ThunderKittens: Simple, Fast, and Adorable AI Kernels

GPUs Go Brrr

Learning From DNA: a grand challenge in biology

Long-Context Retrieval Models with Monarch Mixer

How to scale LLMs better with an alternative to transformers

FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

The Safari of Deep Signal Processing: Hyena and Beyond

Batch computing and the coming age of AI systems

From deep to long learning?

ML without labels or gradients: weak supervision with FlyingSquid