George HotzandGitHub dd575da7ee real minimum cstyle change (#6709) ...

* real minimum cstyle change

* make it match

* bring back DEFINE_GLOBAL store marking writable

* bump line count to 9800

* closer

* precompute don't render

* cast/bitcast too

* smem_align

* vectorize

* more pr match

* remove that test

* less PR diff

2024-09-25 12:40:46 +08:00

..

codegen

split validhack into simplify idx and drop valids (#6719)

2024-09-24 09:40:27 -04:00

engine

hotfix: support JIT_BATCH_SIZE=0, make that the default

2024-09-25 10:36:04 +08:00

nn

minor resnet cleanups (#6382)

2024-09-06 12:50:21 +08:00

renderer

real minimum cstyle change (#6709)

2024-09-25 12:40:46 +08:00

runtime

qcom do not recreate memoryviews on updates (#6701)

2024-09-24 15:36:22 +08:00

shape

use UOp.define_var in Variable shape [run_process_replay] (#6626)

2024-09-20 17:58:29 +08:00

__init__.py

hotfix: add TYPED=1 support

2024-09-15 14:44:26 +08:00

device.py

qcom image copyout (#6667)

2024-09-23 16:11:43 +08:00

dtype.py

put local on the PtrDtype [run_process_replay] (#6656)

2024-09-23 10:29:17 +08:00

function.py

math trait [run_process_replay] (#6364)

2024-09-05 16:19:17 +08:00

helpers.py

feat: use /raid/downloads on tinybox (#6702)

2024-09-24 15:26:31 +08:00

lazy.py

remove e( function just alu( [run_process_replay] (#6589)

2024-09-19 10:24:02 +08:00

multi.py

remove e( function just alu( [run_process_replay] (#6589)

2024-09-19 10:24:02 +08:00

ops.py

viz more touchups (#6685)

2024-09-23 19:44:28 +08:00

py.typed

add a single py.typed (#6083)

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

tensor.py

advanced setitem (#6262)

2024-09-24 22:14:59 -04:00