ThunderKid
Software / AppMentioned in 1 video
A CUDA library developed by the speakers that breaks down compute operations into matrix multiplications, aiming for efficient hardware-model co-design on modern GPUs.
A CUDA library developed by the speakers that breaks down compute operations into matrix multiplications, aiming for efficient hardware-model co-design on modern GPUs.
![2024 in Post-Transformer Architectures: State Space Models, RWKV [Latent Space LIVE! @ NeurIPS 2024]](https://i.ytimg.com/vi/LPe6iC73lrc/maxresdefault.jpg)