Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[conv] Fix conv configuration like matmul to see through fused dequant ops #39

Open
antiagainst opened this issue Jun 29, 2024 · 0 comments
Assignees
Labels
sdxl-int8 Issues replated to SDXL quantized model support

Comments

@antiagainst
Copy link
Contributor

antiagainst commented Jun 29, 2024

Like what we do in iree-org/iree#17764 for matmul, we also need to change configuration for conv to let it match intrinsics.

@antiagainst antiagainst added the sdxl-int8 Issues replated to SDXL quantized model support label Jun 29, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
sdxl-int8 Issues replated to SDXL quantized model support
Projects
Status: Todo
Development

No branches or pull requests

2 participants