cuda 4 Triton: The Compiler That Pretends to Be a Library Jul 19, 2026 Anatomy of a CUDA Binary Jul 14, 2026 Crossing the Boundary: Custom Kernels and the C++/Python ABI in vLLM Jun 22, 2026 Building vLLM from Source: A Field Guide (with all the pitfalls) Jun 19, 2026