George HotzandGitHub 05613c8cac use shape str for tensor cores upcast/reduce [pr] (#11168) ...

* use shape str for tensor cores upcast/reduce [pr]

* reduce axis count isn't fixed

2025-07-10 13:10:58 -07:00

..

apps

add a test for 1B llm (#11124)

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

codegen

hotfix: if no ranges, return None

2025-06-30 18:07:56 -07:00

engine

move cpu_profile and shared ProfileEvents from device.py to helpers [pr] (#11126)

2025-07-08 12:14:03 +03:00

frontend

onnx parser (#10435)

2025-06-09 12:44:28 -04:00

kernelize

[pr] Unify CONTIGUOUS and GBARRIER (#11121)

2025-07-08 10:27:23 -07:00

nn

outerworld range test [pr] (#11059)

2025-07-02 14:28:44 -07:00

opt

use shape str for tensor cores upcast/reduce [pr] (#11168)

2025-07-10 13:10:58 -07:00

renderer

tc should be in opt (#11148)

2025-07-09 14:12:21 -07:00

runtime

nv: relative lv addressing in NVPageTableEntry (#11164)

2025-07-10 22:35:50 +03:00

shape

Fix division by zero and mask bug in add views (#11088)

2025-07-07 10:05:47 -07:00

uop

viz: profile RewriteSteps in TINY device (#11125)

2025-07-10 17:45:57 +03:00

viz

viz: profile RewriteSteps in TINY device (#11125)

2025-07-10 17:45:57 +03:00

__init__.py

move files into uop dir (#10399)

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

device.py

move cpu_profile and shared ProfileEvents from device.py to helpers [pr] (#11126)

2025-07-08 12:14:03 +03:00

dtype.py

Add DType.min and DType.max properties (#10749)

2025-06-10 08:31:34 -07:00

gradient.py

more robust reduce_gradient (#10965)

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

helpers.py

tc should be in opt (#11148)

2025-07-09 14:12:21 -07:00

py.typed

add a single py.typed (#6083)

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

tensor.py

Tensor.diagonal (#11122)

2025-07-07 16:21:26 -04:00