worldwalker2000 552a048a33 make maximum split the grad like torch when equal (#738) ...

* make maximum split grad

* added test for maximum split grad when equal

* minor expr simplification

* (2-eq)/2 only once

* update test bc one more sum output child stays

2023-04-14 00:17:46 -07:00

..

codegen

acc function not needed

2023-03-29 08:03:46 +04:00

nn

fix binop, other tests failure (#723)

2023-03-22 18:15:07 -07:00

runtime

better cacheline test

2023-03-30 06:08:54 +04:00

shape

linearizer! (#714)

2023-03-19 23:43:49 -07:00

graph.py

print gflops avg with DEBUG=2

2023-03-23 16:07:08 -07:00

helpers.py

add Pad onnx operator and rework _padding (#740)

2023-04-06 17:07:36 +05:30

jit.py

fix lint, installed pre-commit on now computer

2023-03-24 11:15:59 -07:00

lazy.py

Do not specify errors when trying to load devices. (#741)

2023-04-06 17:05:36 +05:30

mlops.py

make maximum split the grad like torch when equal (#738)

2023-04-14 00:17:46 -07:00

ops.py

good changes from the M1 Tensor Core project (#730)

2023-03-29 05:11:02 +04:00

tensor.py

Added activation ops + tests (#729)

2023-03-28 13:17:53 +04:00