fxyfxy777 4d39232553 [BugFix] add ut for fused_moe_degemm (#6840) ...

* add ut

* add skip

2026-03-16 12:22:18 +08:00

..

__init__.py

support w4afp8 EP inference (#3044)

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

ep.py

[Feature] Support EP prefill with num_worst_tokens (#6574)

2026-03-11 17:09:07 +08:00

fused_moe_backend_base.py

[Feature] Support EP prefill with num_worst_tokens (#6574)

2026-03-11 17:09:07 +08:00

fused_moe_cutlass_backend.py

[Iluvatar] Support CudaGraph and optimize flash_attn_unpadded and fused_neox_rope_embedding (#6553)

2026-03-02 14:07:17 +08:00

fused_moe_deepgemm_backend.py

[BugFix] add ut for fused_moe_degemm (#6840)

2026-03-16 12:22:18 +08:00

fused_moe_marlin_backend.py

[Optimization] Enable BF16 gate computation for GLM and Qwen (#6457)

2026-02-26 21:08:46 -08:00

fused_moe_triton_backend.py

[Feature] Support EP prefill with num_worst_tokens (#6574)

2026-03-11 17:09:07 +08:00

fused_moe_wint2_backend.py

[loader]supoort wint2 backend (#6139)

2026-02-08 22:42:36 -08:00

moe.py

[loader]supoort wint2 backend (#6139)

2026-02-08 22:42:36 -08:00

routing_indices_cache.py

[RL] add stream guard (#6814)

2026-03-13 11:22:26 +08:00

triton_moe_kernels.py

[OPs] MoE support wfp8afp8(channelwise) and improve per_token_quant_fp8 (#4238)

2025-09-24 16:39:51 +08:00