Summary
nvidia announces new gpu releases, including vera rubin and blackwell ultra, during the gtc 2025 conference. vera rubin delivers substantial performance uplifts compared to its predecessor, grace blackwell, particularly on ai inferencing and training tasks.
Key Points
vera rubin features tens of gigabytes of memory and a custom nvidia-designed cpu called vera
vera rubin can manage up to 50 petaflops while doing inference (i.e., running ai models), more than double the 20 petaflops for nvidia's current blackwell chips
rubin will be followed by rubin ultra in the second half of 2027, a collection of four gpus in a single package delivering up to 100 petaflops of performance
Why It Matters
nvidia's new gpu releases have significant implications for ai and machine learning applications, enabling faster processing times and improved performance
Author
Kyle Wiggers