gnovack f7aadae5e5 add pad-aware reduce path (#48385) ...

Signed-off-by: gnovack <novackgm@gmail.com>

2026-07-14 18:05:50 -07:00

..

kernels

[Perf] Remove redundant repeat and copy for dsv4, 1.8% E2E TPOT improvement. (#48137)

2026-07-15 00:48:10 +00:00

layers

add pad-aware reduce path (#48385)

2026-07-14 18:05:50 -07:00

model_loader

[Bugfix] Preserve unloaded non-persistent buffers during layerwise reload (#44371)

2026-07-14 17:46:29 -07:00

models

[CI Bug] Fully solve accuracy issue for DSv3.2 + MTP + Sequence Parallel (#48036)

2026-07-14 10:00:24 -04:00

offloader

Revert "[Platform] Replace torch.cuda.Event with torch.Event (#47140)" (#47668)

2026-07-06 14:18:33 +01:00

warmup

[Perf][Feat] Add generic cuteDSL LL BF16 router (GEMM) (#42562)

2026-07-13 23:01:21 -07:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

2026-01-04 18:34:04 -08:00

custom_op.py

Add ability to replace oot ops when using lora (#37181)

2026-03-16 18:04:15 -07:00

parameter.py

Speed up docs build (#44635)

2026-06-05 14:51:44 +00:00

utils.py

Remove more unnecessary load_weights methods (#47058)

2026-06-30 15:22:16 +01:00