How AI inference works, clearly explained
If you're using or building on large language models (LLMs), perhaps the most important concept to understand is how inference and key-value (KV) cache work. That's...
Read moreCategory: General
Modernize with confidence: Build a threat-resistant Linux foundation with Red Hat Consulting
Operating an unsupported or outdated Linux distribution can expose your organization to critical security risks, drive up maintenance costs, and keep you from using the newest...
Read moreModernizing database workloads on Red Hat OpenShift
As organizations continue to modernize their workloads, one of the most important questions is how to support the full range of database workloads, including SQL, NoSQL,...
Read moreTaming the agent beast: From monolithic prompt to modular agentic workflow
What happens when you stop thinking of AI agents as chatbots and start treating them as workers in a pipeline? This is the story of turning...
Read moreSambaNova’s SN50 RDU for AI at Hot Chips 2026
This year's Hot Chips conference includes a presentation from AI accelerator developer SambaNova, who is at the show to discuss their latest-generation RDU, the SN50 The...
Read more
Reject Fluid Simulations, Return To Rheoscopic Fluid
Fluid simulations are one of the “killer apps” of high-performance computing, but if you can’t afford the performance, they can take a depressingly long time to...
Read more
Humankind 2 trailer accused of being 'AI slop,' studio says nope: 'real actors, practical sets, and custom-made props'
The uncanny trailer shows the perspective of infants through space and time.
Read moreMicrosoft’s Maia 200 AI Accelerator at Hot Chips 2026
At Hot Chips 2026, Microsoft is going into new detail on Maia 200, their second-generation server AI inference processor The post Microsoft’s Maia 200 AI Accelerator...
Read more
New Next-Gen Dish Adds Muscle to NASA’s Deep Space Network
NASA’s Deep Space Network facility in California is marking the addition of a brand new 34-meter-wide (114-foot-wide) radio frequency antenna to the agency’s deep space communications...
Read moreMoving from Minimus to Docker Hardened Images
The Minimus registry goes offline on October 22. Here is the migration path, the free help Docker is offering, and where to start.
Read more
The world's busiest spaceport is about to get a lot quieter, at least for now
SpaceX aims to launch Starship from Florida by the end of the year. 2027 seems more likely.
Read more
Garmin’s new Fenix 9 adds brighter screens and smoother map panning
Garmin just took the wraps off its new line of rugged Fenix 9 smartwatches, with the base model featuring an OLED display with a brightness of...
Read more