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 (examples/sdxl): Updates to SDXL entry-point #1020

Merged
merged 14 commits into from
Sep 12, 2024

Conversation

nickfraser
Copy link
Collaborator

@nickfraser nickfraser commented Sep 5, 2024

Depends on #1021. Rebased after #1021 was merged into dev. The following updates to SDXL:

  • Specify blacklist via commandline
  • Fix "param-only" export for FP8 datatypes (works with Int8 & FP8)
  • Fix blacklist exclusion issue (in Fix (graph/quant): Bugfix in blacklist matching in find_module #1021)
  • Allow customization of SDPA quantization via command-line
  • Support latest diffusers QKV merging (but still with support for the MLPerf version)

@Giuseppe5
Copy link
Collaborator

Let's sync about this!

@nickfraser nickfraser marked this pull request as ready for review September 10, 2024 11:15
if (args.linear_input_bit_width > 0 or args.conv_input_bit_width > 0 or
args.sdpa_bit_width > 0 or
args.quantize_sdp) and args.input_scale_type == 'static':
# Model needs calibration if any of its activation quantizers are 'static'
Copy link
Collaborator

Choose a reason for hiding this comment

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

Sweet

@nickfraser nickfraser merged commit 9932b92 into Xilinx:dev Sep 12, 2024
23 checks passed
@nickfraser nickfraser deleted the exp/sdxl branch September 12, 2024 10:41
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.

2 participants