GitLab

* add a script to merge models

* finished

* try to merge t5

* merge the config into meta files

* rewrite the t5 model loading

* consider the case of subfolder

* merged the qencoder files

* make the linter happy and fix the tests

* pass tests

* add deprecation messages

* add a script to merge models

* schnell script runnable

* update sana

* modify the model paths

* fix the model paths

* style: make the linter happy

* remove the debugging assertion

* chore: fix the qencoder lpips

* fix the lpips

* update nightly-build.yaml

* use matrix for building

* chore: upgrade the nightly-build.yaml

* chore: start debugging the workflow

* start debugging

* better nightly build

Better 4-bit t5
Fix the removal LoRA
Add nightly windows wheels

* start debugging

* fix: convert the unet state_dict to PeFT one to fix the removal LoRA

* style: make linter happy

* fix the lpips

* Updating quantized t5 encoder

* Fix formatting based on pre-commit hook

* Update test cases

* Fixing linter issue

* Fix linter reformatting

* support fp4

* style: make linter happy

* update the fp4 lpips

* Prevent downloading original t5 model

* Make sure model in eval mode

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

* revise the tag name

* build all linux wheels

* add the cleaning ci

* update the manylinux2_28 builder

* add a workflow

* finished the nightly-build wheels

* chore: add comfyui tests

* finished run ampere tests

* update the blackwell workflows

* install the comfyui test dependencies

* update the expected lpips

* better tests

* update an lpips

Merge into to main for CI

* rename the test CI

* fix the nightly number

* debug building

* debugging version

* debug building

* fixed

* fixed the version

* decrease the MAX_JOBS

* add two nightly build workflows

* style: make the linter happy

release: v0.3.0dev1 pre-release

* Add missing `save_file` call for use of composed.py via command line

* use `output_path` functionality of `compose_lora` instead

* reset_lora is buggy

* fix: fix the LoRA reset

* test: add a test for lora reset

* chore: remove the debug script

* style: make linter happy

* test: enable cpu offloading for the lora reset test

* test: fix the tests

* test: fix the tests

* feat: support FP8 LoRAs (#342)

* feat: support FP8 LoRAs

* fix the int4 expected lpips

* test: use cpu offload to save gpu memory in multi-batch test

* feat: support FP8 LoRAs

* fix the int4 expected lpips

feat: support PuLID, Double FBCache and TeaCache; better linter