Skip to content

Revert "[Feature] Support noaux for eplb" #5160

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

Revert "[Feature] Support noaux for eplb" #5160

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 0 additions & 17 deletions custom_ops/gpu_ops/cpp_extensions.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -647,19 +647,6 @@ std::vector<paddle::Tensor> NoauxTc(paddle::Tensor& scores,
bool renormalize,
float routed_scaling_factor);

std::vector<paddle::Tensor> NoauxTcRedundant(
paddle::Tensor& scores,
paddle::Tensor& scores_with_bias,
paddle::Tensor& expert_id_to_ep_rank_array,
paddle::Tensor& expert_in_rank_num_list,
paddle::Tensor& tokens_per_expert_stats_list,
int n_group,
int topk_group,
int topk,
bool renormalize,
float routed_scaling_factor,
int redundant_ep_rank_num_plus_one);

#ifdef ENABLE_FP8
paddle::Tensor cutlass_fp8_fp8_half_gemm_func(
const paddle::Tensor& x,
Expand Down Expand Up @@ -1498,10 +1485,6 @@ PYBIND11_MODULE(fastdeploy_ops, m) {

m.def("noaux_tc", &NoauxTc, "noaux_tc for Deepseekv3 MoE compute");

m.def("noaux_tc_redundant",
&NoauxTcRedundant,
"noaux_tc_redundant for MoE compute");

#ifdef ENABLE_FP8
m.def("cutlass_fp8_fp8_half_gemm_fused",
&cutlass_fp8_fp8_half_gemm_func,
Expand Down
103 changes: 0 additions & 103 deletions custom_ops/gpu_ops/noaux_tc_redundant.cu
View file
Open in desktop

This file was deleted.

Loading
Loading