AIbin fd91da7b41 【Inference Optimize】Support wint2 triton kernel about triton_utils_v2 (#2842) ...

* update supported_models doc

2025-07-15 14:35:40 +08:00

..

__init__.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

ep.py

Sync v2.0 version of code to github repo

2025-06-29 23:29:37 +00:00

fused_moe_backend_base.py

Simplify the Config code (#2770)

2025-07-14 19:50:05 +08:00

fused_moe_cutlass_backend.py

dcu adapter ernie45t (#2756)

2025-07-09 18:56:27 +08:00

fused_moe_deepgemm_backend.py

Simplify the Config code (#2770)

2025-07-14 19:50:05 +08:00

fused_moe_marlin_backend.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00

fused_moe_triton_backend.py

[Feature] block_wise_fp8 support triton_moe_backend (#2767)

2025-07-09 19:22:47 +08:00

fused_moe_wint2_backend.py

【Inference Optimize】Support wint2 triton kernel about triton_utils_v2 (#2842)

2025-07-15 14:35:40 +08:00

fused_moe_xpu_backend.py

[XPU] Supports BF16 for ERNIE-4.5-21B-A3B and ERNIE-4.5-0.3B (#2765)

2025-07-09 15:57:51 +08:00

moe.py

Simplify the Config code (#2770)

2025-07-14 19:50:05 +08:00

triton_moe_kernels.py

[Sync] Update to latest code (#2679)

2025-07-03 15:43:53 +08:00