co63oc d6369b4d51 fix typos (#3684)

2025-09-01 17:50:17 +08:00

..

__init__.py

support w4afp8 EP inference (#3044)

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

ep.py

fix typos (#3684)

2025-09-01 17:50:17 +08:00

fused_moe_backend_base.py

[Features] support hugging face qwen3 moe (#3649)

2025-08-30 15:26:05 +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

Support 45t fp8 8 GPU (#3659)

2025-08-28 10:52:53 +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

[Features] support hugging face qwen3 moe (#3649)

2025-08-30 15:26:05 +08:00

triton_moe_kernels.py

Support 45t fp8 8 GPU (#3659)

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