[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
parent ac2a723bb3
commit 616a3e20df
7 changed files with 346 additions and 10 deletions
--- a/sgl-kernel/python/sgl_kernel/init.py
+++ b/sgl-kernel/python/sgl_kernel/init.py
@@ -112,6 +112,7 @@ from sgl_kernel.moe import (
    fp8_blockwise_scaled_grouped_mm,
    moe_align_block_size,
    moe_fused_gate,
+    moe_sum_reduce,
    prepare_moe_input,
    topk_softmax,
 )