Commits · e2116d7bdc3d49ed1a30173d96a0c510db8fad4f · fengzch-das / nunchaku

01 Jun, 2025 1 commit

feat: support AWQ 4-bit T5 and single-file model loading in ComfyUI (#421) · f4f11133

Muyang Li authored Jun 01, 2025

* better linter

* update

* remove merge t5; update the nightly-build.yaml workflow

* fix the workflow name

* no __metadata__ key

* remember to remove the files

* make linter happy

* check hardware compatibility

* ready to add tests

* update the README

* update the README

f4f11133

30 May, 2025 1 commit

feat: single-file model loading (#413) · 5182f8f8

Muyang Li authored May 29, 2025

* 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

5182f8f8

26 May, 2025 1 commit

fix: convert the unet state_dict to PeFT one to fix the removal LoRA (#402) · b2cc2361

Muyang Li authored May 26, 2025

* start debugging

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

* style: make linter happy

* fix the lpips

b2cc2361

03 May, 2025 1 commit

fix: resolve bug in LoRA reset logic for normalization layers (#347) · 57147358

Muyang Li authored May 03, 2025

* 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

57147358

02 May, 2025 2 commits

test: use CPU offload to save GPU memory in multi-batch test (#344) · 25383861

Muyang Li authored May 02, 2025

* 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

25383861

feat: support FP8 LoRAs (#342) · 336d56ef
Muyang Li authored May 02, 2025
```
* feat: support FP8 LoRAs

* fix the int4 expected lpips
```
336d56ef

01 May, 2025 2 commits

style: upgrade the linter (#339) · 57e50f8d
Muyang Li authored May 01, 2025
```
* style: reformated codes

* style: reformated codes
```
57e50f8d

feat: expose norm1 layer to support TeaCache (#234) · b4d3f50b

Andrea Ferretti authored May 01, 2025



* feat: expose norm1 layer to support TeaCache

* feat: add TeaCache example

* feat: add idx as optional parameter

* chore: rename function

* refactor: move TeaCache decorator into example script

* test: add a test for the combination of Nunchaku with TeaCache

* feat: expose norm1 layer to support TeaCache

* feat: add TeaCache example

* feat: add idx as optional parameter

* chore: rename function

* refactor: move TeaCache decorator into example script

* test: add a test for the combination of Nunchaku with TeaCache

* fix: make tests run on low memory hardware

* fix: ensure that memory is correctly released between tests

* fix: avoid moving pipeline to device prematurely

* gpu memory does not release

* need to figure out a way to get compatible with offloading

* wrap up the teacache

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

b4d3f50b