onnxruntime
Support larger hidden size in Attention Cuda kernel
#7002
Merged
Overview
Commits
5
Changes
View On GitHub

Support larger hidden size in Attention Cuda kernel #7002

gh-yewang merged 5 commits into master from wangye/hidden_size
gh-yewang
gh-yewang Support larger hidden size in Attention Cuda kernel
16470401
gh-yewang gh-yewang requested a review 5 years ago
gh-yewang gh-yewang marked this pull request as draft 5 years ago
gh-yewang gh-yewang changed the title (WIP)Support larger hidden size in Attention Cuda kernel Support larger hidden size in Attention Cuda kernel 5 years ago
gh-yewang gh-yewang changed the title Support larger hidden size in Attention Cuda kernel (WIP)Support larger hidden size in Attention Cuda kernel 5 years ago
gh-yewang Update attention_transpose.cu
165c5fcf
gh-yewang gh-yewang requested a review from tianleiwu tianleiwu 5 years ago
gh-yewang gh-yewang changed the title (WIP)Support larger hidden size in Attention Cuda kernel Support larger hidden size in Attention Cuda kernel 5 years ago
gh-yewang gh-yewang marked this pull request as ready for review 5 years ago
tianleiwu
tianleiwu requested changes on 2021-03-15
tianleiwu
tianleiwu commented on 2021-03-15
gh-yewang review comments
f2e84fcb
tianleiwu
tianleiwu commented on 2021-03-15
gh-yewang fix typo and add check in quantization
f0d8d96a
gh-yewang gh-yewang requested a review from tianleiwu tianleiwu 5 years ago
gh-yewang update readme
695f5b18
tianleiwu
tianleiwu approved these changes on 2021-03-15
gh-yewang gh-yewang merged 4e670f7a into master 5 years ago
gh-yewang gh-yewang deleted the wangye/hidden_size branch 5 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Terms Of Use Privacy Policy Refund Policy Impressum