George HotzandGitHub e4afdf9ea1 improve DEBUG=2 string with TB/s and TFLOPS [pr] (#11875)

2025-08-27 11:42:41 -07:00

..

apps

BPE tokenizer (#11415)

2025-08-04 09:52:38 -07:00

codegen

split devectorizing of buf/index (#11855)

2025-08-26 12:05:48 -07:00

engine

improve DEBUG=2 string with TB/s and TFLOPS [pr] (#11875)

2025-08-27 11:42:41 -07:00

frontend

onnx RotaryEmbedding cleanup (#11724)

2025-08-18 23:34:42 -04:00

nn

Add mxfp4 support (#11873)

2025-08-27 10:56:56 -07:00

renderer

new (post) group for reduce (#11837)

2025-08-25 18:03:00 -07:00

runtime

amd: correct handling of relocations (#11863)

2025-08-27 01:26:45 +03:00

schedule

small changes from postopt (#11854)

2025-08-26 11:56:16 -07:00

shape

add AxisType to range (#11798)

2025-08-23 11:15:00 -07:00

uop

add ctx to z3_renderer arg (#11867)

2025-08-27 03:38:15 +02:00

viz

tracing: fix types (#11871)

2025-08-27 15:50:43 +03:00

__init__.py

move files into uop dir (#10399)

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

device.py

viz memory: compute nbytes (#11795)

2025-08-23 17:34:07 +03:00

dtype.py

fix nan in float_to_bf16 (#11843)

2025-08-26 11:42:25 -04:00

gradient.py

named expression for POW and MAX gradient (#11858)

2025-08-26 16:03:03 -04:00

helpers.py

tracing: fix types (#11871)

2025-08-27 15:50:43 +03:00

py.typed

add a single py.typed (#6083)

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

tensor.py

call dtypes.as_const in Tensor(list) (#11840)

2025-08-25 22:08:26 -04:00