mirror of
https://github.com/tinygrad/tinygrad.git
synced 2026-01-23 05:48:08 -05:00
817b64f5e5
* universal strided conv * more correct * hmm, CPU works * cleaner cl code output * make noconv a flag * cleanup __getitem__ * refactor broadcasting * put that back * unneeded reshape in getitem * fix strided for torch
This is where we scope out adding accelerators to tinygrad ane -- Apple Neural Engine, in the M1 + newer iPhones cherry -- Largely defunct custom hardware based on a RISC-V extension tpu -- Google's TPU, available for rent in Google Cloud