Skip to content
PR Style Bot

with a custom attention processor for Flux.dev, inference time changes when manually load and inject the transformer model into a flux pipeline versus let the flux pipeline constructor load the transformer internally. #2961

Sign in to view logs

with a custom attention processor for Flux.dev, inference time changes when manually load and inject the transformer model into a flux pipeline versus let the flux pipeline constructor load the transformer internally.

with a custom attention processor for Flux.dev, inference time changes when manually load and inject the transformer model into a flux pipeline versus let the flux pipeline constructor load the transformer internally. #2961

Workflow file for this run

.github/workflows/pr_style_bot.yml at f161e27
name: PR Style Bot
on:
issue_comment:
types: [created]
permissions:
contents: write
pull-requests: write
jobs:
style:
uses: huggingface/huggingface_hub/.github/workflows/style-bot-action.yml@main
with:
python_quality_dependencies: "[quality]"
secrets:
bot_token: ${{ secrets.GITHUB_TOKEN }}