Start Here: The Plan
What an inference engine is, a map of the code, setup and a short C primer.
0 of 3 complete
- ▶ Up next12 min+50 XPWhat we are building: an inference engine you can readStart here. What an inference engine is, the pieces we build (forward pass, weight loading, KV cache, quantised…
- 10 min+50 XPThe plan and the map of the codeThe route through the course with times and checkpoints, a file-by-file map of the engine code, how the pieces call…
- 20 min+50 XPSet up, and a short C primer for the one benchmarkPython and a C compiler, a project folder, a first C program that measures memory bandwidth, and the dozen C ideas…