tinygrad/extra/torch_backend
George Hotz d1cce7a476
put the ranges on store instead of after (#15759)
* put the ranges on store instead of after

* better assert

* fix stuff

* comment out slow rules i don't understand

* simpler rule

* closer

* return false for store

* fix loop

* only a few schedule failures remain

* remove stores to self

* all tests pass locally

* remove junk

* regression test and fix

* better test, bump broken torch count

* bugfix with regression test

* new fusion is better
2026-04-16 19:06:40 +08:00
..
.gitignore torch backend works for ResNet-18 (#9200) 2025-02-22 22:16:23 +08:00
backend.py support shift by Tensor (#15623) 2026-04-06 15:14:57 -04:00
backend2.py torch and numpy dtype interop [pr] (#9224) 2025-02-24 18:26:49 +08:00
example.py put the ranges on store instead of after (#15759) 2026-04-16 19:06:40 +08:00
test.py fix TINY_BACKEND=1 cumsum (#14138) 2026-01-14 09:54:49 -05:00
test_compile.py start torch.compile support (#9279) 2025-02-27 10:29:51 +08:00
test_inplace.py remove allow_shape_mismatch in Tensor.replace (#14536) 2026-02-04 12:38:18 -05:00
test_kernel_fusion.py put the ranges on store instead of after (#15759) 2026-04-16 19:06:40 +08:00
test_multigpu.py move frontend dir to nn [pr] (#12470) 2025-10-07 10:42:22 +08:00
torch_tests.py rig up torch's testing framework [pr] (#9254) 2025-02-26 18:46:22 +08:00
wrapped_tensor.cpp remove allow_shape_mismatch in Tensor.replace (#14536) 2026-02-04 12:38:18 -05:00