AI Briefing#cache-dit
The latest AI and developer news about #cache-dit, with the original source and a short summary.
The latest AI and developer news about #cache-dit, with the original source and a short summary.
The SGLang Diffusion team accelerated the MiniMax-H3 video generation model by up to 6.24x on eight NVIDIA H200 GPUs using Cache-DiT and SubBlock sparse attention.