George HotzandGitHub a77d792aff Codegen gpu cleanups (#640) ...

* cleanups

* fixups

* handle pre upcasted global buffers

* early is just required

* delete junk from hand coded opt

* implicit upcast_in_mid_reduce

* speedup

* fix exec w validhacks

* reorder opt

* only need to check the output for that

* return total runtime from kernels if debugging

2023-03-04 15:31:51 -08:00

..

gemm

Refactor ASTs (#622)

2023-03-01 18:57:29 -08:00

triton

A Triton backend for tinygrad (#470)

2023-02-01 11:53:57 -08:00

augment.py

[Fix] fix typo: test_mnist -> datasets (#492)

2023-01-29 21:30:47 -08:00

gradcheck.py

Remove Tensor.data (#565)

2023-02-18 16:36:12 -08:00

helpers.py

lines from helpers

2023-03-03 23:07:46 -08:00

introspection.py

Refactor ASTs (#622)

2023-03-01 18:57:29 -08:00

kernel_search.py

Refactor ASTs (#622)

2023-03-01 18:57:29 -08:00

lib_test_ast.py

fix ast test

2023-03-04 07:49:25 -08:00

onnx_ops.py

adding comparison operators (#616)

2023-03-02 08:10:44 -08:00

onnx.py

fine, openpilot can have 197 kernels

2023-02-27 11:48:36 -08:00

thneed.py

Codegen gpu cleanups (#640)

2023-03-04 15:31:51 -08:00

training.py

Remove Tensor.data (#565)

2023-02-18 16:36:12 -08:00

utils.py

Fix windows file permission error (#634)

2023-03-04 09:23:55 -08:00