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

Add scale and zero_point to xten_nn.quantize/dequantize #148

Merged
merged 8 commits into from
Feb 25, 2025

Conversation

jorickert
Copy link
Contributor

@jorickert jorickert commented Feb 20, 2025

  • Update downstream users
  • Add custom assembly parser.
  • Add lowering to tosa
  • populate shift in assembly parser
  • Crash in xten_nn to tosa

This is a breaking change for C++ users, but should require no changes in pdll.
Edit: It requires not changes in PDLL matching but requires changes in pdll rewriting, as the pdll rewriter does direclty construct operations, bypassing builders

@jorickert jorickert requested a review from roberteg16 February 21, 2025 01:48
@mathmer-amd mathmer-amd self-requested a review February 21, 2025 11:30
@jorickert jorickert marked this pull request as ready for review February 21, 2025 18:14
@jorickert jorickert requested a review from ljfitz February 22, 2025 20:16
@jorickert jorickert requested a review from ttjost February 24, 2025 03:51
@ttjost ttjost removed their request for review February 24, 2025 14:39
Copy link
Collaborator

@ljfitz ljfitz left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@jorickert jorickert merged commit 93f98b9 into feature/fused-ops Feb 25, 2025
2 checks passed
@jorickert jorickert deleted the jrickert.qdq branch February 25, 2025 02:35
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants