- What is the KV cache?
- Overview of torch.compiler
- Torch Dynamo Overview
- Torch Dynamo Deep-Dive
- Torch Compiler Troubleshouting
- Deep Dive into Triton Internals (3 Parts)
- HF Ultra-Scale Playbook (fused kernels section)
- Liger Kernels repo
- Liger Kernels paper
- FlashAttention
- FlassAttention2
- FlassAttention3
- Flex Attention Tutorial