GitLab

* add the v1 tests

* formalize the requirements

* update

* update

* well format the dependency

* update docs

* update

* update

* update the dependency

* fix the version in ci

* well organize the dependency

* update the pr list

* update tests

* add tests for qwen-image

* add qwen-image lightning

* add tests

* update fp4 lpips

* add tests for qwen-image-edit

* update

* updat

* add 8 steps lora back

* update nvfp4 results

* add qwen-image-edit-lightning

* style: make linter happy

* do not use batch when batchsize is 1

* update

* finished all the tests

* add cn test

* style: make linter happy

* update

* add qwen-image controlnet

* update

* add fp4 metrics

* fix the tests

* update

* update

* docs: update README

* update docs

* style: make linter happy

* tmp

* update

* update

* finished the offloading impl

* the offloading is buggy

* update utils

* the offloading is still buggy

* update

* correctness and speedup done; need to check the vram overhead

* done

* final debugging

* update

* update

* correct now

* fix

* update

* use per-layer offloading

* fix the offloading on 5090

* support setting the num_blocks_on_gpu

* change the import name

* update

* update

* update README

* update dos

* update docs

* improve the lightning script

* update the example script

* change the repo name