gaoziyuan 05b6591c23 【BugFix】add moe noaux_tc tatics in trition backend (#3821) ...

* add moe noaux_tc tatics in trition backend

* fix

* add dp config

2025-09-03 13:28:44 +08:00

..

__init__.py

support w4afp8 EP inference (#3044)

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

ep.py

[BugFix] fix error of import paddle.base.core.Config (#3761) (#3804)

2025-09-03 10:14:03 +08:00

fused_moe_backend_base.py

[Feature] support model weight update in ep (#3802)

2025-09-02 20:52:47 +08:00

fused_moe_cutlass_backend.py

add w4afp8 offline script (#3636)

2025-08-29 17:56:05 +08:00

fused_moe_deepgemm_backend.py

add w4afp8 offline script (#3636)

2025-08-29 17:56:05 +08:00

fused_moe_marlin_backend.py

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

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

fused_moe_triton_backend.py

【BugFix】add moe noaux_tc tatics in trition backend (#3821)

2025-09-03 13:28:44 +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

[v1loader]Reduce EB300B model loading time (#3700) (#3810)

2025-09-03 10:14:31 +08:00

triton_moe_kernels.py

Support 45t fp8 8 GPU (#3659)

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