Sakana AI
· Frontier Labs
Sparser, Faster, Lighter Transformer Language Models
How do we make LLMs faster and lighter? Don’t force the GPU to adapt to sparsity. Reshape the sparsity to fit the GPU! ⚡️ Excited to share our new #ICML2026 paper in collaboration with NVIDIA: “Sparser, Faster, Lighter Transformer Language Models”. This work introduces new open-source GPU kernels and data forma