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

Feat (ptq): adding accumulator-aware extensions to GPxQ #1060

Merged
merged 19 commits into from
Oct 26, 2024

Conversation

i-colbert
Copy link
Collaborator

@i-colbert i-colbert commented Oct 15, 2024

Reason for this PR

Implement accumulator-aware extensions (AXE) for GPxQ (see https://arxiv.org/pdf/2409.17092)

Highlights:

  • Accumulator-aware variants of GPTQ and GPFQ
  • Extend ImageNet classification entrypoint to support
  • Extend LLM entrypoint to support

Changes Made in this PR

Experimental support for AXE was added by extending GPxQ and their entrypoints for ImageNet and LLM quantization.

Testing Summary

N/A

Risk Highlight

  • This PR includes code from another work (please detail).
  • This PR contains API-breaking changes.
  • This PR depends on work in another PR (please provide links/details).
  • This PR introduces new dependencies (please detail).
  • There are coverage gaps not covered by tests.
  • Documentation updates required in subsequent PR.

Checklist

  • Code comments added to any hard-to-understand areas, if applicable.
  • Changes generate no new warnings.
  • Updated any relevant tests, if applicable.
  • No conflicts with destination dev branch.
  • I reviewed my own code changes.
  • Initial CI/CD passing.
  • 1+ reviews given, and any review issues addressed and approved.
  • Post-review full CI/CD passing.

@i-colbert i-colbert marked this pull request as ready for review October 15, 2024 19:36
@i-colbert i-colbert added the next release PRs which should be merged for the next release label Oct 16, 2024
@i-colbert i-colbert changed the title Feat (llm): adding accumulator-aware extensions to GPxQ Feat (ptq): adding accumulator-aware extensions to GPxQ Oct 18, 2024
@i-colbert i-colbert requested review from Giuseppe5 and removed request for Giuseppe5 October 22, 2024 06:38
@Giuseppe5 Giuseppe5 merged commit 2cb8c9d into Xilinx:dev Oct 26, 2024
22 of 23 checks passed
@i-colbert i-colbert deleted the feat/axe branch October 27, 2024 00:04
Giuseppe5 pushed a commit to Giuseppe5/brevitas that referenced this pull request Oct 29, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
next release PRs which should be merged for the next release
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants