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

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

SiliconThe Innovative HP Computer Behind a Hedge Fund Pioneer The Chip Letter

ToolsOne compute platform for end-to-end training at Markov Robotics Modal

VoicesMoving Beyond RAG with Precomputed Context Software Engineering Daily
