AMD’s stealthy gambit
AMD has made a significant move in the world of GPU software development by introducing a solution that bridges the gap between its ROCm technology and NVIDIA’s CUDA binaries.
AMD GPUs easier for Llama-2
AI startup Lamini uses AMD GPUs instead of the more popular Nvidia GPUs to run large language models (LLMs) like Llama-2 for customers.
Life is like that
Leaked versions of Nvidia’s RTX 4090 graphics card have disappointed some Nvidia fanboys who expected more from the company named after a Roman vengence daemon.
Sheep and goats together
Graphics start-up Otoy has claimed it has developed a means of running software written for Nvidia's Compute Unified Device Architecture (CUDA) platform on unmodified on rival graphics cards and CPUs from AMD.
Updated to 16-bit floating point arithmetic
Nvidia has sexed up its CUDA (Compute Unified Device Architecture) parallel programming platform and application programming interface.
Unified memory for CUDA
To get developers ready for Logan
GT 520 and 510 become GT 620 and 605
Meet the new SMX units
GPU set at 1006MHz