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.

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

✨[Feature] Implement QAT converters #2460

Closed
Tracked by #2459
peri044 opened this issue Nov 13, 2023 · 0 comments
Closed
Tracked by #2459

✨[Feature] Implement QAT converters #2460

peri044 opened this issue Nov 13, 2023 · 0 comments
Assignees
@narendasan
Labels
feature request New feature or request

Comments

@peri044
Copy link
Collaborator

peri044 commented Nov 13, 2023

Is your feature request related to a problem? Please describe.
Ensure QAT models get compiled successfully

Describe the solution you'd like

  1. Verify export/compile graph support for QAT models produced by pytorch-quantization toolkit
  2. Implement converter support for torch.fake_quantize_per_tensor_affine and torch.fake_quantize_per_channel_affine ops

Describe alternatives you've considered

Additional context
@peri044 peri044 added the feature request New feature or request label Nov 13, 2023
@peri044 peri044 mentioned this issue Nov 13, 2023
Open
@peri044 peri044 changed the title ✨[Feature] Support QAT in dynamo workflows ✨[Feature] Implement QAT converters Nov 23, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@narendasan narendasan

Labels
feature request New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@narendasan @peri044