cuda 7
- Types Without Places, Places Without Types
- Hacking by Breaking: Five Strategies to Reverse Engineer Opaque Compilers
- The World Would Be a Better Place Had Compiler Engineers Stepped Up
- Triton: The Compiler That Pretends to Be a Library
- Anatomy of a CUDA Binary
- Crossing the Boundary: Custom Kernels and the C++/Python ABI in vLLM
- Building vLLM from Source: A Field Guide (with all the pitfalls)