Contents

14 modules · 5 parts · ~221 min

ML Software & Compilers

Fourteen modules on the stack between model code and the GPU. Why eager execution won and what it costs per op, how torch.compile captures Python at runtime, what Inductor and Triton actually generate, how the caching allocator and CUDA Graphs attack the two runtime overheads, and the three places where none of it works cleanly yet: dynamic shapes, MoE routing, and top-k.

Part JThe fault line

Why the stack looks like this.

Part KCapture

From Python bytecode to kernels.

Part LRuntime

Memory and launch.

Part MWhere it breaks

Dynamism the compiler cannot see.

Part NSynthesis

Choosing, and serving.