Yuan Luo 616a3e20df [sgl-kernel] Support moe_sum_reduce cuda kernel (#10321) ...

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

2025-09-19 14:12:09 +08:00

..

cutlass_moe/w4a8

pass a_scale from fp8 quant result instead of hard code to 1.0f (#10241)

2025-09-10 12:56:05 -07:00

marlin_moe_wna16

…

cutlass_moe_helper.cu

…

fp8_blockwise_moe_kernel.cu

Update CUTLASS. Refine KernelSchedule for fp8 (grouped) gemm. (#10491)

2025-09-16 02:47:37 -07:00

moe_align_kernel.cu

…

moe_fused_gate.cu

Fix correction bias undefined behavior for nvfp4 models (#10426)

2025-09-14 18:41:09 -07:00

moe_sum_reduce.cu

[sgl-kernel] Support moe_sum_reduce cuda kernel (#10321)

2025-09-19 14:12:09 +08:00

moe_topk_softmax_kernels.cu

…

nvfp4_blockwise_moe.cu

…

prepare_moe_input.cu

…