Hosted on MSN2d
DeepSeek's AI breakthrough bypasses Nvidia's industry-standard CUDA, uses assembly-like PTX programming instead
D eepSeek made quite a splash in the AI industry by training its Mixture-of-Experts (MoE) language model with 671 billion ...
Hosted on MSN10mon
Nvidia software exec Kari Briski on NIM, CUDA, and dogfooding AI
Interview Nvidia's GPU Technology Conference concluded last week, bringing word of the company's Blackwell chips and the much-ballyhooed wonders of AI ... we called it CUDA-X, because you had ...
CRN3y
Nvidia Reveals Arm-Based Data Center CPU To Take On Intel, AMD
Nvidia has revealed an Arm-based data center CPU for AI and high-performance ... support by Nvidia’s HPC software development kit and its full suite of CUDA and CUDA-X libraries, according ...
Seeking Alpha25d
Nvidia: Expect Shares To Soar Higher On 2025's AI Spending Frenzy
At the same time, Nvidia’s hardware innovations are complemented by the company's proprietary CUDA platform, which has become the industry standard for AI and HPC applications. This ecosystem of ...
GIGAZINE1mon
What did we find out by comparing the performance of the chips 'H100', 'H200' and 'MI300X' used in AI training?
In the market for AI infrastructure used for AI learning and inference, NVIDIA's AI-specialized chips such as 'H100' and 'H200' have a large share. Meanwhile, AMD, a rival of NVIDIA, also ...