zyl_keep_movingandXiaoyu Zhang a9ce1623cd [kernel][moe] add moe topk fast (#13969) ...

Co-authored-by: Xiaoyu Zhang <35585791+BBuf@users.noreply.github.com>

2025-12-14 22:26:40 +08:00

..

cutlass_moe/w4a8

…

marlin_moe_wna16

Add new moe wna16 marlin gemm (#14122)

2025-12-01 23:07:53 +08:00

cutlass_moe_helper.cu

…

fp8_blockwise_moe_kernel.cu

…

fused_qknorm_rope_kernel.cu

[sgl-kernel][1/2] Fused qk_norm_rope for Qwen3-MoE (#14036)

2025-11-28 12:25:15 +08:00

kimi_k2_moe_fused_gate.cu

[opt kimi k2 3/n] opt kimi_k2 moe_fused_gate kernel (#13374)

2025-11-18 15:36:31 +08:00

moe_align_kernel.cu

Opt moe align block size kernel (#14133)

2025-12-02 19:13:55 +08:00

moe_fused_gate.cu

…

moe_sum_reduce.cu

…

moe_sum.cu

…

moe_topk_sigmoid_kernels.cu

Support moe topk sigmoid kernel (#13049)

2025-11-20 00:24:37 +08:00

moe_topk_softmax_kernels.cu

[kernel][moe] add moe topk fast (#13969)

2025-12-14 22:26:40 +08:00

nvfp4_blockwise_moe.cu

…

prepare_moe_input.cu

fix: fix apply_shuffle_mul_sum (#7444)

2025-07-04 23:23:30 -07:00