chenyuandGitHub 73002ebffa print p.applied_opts with DEBUG >= 3 (#13024)

2025-10-30 16:51:21 -04:00

..

apps

clean up the LLM tokenizer (#12653)

2025-10-14 14:22:01 +08:00

codegen

fp8 amd cstyle (#12999)

2025-10-30 10:45:52 -04:00

engine

print p.applied_opts with DEBUG >= 3 (#13024)

2025-10-30 16:51:21 -04:00

nn

Onnx Layer/Group/RMS/Batch-Norm ReduceL2 fp32 intermediates for fp16 (#12109)

2025-10-24 12:26:11 +02:00

renderer

remove unneeded TYPE_CHECKING [pr] (#13020)

2025-10-30 12:01:13 -04:00

runtime

amd: sqtt works in profile mode (#13019)

2025-10-30 23:48:52 +08:00

schedule

ues less typing.cast [pr] (#13002)

2025-10-30 09:29:52 -04:00

uop

New symbolic renderer + strip parens (#13017)

2025-10-30 16:41:32 +01:00

viz

uops programs (#13005)

2025-10-30 12:28:10 +08:00

__init__.py

move files into uop dir (#10399)

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

device.py

fp8 amd cstyle (#12999)

2025-10-30 10:45:52 -04:00

dtype.py

fix fp8 cast folding (#12997)

2025-10-29 09:27:42 -04:00

gradient.py

rename RECIP to RECIPROCAL (#12939)

2025-10-27 16:53:13 +08:00

helpers.py

delete untested quantize (#12990)

2025-10-29 12:46:32 +08:00

py.typed

add a single py.typed (#6083)

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

tensor.py

add unique to const, fix longstanding bug (#12965)

2025-10-28 15:11:37 +08:00