3 people e9c5b23ba1 Use MTLCompiler directly (v2) (#7920) ...

* Use MTLCompiler directly (v2)

* to_block_literal and REQUEST_TYPE_COMPILE

* Rewrite command encoding

* Revert to_block_literal

* Maybe that's more readable to some people?

* Typo and comment about stdlib caching

* Update ops_metal.py

* Update ops_metal.py

* Update ops_metal.py

---------

Co-authored-by: George Hotz <[email protected]>

2024-12-04 16:36:48 +08:00

..

codegen

local reordering in block (#8029)

2024-12-04 15:11:29 +08:00

engine

lazy srcs shape mistmatch assert + fix ASSIGN [pr] (#8014)

2024-12-03 15:40:37 -05:00

nn

minor nn cleanups (#8018)

2024-12-03 12:34:52 -05:00

renderer

update uop and tests to not use lt/gt/le/ge [pr] (#8023)

2024-12-03 21:02:52 -05:00

runtime

Use MTLCompiler directly (v2) (#7920)

2024-12-04 16:36:48 +08:00

shape

update uop and tests to not use lt/gt/le/ge [pr] (#8023)

2024-12-03 21:02:52 -05:00

viz

replace all sparents with toposort (#7983)

2024-12-02 15:00:30 +08:00

__init__.py

UOp.variable (#7010)

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

device.py

PYTHON device is okay to use everywhere [pr] (#7981)

2024-12-02 12:34:42 +08:00

dtype.py

prepare mypy==1.13.0: legacy cast (#7866)

2024-11-27 10:33:35 -05:00

function.py

update function to not use gt/lt [pr] (#8025)

2024-12-03 22:39:06 -05:00

helpers.py

small helpers cleanups (#7977)

2024-12-01 21:50:47 -05:00

multi.py

least controversial (#7863)

2024-11-23 21:23:30 +08:00

ops.py

local reordering in block (#8029)

2024-12-04 15:11:29 +08:00

py.typed

add a single py.typed (#6083)

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

tensor.py

remove lt/gt/le/ge from SimpleMathTrait [pr] (#8027)

2024-12-04 00:24:33 -05:00