โ‰ˆ the.bay.news

Vera Rubin NVL72 inference tests show up to 7x better token throughput per MW vs. Blackwell on a 1.6T DeepSeek model, above Huang's 3x claim for 1T-3T LLMs (Bryan Shan/SemiAnalysis)

Techmeme
Vera Rubin NVL72 inference tests show up to 7x better token throughput per MW vs. Blackwell on a 1.6T DeepSeek model, above Huang's 3x claim for 1T-3T LLMs (Bryan Shan/SemiAnalysis)
By Bryan Shan / SemiAnalysis. View the full context on Techmeme.

0 comments

Sign in to join the discussion โ€” your thebay.events account works here.

No comments yet.