Martin Hickey b2fb83e7ff [Attention]: Use KVCacheSpec for AttentionMetadataBuilder type hints (#50148) ...

Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>

2026-07-31 11:20:18 +00:00

..

kernels

[XPU] Fix FP8 block scale layout for MLA compatibility (#50349)

2026-07-31 11:05:35 +08:00

layers

[Attention]: Use KVCacheSpec for AttentionMetadataBuilder type hints (#50148)

2026-07-31 11:20:18 +00:00

model_loader

[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)

2026-07-31 11:28:18 +01:00

models

[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)

2026-07-31 11:28:18 +01:00

offloader

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

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

warmup

[MoE Refactor] Rename FusedMoE to FusedMoEFactory (#44941)

2026-07-31 11:28:18 +01:00

__init__.py

[Platform] Deprecate seed_everything (#31659)

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

custom_op.py

[Bugfix] Reject contradictory custom-op directives (#49134)

2026-07-26 08:42:14 -04:00

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