add Tensor.max_unpool2d (#9518)

* why does max_unpool2d feel slower than out.gradient ...

* slightly cleaner

* what happened to ruff

* need to think about this some more

* slightly faster now?

* clean up, 1 more failing edge case

* ok good

* working TINY_BACKEND

* nit doc wording

* retry CI
This commit is contained in:
geohotstan
2025-03-23 00:11:33 +08:00
committed by GitHub
parent bdd44d4255
commit 309afa20b7
7 changed files with 73 additions and 12 deletions

View File

@@ -22,6 +22,7 @@
::: tinygrad.Tensor.avg_pool2d
::: tinygrad.Tensor.max_pool2d
::: tinygrad.Tensor.max_unpool2d
::: tinygrad.Tensor.conv2d
::: tinygrad.Tensor.conv_transpose2d
::: tinygrad.Tensor.dot