Reactions from ranked influencers
7 posts
what the hell no way
10x more tokens per megawatt. CoreWeave has the first measured performance of NVIDIA Vera Rubin NVL72, showing 10x improvement in tokens per second per megawatt on DeepSeek-R1 compared to Blackwell. https://twitter.com/CoreWeave/status/2079587123196280921
10x more tokens per megawatt. CoreWeave has the first measured performance of NVIDIA Vera Rubin NVL72, showing 10x improvement in tokens per second per megawatt on DeepSeek-R1 compared to Blackwell.
The first-ever measured silicon numbers for @NVIDIA Vera Rubin NVL72 are in 😲 First measured performance shows 10x more tokens per megawatt than Blackwell. No projections. Real results from live hardware.
🤯
10x more tokens per megawatt. CoreWeave has the first measured performance of NVIDIA Vera Rubin NVL72, showing 10x improvement in tokens per second per megawatt on DeepSeek-R1 compared to Blackwell. https://twitter.com/CoreWeave/status/2079587123196280921
Again, I expected more.
The underrated thing is that they're running R1 at ≈150 tps, about 7 times faster than it was served by DeepSeek proper. And for Rubin, this is a healthy regime, not desperate at all, 60% of peak throughput. Almost 1 t/s/watt. V4 does roughly this, but with DSpark and 2x slower.
The first-ever measured silicon numbers for @NVIDIA Vera Rubin NVL72 are in 😲 First measured performance shows 10x more tokens per megawatt than Blackwell. No projections. Real results from live hardware.
https://x.com/CoreWeave/status/2079587123196280921/video/1 https://x.com/CoreWeave/status/2079587123196280921/video/1
10x more tokens per megawatt. CoreWeave has the first measured performance of NVIDIA Vera Rubin NVL72, showing 10x improvement in tokens per second per megawatt on DeepSeek-R1 compared to Blackwell. https://twitter.com/CoreWeave/status/2079587123196280921