GitLab

* update sphinx docs

* update the doc configration

* configure doxyfile

* start building the docs

* building docs

* building docs

* update docs

* finish the installation documents

* finish the installation documents

* finish the installation documents

* start using rst

* use rst instead of md

* need to figure out how to maintain rst

* update

* make linter happy

* update

* link management

* rst is hard to handle

* fix the title-only errors

* setup the rst linter

* add the lora files

* lora added, need to be more comprehensive

* update

* update

* finished lora docs

* finished the LoRA docs

* finished the cn docs

* finished the cn docs

* finished the qencoder docs

* finished the cpu offload

* finished the offload docs

* add the attention docs

* finished the attention docs

* finished the fbcache

* update

* finished the pulid docs

* make linter happy

* make linter happy

* add kontext

* update

* add the docs for gradio demos

* add docs for test.py

* add the docs for utils.py

* make the doc better displayed

* update

* update

* add some docs

* style: make linter happy

* add docs

* update

* add caching docs

* make linter happy

* add api docs

* fix the t5 docs

* fix the t5 docs

* fix the t5 docs

* hide the private functions

* update

* fix the docs of caching utils

* update docs

* finished the docstring of nunchaku cahcing

* update packer

* revert the docs

* better docs for packer.py

* better docs for packer.py

* better docs for packer.py

* better docs for packer.py

* update

* update docs

* caching done

* caching done

* lora

* lora

* lora

* update

* python docs

* reorg docs

* add the initial version of faq

* update

* make linter happy

* reorg

* reorg

* add crossref

* make linter happy

* better docs

* make linter happy

* preliminary version of the docs done

* update

* update README

* update README

* docs done

* update README

* update docs

* not using datasets 4 for now

* Fix: Correctly specify non-zero GPUs in multi-GPU environments

This commit resolves an issue where the Nunchaku model could not be
correctly initialized and run on a user-specified non-zero GPU in
multi-GPU systems.

Key changes include:
- Using CUDADeviceContext in the FluxModel constructor to ensure
  the model and its submodules are created within the specified GPU context.
- Modifying the logic in FluxModel::forward for copying residual data
  from CPU back to GPU, ensuring it returns to the correct original GPU device.
- Adding explicit CUDA context management in Tensor::copy_ for data
  copy operations involving CUDA devices (H2D, D2H, D2D) to guarantee
  cudaMemcpyAsync executes on the correct device.

These changes allow users to reliably run Nunchaku on any specified
GPU in a multi-GPU setup.

* finish pre-commit

* fix:txt2_img pipe and controlnet pipe share components

* add the test script

* comfyUI bug fix

* garbage collection

* wrap the test

---------
Co-authored-by: Muyang Li <lmxyy1999@foxmail.com>

* fix the use count

* update

* change the example step to 20

* allow embedding website

* support fp4 on blackwell

* fp4 kontext runnable

* add more examples

* add kontext examples

chore: update the kontext support

* update kontext examples

* update tests

* add tests for kontext

* remove the warning of txt_ids and img_ids

* chore: add kontext to be synced from hf to ms

* add kontext demo

* make linter happy

* style: make linter happy

* update docs

* change the model path

* change the model path

* fix the model paths

* rename facexlib_path to facexlib_dirpath

* add start_timestep and end_timestep

* no need to download the files if the folder exists

* kohya supported

* add a test for the LoRA

* add a gc

* upgrade pulid to 0.9.1,When the EVA CLIP config is not found, I use the built-in JSON parameters instead.The issue of repeated model downloads has been resolved, and the model path specified by ComfyUI will be faithfully used.

style:apply black check

style:apply isort check

* fix callback bugs

style: apply clang-format