apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +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/moe/moe_redundant_topk_select.cu
View File

@@ -254,7 +254,7 @@ std::vector<paddle::DataType> MoERedundantTopKSelectKernelInferDtype(
}
PD_BUILD_OP(moe_redundant_topk_select)
PD_BUILD_STATIC_OP(moe_redundant_topk_select)
.Inputs({"gating_logits", "expert_id_to_ep_rank_array", "expert_in_rank_num_list", "tokens_per_expert_stats_list", paddle::Optional("bias")})
.Outputs({"topk_ids",
"topk_weights",