Charles Volzka

@andife My initial thought is that this missed the boat for the 1.16 release. I'm working on uploading 1.16.0rc1 ~~later today~~ tomorrow morning and this hasn't even merged into `main`...

I cherry-picked the fix for the MacRelease actions. Based on it's description, it looks like I'm hitting on https://github.com/onnx/onnx/pull/6120 as I'm seeing on LinuxRelease_x86_64 results: ``` note: This error originates...

I cherry-picked the fix for the MacRelease actions. Based on it's description, it looks like I'm hitting on https://github.com/onnx/onnx/pull/6120 as I'm seeing on LinuxRelease_x86_64 results: ``` note: This error originates...

@justinchuby any idea why the Linux/MacOS/Windows-CI tests are staying at "expected"? Is there another commit from main I need to pull related to that? (also affects https://github.com/onnx/onnx/pull/6107)

> Could be that the branch rules for rel-* branches were not modified to remove the azure devop checks. @prasanthpul has the access to adjust the branch protection rules. @prasanthpul,...

Yay! Finally everything passes! I've had to pull in a few more cherry-picks since the original approval. I updated the description above to match. @justinchuby and @gramalingam I reset your...

No. Dequantizing would turn them back into floats. So you'd loose both the memory savings and performance improvements of integer math on the operation. You'd also have to recalculate scales...

@imaihal can this issue be closed?

Closing as duplicate of https://github.com/onnx/onnx-mlir/issues/1808

Based on the last comment, can this issue be closed or is there something left to investigate?