optimum
Fix float16 ORT conversion for models > 2GB
#1079
Merged

Fix float16 ORT conversion for models > 2GB #1079

fxmarty
fxmarty use ORT symbolic shape inference instead of ONNX shape inference at O…
49057554
fxmarty hopefully fix
f332c184
fxmarty fxmarty merged 4d37ed91 into main 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
No reviews
Assignees
No one assigned
Labels
Milestone