GitLab

Added a note about upcoming Lightning models in the release announcement.

* update

* update

* docs: update README

* add a note

* 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

* feat: sdxl model support

* code style auto-modified by pre-commit hook

* refine comments

* add tests and examples for sdxl

* refine sdxl tests code

* make linter happy

* mv the locations of the examples

* move the locations of the tests

* refine tests and examples

* add API documentation for unet_sdxl.py

* usage doc for sdxl

* update docs

* update

* refine pipeline initialization

* refine tests for sdxl/sdxl-turbo

* add controlnet support to the qwenimagemodel and add example file for controlnet

* add controlnet support

* add controlnet support for qwenimage

* add controlnet support for qwenimage

* style: make linter happy

* update example script for qwen controlnet

* style: make linter happy

* update

* update diffusers version

* update

* update

* docs: update README

* update docs

* style: make linter happy

Removed Slack user group link from README.

* Update utils.py-fix [Bug] ksampler error #535

* Update utils.py

* Update linear.py-fix [Bug] ksampler error #535 New issue

* update

* update

* chore: update the docs workflow

* docs: update README

* add v2 flux examples

* add the docs

* add docs

* update

* finished ops

* add ops

* update

* update

* update

* update

* update

* update

* update

* update docstrings

* update

* update

* update

* update

* update

* update

* update

* finished the api docs

* update

* update

* 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

* feat: add support for python 3.13

* update workflow to exclude py3.13+torch2.5

* fix typo

Co-authored-by: Kung Talon <31659820+kungtalon@users.noreply.github.com>

* Add paddings if LoRA ranks for q, k, v are different

* No need to create a list

* feat: add support for teacache in flux kontext

* merge main and make linter happy

* caching_v2

* rename fb cache and write docstring

* lint

* rename utils to fbcache

* no need maintain sana for caching

* update

* update

* update README

* update dos

* update docs

* improve the lightning script

* update the example script

* change the repo name

* update

* add parameter of act unsigned

* upgrade the diffusers to v0.35.1

* bump the comfyui version to 0.3.51

* update version

* revert the test comfyui-version back to 0.3.44

* fix: enhance latent variable preparation in NunchakuQwenImagePipeline

- Refactored latent variable preparation to utilize the parent method for generating latents.
- Added manual generation of latent_image_ids to ensure correct indexing.

* refactor: clean up whitespace in NunchakuQwenImagePipeline

- Removed unnecessary whitespace in the latent variable preparation section for improved readability.

* update app

* depth supports fp4

* update

* fix the demo website

* style: make linter happy

* start refract the codebase

* update

* update

* start to implement ops

* add gemm

* write the docstrings

* define the w4a4 svdq linear

* update

* make the linter happy

* finished the SVDQW4A4Linear

* finished the SVDQW4A4Linear

* update

* update

* add a patcher to the model

* update

* add adanormsinglezero

* update

* update

* finished the naive implementation of nunchaku flux

* add ff

* finished the naive forward

* update

* svdq linear

* start debugging

* fix some issues

* successfully built the model

* update

* successfully load the model

* update

* update

* update

* try to making it runnable

* debugging

* debugging

* debugging

* add bias to awq linear

* run through

* fix the normalization

* update

* update

* update

* fix the attention

* fix the no fuse nvfp models

* update

* finished the fused ff

* make linter happy

* make linter happy

* make linter happy

* debugging the fp16 attn

* nunchaku fp16 is buggy

* finish the fp16 attn

* fp4 done

* fix the lora scales

* add a default value for alpha; need to debug int4

* fix input4

* update

* update

* ff does not work

* specialize the processors

* qwen transformer done. start debugging

* make linter happy

* add schnell v2 for metrics eval

* chore: schnellv2 eval

* update

* ff and attention correct

* need to check what happened to module

* fp4 done

* make linter happy

* update an example script

* reformat

* add an example script

* add the annoucement

* remove a misleading info

* ready to release

* fix teacache_batch

* lint

* fix the hf uploading

* use conda python

* chore: support uploading wheel to hf

* support ready_for_review