Neil Zhu 0edda75a56 [Metax] optimize cutlass moe and flash attention backend (#5128)

2025-11-20 16:12:35 +08:00

..

apply_rope.cu

[Metax] optimize cutlass moe and flash attention backend (#5128)

2025-11-20 16:12:35 +08:00

fused_moe_helper.h

[Metax] support cutlass moe & optimize flash attention (#4208)

2025-09-29 11:22:43 +08:00

fused_moe_imp_op.h

c++ code format (#4527)

2025-10-22 17:59:50 +08:00

fused_moe_op.h

c++ code format (#4527)

2025-10-22 17:59:50 +08:00

fused_moe.cu

[Metax] adapt cutlass moe for ernie-vl (#4685)

2025-11-03 17:44:27 +08:00

mc_fused_moe_helper.h

[Metax] optimize cutlass moe and flash attention backend (#5128)

2025-11-20 16:12:35 +08:00

moe_dispatch.cu

[Metax] adapt cutlass moe for ernie-vl (#4685)

2025-11-03 17:44:27 +08:00

moe_ffn.cu

[Metax] optimize cutlass moe and flash attention backend (#5128)

2025-11-20 16:12:35 +08:00

moe_reduce.cu

c++ code format (#4527)

2025-10-22 17:59:50 +08:00