apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-04 08:16:42 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Feature] Support_eplb (#2997)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
Details

Browse Source 
* [Feature] support_eplb

* [Feature] support_eplb

* [Fix] fix mm ep
This commit is contained in:
xiaoxiaohehe001
2025-07-24 20:22:45 +08:00
committed by GitHub
parent f37d00e856
commit 2970b00dfa
11 changed files with 118 additions and 50 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
custom_ops/gpu_ops/cpp_extensions.cc
View File

@@ -765,7 +765,7 @@ PYBIND11_MODULE(fastdeploy_ops, m) {
* moe/fused_moe/moe_redundant_topk_select.cu
* moe_redundant_topk_select
*/
m.def("f_moe_redundant_topk_select", &MoERedundantTopKSelectKernel,
m.def("moe_redundant_topk_select", &MoERedundantTopKSelectKernel,
py::arg("gating_logits"), py::arg("expert_id_to_ep_rank_array"),
py::arg("expert_in_rank_num_list"),
py::arg("tokens_per_expert_stats_list"), py::arg("bias"),