8000 [ONNX] Quantization documentation outdated · Issue #4188 · llvm/torch-mlir · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

[ONNX] Quantization documentation outdated #4188

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.

Sign up for GitHub

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

Jump to bottom
Open
anuragsingh-tt opened this issue May 19, 2025 · 0 comments
Open

[ONNX] Quantization documentation outdated #4188

anuragsingh-tt opened this issue May 19, 2025 · 0 comments

Comments

@anuragsingh-tt
Copy link

The documentation here states the following:

Quantization parameters are carried out of line in the ONNX protobuf
and will be repatriated upon import to torch. The exact mechanism is
not yet implemented.

This is outdated. The following simple conv2d in onnx:

Image

contains the quantization parameters in line. There are already test cases in the torch-mlir repo (e.g. here) that can translate this successfully to torch.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@anuragsingh-tt
0