onnxruntime
Add MLFloat16 support for SoftmaxCrossEntropyLoss for CUDA EP
#7679
Merged
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Overview
Commits
4
Changes
View On
GitHub
Add MLFloat16 support for SoftmaxCrossEntropyLoss for CUDA EP
#7679
ashbhandare
merged 4 commits into
master
from
aibhanda/SCE_fp16
ashbhandare
added
ep:CUDA
ashbhandare
added
core runtime
ashbhandare
added
training
weixingzhang
commented on 2021-05-13
ashbhandare
marked this pull request as ready for review
5 years ago
ashbhandare
requested a review
5 years ago
weixingzhang
dismissed these changes on 2021-05-13
codemzs
requested a review
from
codemzs
5 years ago
codemzs
dismissed these changes on 2021-05-13
Forward op changes
963abb60
Add tests, improve kernel
998b6fe4
add opset 13 registration, remove unnecessary changes
c0dada14
Add fp16 grad for SCELoss, review comments
a40b0e97
ashbhandare
dismissed their stale review via
a40b0e97
5 years ago
ashbhandare
dismissed their stale review via
a40b0e97
5 years ago
ashbhandare
force pushed
from
0da50c20
to
a40b0e97
5 years ago
weixingzhang
approved these changes on 2021-05-14
ashbhandare
merged
bfbcc89d
into master
5 years ago
ashbhandare
deleted the aibhanda/SCE_fp16 branch
5 years ago
Login to write a write a comment.
Login via GitHub
Reviewers
weixingzhang
codemzs
Assignees
No one assigned
Labels
training
core runtime
ep:CUDA
Milestone
No milestone
Login to write a write a comment.
Login via GitHub