yangjianfengo1 e81046fdad 【New Feature】集中式支持w4afp8 (#3644) ...

* 支持tp w4afp8

* code style

2025-08-28 10:53:24 +08:00

..

moe_wna16_marlin_utils

…

deepgemm_preprocess.cu

…

ep_moe_prefill_func.cu

[NewFeature]Support dp multi api server && Fix some bug in mixed ep && merge develop (#3598)

2025-08-26 19:59:02 +08:00

fast_hardamard_kernel.cu

support w4afp8 EP inference (#3044)

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

fast_hardamard_kernel.h

…

fused_moe_helper.h

…

fused_moe_imp_op.h

…

fused_moe_op.h

【New Feature】集中式支持w4afp8 (#3644)

2025-08-28 10:53:24 +08:00

fused_moe.cu

…

gptq_marlin_repack.cu

…

group_swiglu_with_masked.cu

…

group_swiglu_with_masked.h

…

moe_deepgemm_depermute.cu

…

moe_deepgemm_permute.cu

…

moe_dispatch.cu

【New Feature】集中式支持w4afp8 (#3644)

2025-08-28 10:53:24 +08:00

moe_ffn_wint2.cu

…

moe_ffn.cu

【New Feature】集中式支持w4afp8 (#3644)

2025-08-28 10:53:24 +08:00

moe_reduce.cu

…

moe_redundant_topk_select.cu

topk_gating_softmax support bias (#3405)

2025-08-15 11:57:45 +08:00

moe_topk_select.cu

topk_gating_softmax support bias (#3405)

2025-08-15 11:57:45 +08:00

moe_wna16_marlin_gemm.cu

…

moe_wna16_marlin_gemm.h

…

tritonmoe_preprocess.cu

…

wintx_unzip.cu

…