Notes Overview

check notes

• Graph-level (e.g., operator fusion, kernel scheduling, memory planning)
• Kernel-level (e.g., CUDA, Triton, custom operators for specialized hardware)
• System-level (e.g., distributed training across GPUs/TPUs, inference serving at scale)

Projects

• Pytorch Compiler (TorchFX, TorchInductor, IR Graph, Functorch)
• CUDA programming
• Triton
• LeetGPU
• CUDA Graphs
• NVFuser
• Modular (mojo)