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

..

__init__.py

[Frontend] new online quantization frontend (#38138)

2026-04-03 11:58:39 -04:00

base.py

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

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

fp8.py

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

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

int8.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

moe_base.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

mxfp8.py

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

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