4 people 823eaf667d [XPU] FP8 o_proj with fp8_bmm and load-time scale transpose (#48334) ...

Signed-off-by: Wu, Xiaochang <xiaochang.wu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

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

..

kernels

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

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

layers

[XPU] [MoE] add quant input when prepare for fusedmoe (#47122)

2026-07-20 15:47:26 +08:00

model_loader

[Bugfix] Re-sync parameter tp_rank after process_weights_after_loading (fix replicated / disable_tp weight reload) (#48025)

2026-07-18 08:40:06 +00:00

models

[Multimodal] Automatically fallback to ViT DP when TP is unavailable (#49046)

2026-07-18 14:41:04 -07:00

offloader

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

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

warmup

[Refactor] Remove deepseek dead code (#48780)

2026-07-17 14:57:13 +00:00

__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