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.

轉發到社區

熱門用戶

465.9K 粉絲

4.2M 粉絲

2M 粉絲

101.4K 粉絲

37.4K 粉絲

257.8K 粉絲

547.2K 粉絲

182.1K 粉絲

28.3K 粉絲

135.1K 粉絲

574.2K 粉絲

26.4M 粉絲

110.4K 粉絲

11K 粉絲

348.8K 粉絲