Yongye ZhuandClaude f8848b2f2d [Bugfix] Add swiglu limits to deepgemm fp8 methods (#41986) ...

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>

2026-05-14 15:43:13 -07:00

..

kernels

[XPU] Fix double-transpose in XPUFP8ScaledMMLinearKernel for W8A8 quant method (#41689)

2026-05-14 17:17:39 +08:00

layers

[Bugfix] Add swiglu limits to deepgemm fp8 methods (#41986)

2026-05-14 15:43:13 -07:00

model_loader

[Quantization] Rework quantization_config to use QuantKey and allow for activation override (#41566)

2026-05-13 16:58:32 -04:00

models

[Fix] Misc Fixes in ViT CUDA Graph (#38040)

2026-05-14 23:49:06 +08:00

offloader

[Refactor] Clean up log once scope="local" (#40540)

2026-04-22 16:42:43 -04:00

warmup

[MoE Refactor] Move remaining experts classes to experts directory (#42334)

2026-05-12 09:19:46 -04:00

__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

[Quantization] add humming quantization kernel (#34556)

2026-04-24 09:29:44 -04:00

utils.py

[Bugfix][Rocm]Aiter MoE re-uses existing tensor addresses after weight update. (#40390)

2026-05-06 10:32:26 +00:00