onnxruntime
Update Attention op to support attention mask for GPT-2
#4330
Merged

Update Attention op to support attention mask for GPT-2 #4330

tianleiwu merged 11 commits into master from tlwu/gpt2_attention_mask
tianleiwu
tianleiwu Fix mask in EmbedLayerNormalization
d41754fe
tianleiwu Add MaskIndex cuda op for BERT optimization
8864979a
tianleiwu Update dynamic axes of gpt2 with past state
51d68cf3
tianleiwu tianleiwu requested a review 5 years ago
tianleiwu tianleiwu marked this pull request as draft 5 years ago
tianleiwu Add attention mask for GPT-2 in cuda & cpu Attention operator
bb8e3958
tianleiwu Merge master
0b91f1ab
tianleiwu tianleiwu marked this pull request as ready for review 5 years ago
tianleiwu tianleiwu changed the title WIP: Support Attention Mask for GPT-2 with past state Update Attention op to support attention mask for GPT-2 with left side padding 5 years ago
tianleiwu tianleiwu added GPT2
tianleiwu tianleiwu requested a review from yufenglee yufenglee 5 years ago
tianleiwu tianleiwu requested a review from liuziyue liuziyue 5 years ago
tianleiwu Add back unit tests that removed in merge.
809249d9
tianleiwu format
eb3ed536
tianleiwu Remove printf
1fbf5002
tianleiwu Support 2D attention mask
91bdc45f
tianleiwu fix build warning
fdefb43a
tianleiwu Update script to fuse model with attention mask
0c97b26c
tianleiwu tianleiwu changed the title Update Attention op to support attention mask for GPT-2 with left side padding Update Attention op to support attention mask for GPT-2 5 years ago
liuziyue
liuziyue approved these changes on 2020-06-30
tianleiwu tianleiwu merged 55f25a4b into master 5 years ago
tianleiwu tianleiwu deleted the tlwu/gpt2_attention_mask branch 5 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone