Together AITools
To Infinity and Beyond: ThunderKittens Now on NVIDIA Vera Rubin NVL72!

We ported ThunderKittens to NVIDIA's Vera Rubin NVL72 and rebuilt our NVFP4 GEMM around the new hardware, taking it from 42% of roofline to over 22 PFLOPS — competitive with cuBLAS and CuTe DSL.
Read at Together AI ↗Related

ToolsIntroducing preemptible compute: the same compute, half the price Together AI

ToolsTogether AI and Y Combinator partner to launch the first dedicated GPU cluster for the YC community Together AI

SiliconHPE Sees No Customer Pushback On Rising Datacenter Equipment Costs The Next Platform

VoicesSED News: The NVIDIA-Hugging Face Deal, China’s Proxy Economy, the Open Weight Surge Software Engineering Daily

SiliconInside Arm CSS for Mobile 2: The AI-native compute platform for mobile Arm Newsroom
