Zero Rains fef447e350 [V1 Loader] Support MOE parameters create and load for DeepGemm and marlin backend (#3447) ...

* support deepgemm backend

* support marlin backend

* remove print

* fix process_prequanted_weights

2025-08-19 14:15:53 +08:00

..

__init__.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

check_backend_supported.py

[V1 Loader] Support MOE parameters create and load for DeepGemm and marlin backend (#3447)

2025-08-19 14:15:53 +08:00

ep.py

[Bugfix] Fix model accuracy in some ops (#3231)

2025-08-08 17:30:37 +08:00

fused_moe_backend_base.py

[V1 Loader] Support Ernie text（moe and dense） (#3110)

2025-08-14 20:25:28 +08:00

fused_moe_cutlass_backend.py

[V1 Loader] Support DeepSeekV3(bf16) (#3294)

2025-08-11 13:39:28 +08:00

fused_moe_deepgemm_backend.py

[V1 Loader] Support MOE parameters create and load for DeepGemm and marlin backend (#3447)

2025-08-19 14:15:53 +08:00

fused_moe_marlin_backend.py

[V1 Loader] Support MOE parameters create and load for DeepGemm and marlin backend (#3447)

2025-08-19 14:15:53 +08:00

fused_moe_triton_backend.py

[V1 Loader] Support MOE parameters create and load for DeepGemm and marlin backend (#3447)

2025-08-19 14:15:53 +08:00

fused_moe_wint2_backend.py

qwen3_moe (#3084)

2025-08-06 14:45:27 +08:00

fused_moe_xpu_backend.py

qwen3_moe (#3084)

2025-08-06 14:45:27 +08:00

moe.py

[V1 Loader] Support Ernie text（moe and dense） (#3110)

2025-08-14 20:25:28 +08:00

triton_moe_kernels.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00