EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Revert "[1/2][resubmit] sgl-kernel: Fuse routed scaling factor into m… (#9035)

Browse Source
This commit is contained in:
Yineng Zhang
2025-08-10 17:34:54 -07:00
committed by GitHub
parent f2887498f0
commit dd949ace23
6 changed files with 12 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
sgl-kernel/csrc/common_extension.cc
View File

@@ -174,7 +174,7 @@ TORCH_LIBRARY_FRAGMENT(sgl_kernel, m) {
m.def(
"moe_fused_gate(Tensor input, Tensor bias, int num_expert_group, int topk_group, int topk, int "
"num_fused_shared_experts, float routed_scaling_factor, bool apply_routed_scaling_factor_on_output) -> "
"num_fused_shared_experts, float routed_scaling_factor) -> "
"(Tensor[])");
m.impl("moe_fused_gate", torch::kCUDA, &moe_fused_gate);
m.def(