chenyu 88c338bfcc add kernelize to keccak for each data block (#11370) ...

* add kernelize to keccak for each data block

test_long works now. this prevents internal uops from growing propotional to data length and eventually too deep

* this?

* hash stuff

* gate test

* mv

2025-07-25 16:07:20 -04:00

..

apps

add a test for 1B llm (#11124)

2025-07-07 18:47:25 -07:00

codegen

define reg doesn't have init anymore (#11365)

2025-07-24 19:15:49 -07:00

engine

hcq: graphed copies (#11302)

2025-07-24 17:36:19 +03:00

frontend

OnnxRunner file as input (#10789)

2025-07-12 14:27:46 -04:00

nn

type remove Union and Optional [pr] (#11283)

2025-07-19 14:05:52 -04:00

opt

use AddrSpace instead of local (#11314)

2025-07-21 14:00:06 -07:00

renderer

define reg doesn't have init anymore (#11365)

2025-07-24 19:15:49 -07:00

runtime

hcq: fix race in _at_profile_finalize (#11368)

2025-07-25 14:14:02 +03:00

schedule

rename kernelize to schedule, try 2 (#11305)

2025-07-21 11:18:36 -07:00

shape

type remove Union and Optional [pr] (#11283)

2025-07-19 14:05:52 -04:00

uop

use next instead of full list in UOp._device [pr] (#11369)

2025-07-25 10:04:29 -04:00

viz

viz: generic stuff from gpu counters ui (#11358)

2025-07-24 20:29:24 +03:00

__init__.py

move files into uop dir (#10399)

2025-05-18 11:38:28 -07:00

device.py

support DEV= to specify device (#11351)

2025-07-23 17:40:55 -04:00

dtype.py

generic changes from define_reg_2 (#11315)

2025-07-21 15:14:06 -07:00

gradient.py

more robust reduce_gradient (#10965)

2025-06-24 14:09:33 -07:00

helpers.py

fix word_wrap with newlines in input string [pr] (#11319)

2025-07-22 12:03:13 +03:00

py.typed

add a single py.typed (#6083)

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

tensor.py

add kernelize to keccak for each data block (#11370)

2025-07-25 16:07:20 -04:00