onnxruntime
Add non-zero zp support for quant matmul and attention
#7570
Merged

Add non-zero zp support for quant matmul and attention #7570

yufenglee merged 6 commits into master from yufeng/matmul_non_zp
yufenglee
yufenglee add non-zero zp support
335e3514
yufenglee yufenglee requested a review 4 years ago
yufenglee Merge branch 'master' into yufeng/matmul_non_zp
bb515c93
yufenglee support A and B scale with any dimensions
8b395219
yufenglee yufenglee force pushed from ec299922 to 8b395219 4 years ago
yufenglee fix build breaks
49f6edab
yufenglee fix warning in MSVC
745c6371
yufenglee yufenglee force pushed from b6f5c2cf to 745c6371 4 years ago
zhanghuanrong
zhanghuanrong dismissed these changes on 2021-05-14
yufenglee add op type check for DynamicQuantizeLinear
bca20cc3
yufenglee yufenglee dismissed their stale review via bca20cc3 4 years ago
zhanghuanrong
zhanghuanrong approved these changes on 2021-05-14
yufenglee yufenglee merged a74e41e4 into master 4 years ago
yufenglee yufenglee deleted the yufeng/matmul_non_zp branch 4 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone