geohotstan 0b7c44677d Fix uint8 cast underflow (#6305) ...

* hacky fix for cast

* only float to uint8

* limit to float -> uint8

* touchup alu cast test

* improve tests and support more float to unsigned casts

* del one repeated test

* del 1 more repeated test

* try removing expected failure test

* hmmm try 1 more

* skip tests for flakiness

* uint64 super flaky

* clean up

* grammar

* just match numpy

* why is CI numpy different from local numpy

* increase verbosity

* try

* try2

* try3

* try4

* yeah idk

* new direction

* try again

* just don't support uint32 and uint64

* done?

* oops

* comment

* documentation

* it is what it is

---------

Co-authored-by: chenyu <chenyu@fastmail.com>

2024-12-06 10:25:03 -05:00

..

codegen

Cleaner rule for mul/idiv by power of two [pr] (#8076)

2024-12-06 08:02:24 -05:00

engine

move view_supported_devices to device [pr] (#8085)

2024-12-06 16:44:15 +02:00

nn

refactor safe_load (#8035)

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

renderer

Use atomicLoad builtin when loading atomic type (#8084)

2024-12-06 15:33:11 +01:00

runtime

qcom has not transfer (#8075)

2024-12-06 14:45:01 +03:00

shape

clean up reshape size check [pr] (#8067)

2024-12-06 07:51:19 -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

move view_supported_devices to device [pr] (#8085)

2024-12-06 16:44:15 +02:00

dtype.py

mypy==1.13.0 (#7990)

2024-12-06 12:09:14 +08:00

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

improve idiv _min_max (#8066)

2024-12-05 23:02:16 -05:00

py.typed

add a single py.typed (#6083)

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

tensor.py

Fix uint8 cast underflow (#6305)

2024-12-06 10:25:03 -05:00