3 people 4e8370309c Support onnx If OP (#11648) ...

* start

* tiny clean up

* whoops, didn't mean to accidentally fix this

* fix .to(device), kinda hacky and this fix makes it slower?

* merge properly

* FINALLY figured out slowness, also hack pylint for now

* add DEBUGONNX print for subgraph

* oops

* WOOOOOOOO SHAPE CACHE 50% SPEED INCREASE

* small fix, but maybe all deterministic Tensor creation in fp should be cached

* cache condition

* sliiiightly cleaner

* better abstraction?

* remove sam from model_benchmark

* remove shape cache speed up for now

* less lines

* isinstance fix

---------

Co-authored-by: chenyu <[email protected]>

2025-08-28 10:17:35 -04:00

..

apps

BPE tokenizer (#11415)

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

codegen

support for tuple ranges (#11890)

2025-08-28 07:02:31 -07:00

engine

memplan: fix large buffers planning (#11878)

2025-08-27 23:54:27 +03:00

frontend

Support onnx If OP (#11648)

2025-08-28 10:17:35 -04:00

nn

Add mxfp4 support (#11873)

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

renderer

support for tuple ranges (#11890)

2025-08-28 07:02:31 -07:00

runtime

memory: tiny tlsf cleanup (#11887)

2025-08-28 14:07:18 +03:00

schedule

postrange boilerplate work (#11881)

2025-08-27 15:22:59 -07:00

shape

add AxisType to range (#11798)

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

uop

support for tuple ranges (#11890)

2025-08-28 07:02:31 -07:00

viz

support for tuple ranges (#11890)

2025-08-28 07:02:31 -07:00

__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

FUSE_ATTENTION (#11884)

2025-08-27 19:59:17 -04:00

py.typed

add a single py.typed (#6083)

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

tensor.py

FUSE_ATTENTION (#11884)

2025-08-27 19:59:17 -04:00