SemiAnalysis(@SemiAnalysis_):BREAKING NEWS🚨: RUBIN NVL72 HITS 862 tok/s/user on GLM5.3 744B on agentic workloads! In less than 8 days, NVIDIA has increased interactivity on Rubin by close to 2x through low-latency specialized kernels.

2026.10.23 01:40

BREAKING NEWS🚨: RUBIN NVL72 HITS 862 tok/s/user on GLM5.3 744B on agentic workloads! In less than 8 days, NVIDIA has increased interactivity on Rubin by close to 2x through low-latency specialized kernels.

커뮤니티로 전달

인기 있는 사용자

4.2M 팬

2M 팬

101.4K 팬

257.8K 팬

37.4K 팬

28.3K 팬

547.2K 팬

182.1K 팬

574.2K 팬

26.4M 팬

2M 팬

10.5M 팬

16.8M 팬

68.8K 팬

266.8K 팬