Slow the madness, tariffs are officially paused for 90 days. except for China that now has 125% tariffs.
COMPUTING
-
Llama 4 Maverick fastest inference 655 tokens per second
By
–
I feel the need, the need for speed! Llama 4 Maverick from @AIatMeta is now available on SambaNova Cloud & it's the fastest inference verified by @ArtificialAnlys at 655 t/s. $0.50 / million input tokens & $2.00 per million output tokens. On SambaNova Cloud
-
Metis M.2 Powers Offline AI Chatbot on Arduino Portenta X8
By
–
Metis M.2 Meets Arduino Portenta X8 Check out the power of @AxeleraAI
’s Metis PCIe on the @arduino Portenta X8 at #ArduinoDay! Fully offline AI chatbot demo—no cloud needed. Now in Early Access: https://
eu1.hubs.ly/H0j8JM40 #EdgeAI #AIinference #Metis #Arduino #OfflineAI -
Understanding GPU Architecture Fundamentals for AI Systems
By
–
Fundamentals of GPU Architecture https://
buff.ly/Zc6p5ks
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Google Cloud team celebrates major success with partners
By
–
Great day for Google, the Cloud team, and our partners!
-
Google Introduces Ironwood TPU for Inference Era
By
–
Introducing Ironwood, the first TPU built for the age of inference, and the timing could not be better : ) – Ironwood perf/watt is 2x relative to Trillium, 6th gen TPU
– Ironwood offers 192 GB per chip, 6x that of Trillium
– 4.5x faster data access -
Exponential AI Demand Requires Investment Across Full Stack
By
–
The demand for AI is on an exponential, we need to continue investing at every layer of the stack if we are going to be able to service the demand for AI compute efficiently and at humanity scale. TPU's are so wonderful : )
-
World Models Revolutionizing Autonomous Driving Technology
By
–
World models in autonomous driving FTW !
-
Jensen’s Quantum Panel: Exploring Abstract Quantum Computing at GTC
By
–
I attended Jensen’s Quantum panel with 14 leaders in the field at GTC, and it was the “coolest” one. With all my time spent in AI, quantum has always felt a bit abstract and hyped. Yep, even for someone in “AI” (with everything from generative AI to agentic AI, and whatever in