GitLab

Feature:
    1. added mlu590 bfloat16, single-gpu and multi-gpus inference.
    2. added mlu590 int8 inference.

update deploy

---------
Co-authored-by: liuliang1 <liuliang1@sensetime.com>
Co-authored-by: qinxinyi <qinxinyi@sensetime.com>
Co-authored-by: Yang Yong(雍洋) <yongyang1030@163.com>

deploy update

---------
Co-authored-by: liuliang1 <liuliang1@sensetime.com>
Co-authored-by: qinxinyi <qinxinyi@sensetime.com>

* [Feat] audio driven for wan2.2-r2v-5b

* refactor: reduce vae args dim &&  timestep init

* update audio pre_infer

* update runner

* update scripts

* [Fix] move ref timestep padding to Scheduler

* fix wan i2v

---------
Co-authored-by: helloyongyang <yongyang1030@163.com>

* [Fix] Fix audio model offload bug.

* Fix

* Fix

* Fix

* Fix

* Fix

* Fix

* add gguf loading functions

* support wan22 distill

* feat: add vfi(rife)

* refactor: update video saving functionality and add VAE to ComfyUI image conversion.

* refactor: enhance video saving process and integrate VAE to ComfyUI image conversion

* refactor: reorganize imports and enhance code structure in default_runner and utils modules

* feat: add video frame interpolation support with RIFE model integration

* refactor: streamline code structure and improve readability in IFNet and refine modules

* fix: style

* feat: add script for downloading and installing RIFE model with flownet.pkl extraction

* update

* docs: update README and documentation to include video frame interpolation feature with RIFE model

* fix ci

* docs: enhance video frame interpolation documentation and update configuration usage for RIFE model

---------
Co-authored-by: helloyongyang <yongyang1030@163.com>

* [minor]: optimize dockerfile for fewer layer

* [feature]: add pre-commit lint, update readme for contribution guidance

* [minor]: fix run shell privileges

* [auto]: first lint without rule F, fix rule E

* [minor]: fix docker file error