. NVIDIA has expanded […]
The world’s top-performing system for graph processing at scale was built on a commercially available cluster. NVIDIA last month announced a record-breaking benchmark result of 410 trillion traversed edges per second (TEPS), ranking No. 1 on the 31st Graph500 breadth-first search (BFS) list. Performed on an accelerated computing cluster hosted in a CoreWeave data center […]
Introducing new networking features in .NET 10 including HTTP space, WebSockets, security and more! The post .NET 10 Networking Improvements appeared first on .NET Blog.
At AWS re:Invent, NVIDIA and Amazon Web Services expanded their strategic collaboration with new technology integrations across interconnect technology, cloud infrastructure, open models and physical AI. As part of this expansion, AWS will support NVIDIA NVLink Fusion — a platform for custom AI infrastructure — for deploying its custom-designed silicon, including next-generation Trainium4 chips for […]
Timed with the Microsoft Ignite conference running this week, NVIDIA is expanding its collaboration with Microsoft, including through the adoption of next-generation NVIDIA Spectrum-X Ethernet switches for the new Microsoft Fairwater AI superfactory, powered by the NVIDIA Blackwell platform. The collaboration brings new integrations across Microsoft 365 Copilot, as well as the public preview of […]
AI agents have the potential to become indispensable tools for automating complex tasks. But bringing agents to production remains challenging. According to Gartner, “about 40% of AI prototypes make it into production, and participants reported data availability and quality as a top barrier to AI adoption.1” Just like human workers, AI agents need secure, relevant, […]
Where CPUs once ruled, power efficiency — and then AI — flipped the balance. Extreme co-design across GPUs, networking and software now drives the frontier of science.
At SC25, NVIDIA unveiled advances across NVIDIA BlueField DPUs, next-generation networking, quantum computing, national research, AI physics and more — as accelerated systems drive the next chapter in AI supercomputing. NVIDIA also highlighted storage innovations powered by the NVIDIA BlueField-4 data processing unit, part of the full-stack BlueField platform that accelerates gigascale AI infrastructure. More […]
Today’s AI workloads are data-intensive, requiring more scalable and affordable storage than ever. By 2028, enterprises are projected to generate nearly 400 zettabytes of data annually, with 90% of new data being unstructured, comprising audio, video, PDFs, images and more. This massive scale, combined with the need for data portability between on-premises infrastructure and the […]
In the age of AI reasoning, training smarter, more capable models is critical to scaling intelligence. Delivering the massive performance to meet this new age requires breakthroughs across GPUs, CPUs, NICs, scale-up and scale-out networking, system architectures, and mountains of software and algorithms. In MLPerf Training v5.1 — the latest round in a long-running series […]
AI factories continue to grow at unprecedented scale, processing structured, unstructured and emerging AI-native data. With demand for trillion-token workloads exploding, a new class of infrastructure is required to keep pace. At NVIDIA GTC Washington, D.C, NVIDIA revealed the NVIDIA BlueField-4 data processing unit, part of the full-stack BlueField platform that accelerates gigascale AI infrastructure, […]
This is one of those times when I feel pretty stupid.We booked the MagentaMobil Business Speedbox Flex tariff from Telekom for a company event. As the Speedbox wasn’t available and the event was taking place soon, we booked a FRITZ!Box 6850 LTE at short notice. After inserting the SIM card […] The post Unknown status LTE_DIA_IP with FRITZ!Box 6850 LTE…
We’ve been working to bring components of Quip’s technology into Slack with the canvas feature, while also maintaining the stand-alone Quip product. Quip’s backend, which powers both Quip and canvas, is written in Python. This is the story of a tricky bug we encountered last July and the lessons we learned along the way about…
Slack handles billions of inbound network requests per day, all of which traverse through our edge network and ingress load balancing tiers. In this blog post, we’ll talk about how a request flows — from a Slack’s user perspective — across the vast ether of the network to reach AWS and then Slack’s internal…
Summary In recent years, cellular architectures have become increasingly popular for large online services as a way to increase redundancy and limit the blast radius of site failures. In pursuit of these goals, we have migrated the most critical user-facing services at Slack from a monolithic to a cell-based architecture over the last 1.5 years.…
Sophos’ access points are very sensitive with PoE enabled cable connections. If your access point gets disconnected, disable PoE for the given Ethernet port. As a long time reader of my blog, you might know that I am struggling a lot with curious issues like broken L2TP/IPSec VPN connections. This […] The post Sophos UTM and AP15: fixing “ll_read: dead…
A few months ago I had a strange behaviour: Sometimes the L2TP/IPSec connection between my workstation at home and our company VPN silently failed. After clicking on the VPN connection icon in the tasktray it only showed Connecting to… and stopped working after 60 seconds. The VPN connection status did […] The post Windows 10 LT2P/IPSec VPN connection fails silently…
This was one of those network bugs which took some time to fix. To give you a short background: In the last weeks we had random time NTP drifts in our Linux infrastructure, nothing serious but it was odd as they disappeared after restarting the ntpd or chrony service. During […] The post w32tm: “No valid response has been received…
It’s been 4 years since Microsoft acquired Yammer, and we easily remember how being acquired was our springboard into a bustle of structural adaptations. An acquisition by such a large company alone presents all kinds of new and exciting challenges. Not to mention, Yammer is a pretty unique product under the Microsoft umbrella; we’re a Linux shop. Microsoft-owned datacenters are,…
Due to some internal network problems I fired up Wireshark and saw a lot of gratuitous ARP requests/broadcasts. I had never seen the sending MAC or IP before but could assign it to one the ports our switching hardware. The designated port was used for a Citrix XenServer virtualization environment, […] The post Fixing gratuitous ARP requests appeared first on…
Hin und wieder kann es vorkommen, dass der pop3proxy der Sophos UTM (ehemals Astaro) die eingehenden E-Mails “verschluckt”. Grund dafür ist der Spamassassin, der im Hintergrund läuft und bei bestimmten E-Mails eine extrem hohe Prozessorlast verursacht. Das Verhalten habe ich jetzt einige Male bei E-Mails beobachtet, die über die Bugtraq-Mailingliste […] The post How-To: Mail-Queue in Sophos UTM pop3proxy flushen/löschen…
// type to search
