qazalandGitHub 32e1c267ee viz: SQTT timeline with our decoder (#14139) ...

* viz: sqtt OCC/INST timeline in our decoder

* todo

* lint

* work

* cleaner

* profiling

* better timing

* keep the generic api

* more generic

* 80x -> 20x off the C decoder

* unusably slow

* rm filters

* work

* work

* other way to sort ops

* work

* first 10k

* 100K actually tells a story

* barrier INST packets get their own red color and row

* minor detail

* 50K

* soft_err

2026-01-15 20:45:16 +09:00

..

apps

test fixups / speedups / var_vals refactor (#13812)

2025-12-23 12:05:59 -05:00

codegen

codegen/custom_kernel: do not attach KernelInfo to user program (#14160)

2026-01-15 14:01:48 +09:00

engine

more fa multi fix (#14152)

2026-01-14 13:57:11 -08:00

mixin

clean up rearrange (#13851)

2025-12-27 11:06:10 -05:00

nn

more onnx ops (#14104)

2026-01-12 09:11:13 -05:00

renderer

remove ctypes.Structure (#13651)

2026-01-15 05:06:22 -05:00

runtime

remove ctypes.Structure (#13651)

2026-01-15 05:06:22 -05:00

schedule

clean up comments that mentioned outdated terms (#14026)

2026-01-05 09:42:58 -05:00

uop

scheduler: sched_cache bugfix for different Tensor.custom_kernel schedules (#14161)

2026-01-15 14:59:14 +09:00

viz

viz: SQTT timeline with our decoder (#14139)

2026-01-15 20:45:16 +09:00

__init__.py

move files into uop dir (#10399)

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

device.py

support bfloat16 for CL (#14073)

2026-01-08 14:14:29 -05:00

dtype.py

use bitsize on dtype (#14011)

2026-01-04 12:16:21 -08:00

gradient.py

fix typing in compute_gradient (#13852)

2025-12-28 11:52:14 -05:00

helpers.py

remove ctypes.Structure (#13651)

2026-01-15 05:06:22 -05:00

py.typed

add a single py.typed (#6083)

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

tensor.py

disable fast_idiv on metal (#14137)

2026-01-13 21:40:40 -05:00