[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>
This commit is contained in:
@@ -309,6 +309,7 @@ set(SOURCES
|
||||
"csrc/moe/marlin_moe_wna16/ops.cu"
|
||||
"csrc/moe/moe_align_kernel.cu"
|
||||
"csrc/moe/moe_fused_gate.cu"
|
||||
"csrc/moe/moe_sum_reduce.cu"
|
||||
"csrc/moe/moe_topk_softmax_kernels.cu"
|
||||
"csrc/moe/nvfp4_blockwise_moe.cu"
|
||||
"csrc/moe/fp8_blockwise_moe_kernel.cu"
|
||||
|
||||
Reference in New Issue
Block a user