Harry MellorandClaude Opus 5 9321aff536 [Bugfix] Wait for the linear bias before layerwise online processing (#49805) ...

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

2026-07-25 17:56:32 +00:00

..

kernels

[XPU] FP8 o_proj with fp8_bmm and load-time scale transpose (#48334)

2026-07-20 16:32:03 +08:00

layers

Revert "[Perf][GLM-5.2] Blackwell decode optimizations" (#49768)

2026-07-24 16:04:59 -07:00

model_loader

[Bugfix] Wait for the linear bias before layerwise online processing (#49805)

2026-07-25 17:56:32 +00:00

models

[Model] Add VaultGemma via Transformers modeling backend (#49803)

2026-07-25 16:54:15 +00:00

offloader

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

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

warmup

[Bugfix] Support non-uniform page sizes in KVBlockZeroer (#49704)

2026-07-24 13:38:59 -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