xiaoxiaohehe001 ee37882a26 [NewFeature] support eplb noaux (#4725) ...

* support eplb noaux

* support eplb noaux

* add  eplb noaux test

2025-11-05 20:59:12 +08:00

..

__init__.py

support w4afp8 EP inference (#3044)

2025-08-25 11:27:45 +08:00

ep.py

[NewFeature] support eplb noaux (#4725)

2025-11-05 20:59:12 +08:00

fused_moe_backend_base.py

fix ep perf (#4381)

2025-10-15 18:38:20 +08:00

fused_moe_cutlass_backend.py

[NewFeture]add ep rollout model init and update/clear ep buffer (#3927)

2025-09-12 14:15:13 +08:00

fused_moe_deepgemm_backend.py

[NewFeture]add ep rollout model init and update/clear ep buffer (#3927)

2025-09-12 14:15:13 +08:00

fused_moe_marlin_backend.py

[NewFeture]add ep rollout model init and update/clear ep buffer (#3927)

2025-09-12 14:15:13 +08:00

fused_moe_triton_backend.py

[NewFeture]add ep rollout model init and update/clear ep buffer (#3927)

2025-09-12 14:15:13 +08:00

fused_moe_wint2_backend.py

【New Feature】集中式支持w4afp8 (#3644)

2025-08-28 10:53:24 +08:00

fused_moe_xpu_backend.py

[V1 Loader]support param create and load for wint2 and xpu backend (#3581)

2025-08-28 09:49:36 +08:00

moe.py

[NewFeature] support eplb noaux (#4725)

2025-11-05 20:59:12 +08:00

triton_moe_kernels.py

Support 45t fp8 8 GPU (#3659)

2025-08-28 10:52:53 +08:00