New to Axelera AI? Here's a great way to get up to speed: Getting Started with Voyager® SDK – A Quick Intro Build edge AI apps effortlessly: Setup dev environment Run inference on camera streams Tips from the Model Zoo & SDK pros Check it out now & start deploying!
AI HARDWARE
-
21st Century Tech Revolution: Which Innovation Excites You Most?
By
–
Quel est la révolution technologique du 21 eme siècle qui vous enthousiasme le plus ? . La sélection des bébés selon leur QI . Les robots humanoïdes intelligents . Les implants cérébraux @neuralink . L’utérus artificiel Pour quelle raison ?
-
GPU Count Power of Two for Task Distribution Optimization
By
–
It actually does matter here — number of GPUs in a system is almost always a power of two, and to maximize your utilization you will want that to evenly divide into the number of tasks.
-
NVIDIA Grace Blackwell Systems Launch at VivaTech 2025
By
–
GTC Highlights: Lighting Up Europe
— NVIDIA (@nvidia) 1 juillet 2025
GTC Paris at VivaTech 2025 spotlighted how NVIDIA and partners are building the future of AI—from sovereign infrastructure to agentic systems.
Jensen Huang’s keynote introduced major advances like Grace Blackwell systems in full production and… pic.twitter.com/Y9294Q3druGTC Highlights: Lighting Up Europe GTC Paris at VivaTech 2025 spotlighted how NVIDIA and partners are building the future of AI—from sovereign infrastructure to agentic systems. Jensen Huang’s keynote introduced major advances like Grace Blackwell systems in full production and
-
Emerald AI Optimizes Data Center Power During Peak Grid Demand
By
–
Emerald AI, an #NVIDIAInception startup, is developing software to control power used in data centers during times of peak grid demand. This can help reduce grid stress while meeting the performance requirements of AI workloads. Read our blog to learn more:
-
Voice-Controlled PR Creation on Smartwatch During Activities
By
–
How long until I can trigger cursor to make a PR using a voice assistant on my smart watch during a run? I have my best ideas while walking or running, and genuinely would love to just review how they turned out when I get home.
-
GR00T N1.5: NVIDIA’s VLA Model Teaching Robots Like Toddlers
By
–
📢GR00T N1.5 Explained: NVIDIA’s VLA Model for Humanoids
— Satya Mallick (@LearnOpenCV) 30 juin 2025
🧠 Imagine teaching a robot like you’d teach a toddler, show, guide, repeat. Only this time, it’s not just blocks, it’s fruit, microwaves, tools… the whole world.
Now, with NVIDIA’s GR00T N1.5, robots can start learning… pic.twitter.com/FiQRuPapGoGR00T N1.5 Explained: NVIDIA’s VLA Model for Humanoids Imagine teaching a robot like you’d teach a toddler, show, guide, repeat. Only this time, it’s not just blocks, it’s fruit, microwaves, tools… the whole world.
Now, with NVIDIA’s GR00T N1.5, robots can start learning -
Scira and Groq: How Accessible AI Saves Startups
By
–
Scira grew fast, but it wasn't built to scale affordably. Running large models like Anthropic was burning over $1,000/month. Every search chipped away at Zaid's savings.
He nearly pulled the plug. Then @GroqInc stepped in with compute that could finally keep up. -
NVIDIA Edge AI Solution Drives Innovation Forward
By
–
Congratulations! Proud to see our NVIDIA Edge AI solution driving innovation at the edge
-
Draft Model Pruning Achieves 43% Fewer MACs with Strong Performance
By
–
The results: – 1.59× higher Mean Accepted Length (MAL) than layer-pruned draft models
– 43.87% fewer MACs (Multiply-Accumulate operations) than dense draft models
– Only 8.36% reduction in MAL vs. dense models — a strong tradeoff for efficiency