Skip to content

refactor(ops): migrate softmax to canonical InfiniOps API #1471

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
voltjia wants to merge 1 commit into from
Closed

refactor(ops): migrate softmax to canonical InfiniOps API #1471

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
4 changes: 2 additions & 2 deletions src/infinicore/ops/softmax/softmax_infiniops.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
#ifdef ENABLE_INFINIOPS_API
#include "../infiniops_impl.hpp"

#include "base/softmax_infinilm.h"
#include "base/softmax.h"

#include <optional>

Expand All @@ -22,7 +22,7 @@ void calculate(Tensor output, Tensor input, int axis) {

TensorMeta output_meta(output);
TensorMeta input_meta(input);
infini::ops::SoftmaxInfinilm::Call(
infini::ops::Softmax::Call(
handle,
config,
input_meta.tensor(input),
Expand Down
2 changes: 1 addition & 1 deletion submodules/InfiniOps
Open in desktop
Submodule InfiniOps updated 7 files
+10 −1 src/base/softmax.h
+21 −0 src/native/cuda/iluvatar/ops/softmax/kernel.h
+21 −0 src/native/cuda/metax/ops/softmax/kernel.h
+22 −0 src/native/cuda/moore/ops/softmax/kernel.h
+21 −0 src/native/cuda/nvidia/ops/softmax/kernel.h
+115 −0 src/native/cuda/ops/softmax/kernel.h
+73 −0 tests/test_softmax.py
Loading