George HotzandGitHub cac8bcf8b5 use Ops.REDUCE (#9721) ...

* decrease bert python time [pr]

* order copies

* Revert "order copies"

This reverts commit 3f62c8693b.

* rewrite count

* Ops.REDUCE

* acc first in the add chain

* Fix tensor core acc

* arange patterns look good

* fix multireduce gate

* reduce rewrite rule

* bump that to 15 minutes

* multiwmma isn't fusing

* gep through wmma is gep pushing

* bump that timeout too, it's all env setup

* add failing test

2025-04-04 10:14:34 +08:00

..

codegen

use Ops.REDUCE (#9721)

2025-04-04 10:14:34 +08:00

engine

use Ops.REDUCE (#9721)

2025-04-04 10:14:34 +08:00

frontend

add onnx frontend stub [pr] (#9558)

2025-03-24 12:24:34 +08:00

nn

nn.state docs cleanup (#8332)

2025-03-18 17:16:40 -04:00

renderer

add bf16 mfma support (#9695)

2025-04-02 21:44:49 +08:00

runtime

use Ops.REDUCE (#9721)

2025-04-04 10:14:34 +08:00

shape

use functools.cache instead of lru_cache(None) [pr] (#9714)

2025-04-03 11:47:13 +08:00

viz

use functools.cache instead of lru_cache(None) [pr] (#9714)

2025-04-03 11:47:13 +08:00

__init__.py

UOp.variable (#7010)

2024-10-12 18:20:44 +08:00

device.py

use functools.cache instead of lru_cache(None) [pr] (#9714)

2025-04-03 11:47:13 +08:00

dtype.py

cleanup truncate_bf16 [pr] (#9725)

2025-04-03 05:43:49 -04:00

gradient.py

add gc tests [pr] (#9718)

2025-04-03 14:08:32 +08:00

helpers.py

use functools.cache instead of lru_cache(None) [pr] (#9714)

2025-04-03 11:47:13 +08:00

ops.py

use Ops.REDUCE (#9721)

2025-04-04 10:14:34 +08:00

py.typed

add a single py.typed (#6083)

2024-08-14 17:31:46 -07:00

spec.py

print idx when OUT OF BOUNDS ACCESS (#9646)

2025-03-31 06:12:44 -04:00

tensor.py

delete Ops.EMPTY and Tensor._metaop (#9715)

2025-04-03 12:29:02 +08:00