Skip to content

GitLab

"test/vscode:/vscode.git/clone" did not exist on "93c3025f935b9dae47ba8b8f78a8003eb3bb1ffd"
Switch branch/tag
  1. 05 Dec, 2025 1 commit
  3. 03 Dec, 2025 2 commits
  5. 17 Oct, 2025 1 commit
  7. 02 Oct, 2025 1 commit
    • Benjamin Bossan's avatar
      FIX Test to ignore warning for enable_lora_hotswap (#12421) · 7242b5ff
      Benjamin Bossan authored 
      I noticed that the test should be for the option check_compiled="ignore"
but it was using check_compiled="warn". This has been fixed, now the
correct argument is passed.

However, the fact that the test passed means that it was incorrect to
begin with. The way that logs are collected does not collect the
logger.warning call here (not sure why). To amend this, I'm now using
assertNoLogs. With this change, the test correctly fails when the wrong
argument is passed.
      7242b5ff
  9. 30 Sep, 2025 1 commit
  11. 29 Sep, 2025 1 commit
  13. 25 Sep, 2025 1 commit
  15. 03 Sep, 2025 1 commit
  17. 28 Aug, 2025 1 commit
  19. 14 Aug, 2025 1 commit
  21. 13 Aug, 2025 1 commit
  23. 11 Aug, 2025 1 commit
  25. 29 Jul, 2025 1 commit
  27. 23 Jul, 2025 1 commit
  29. 22 Jul, 2025 1 commit
  31. 09 Jul, 2025 1 commit
  33. 01 Jul, 2025 1 commit
  35. 26 Jun, 2025 2 commits
  37. 25 Jun, 2025 1 commit
  39. 24 Jun, 2025 1 commit
  41. 23 Jun, 2025 1 commit
  43. 19 Jun, 2025 1 commit
  45. 18 Jun, 2025 2 commits
  47. 13 Jun, 2025 1 commit
  49. 06 Jun, 2025 1 commit
  51. 02 Jun, 2025 1 commit
  53. 26 May, 2025 1 commit
  55. 15 May, 2025 1 commit
  57. 09 May, 2025 1 commit
  59. 28 Apr, 2025 3 commits
  61. 09 Apr, 2025 2 commits
  63. 08 Apr, 2025 2 commits
    • Sayak Paul's avatar
      [feat] implement `record_stream` when using CUDA streams during group offloading (#11081) · 4b27c4a4
      Sayak Paul authored 
      

* implement record_stream for better performance.

* fix

* style.

* merge #11097

* Update src/diffusers/hooks/group_offloading.py
Co-authored-by: default avatarAryan <aryan@huggingface.co>

* fixes

* docstring.

* remaining todos in low_cpu_mem_usage

* tests

* updates to docs.

---------
Co-authored-by: default avatarAryan <aryan@huggingface.co>
      4b27c4a4
    • Benjamin Bossan's avatar
      [LoRA] Implement hot-swapping of LoRA (#9453) · fb544996
      Benjamin Bossan authored 
      * [WIP][LoRA] Implement hot-swapping of LoRA

This PR adds the possibility to hot-swap LoRA adapters. It is WIP.

Description

As of now, users can already load multiple LoRA adapters. They can
offload existing adapters or they can unload them (i.e. delete them).
However, they cannot "hotswap" adapters yet, i.e. substitute the weights
from one LoRA adapter with the weights of another, without the need to
create a separate LoRA adapter.

Generally, hot-swapping may not appear not super useful but when the
model is compiled, it is necessary to prevent recompilation. See #9279
for more context.

Caveats

To hot-swap a LoRA adapter for another, these two adapters should target
exactly the same layers and the "hyper-parameters" of the two adapters
should be identical. For instance, the LoRA alpha has to be the same:
Given that we keep the alpha from the first adapter, the LoRA scaling
would be incorrect for the second adapter otherwise.

Theoretically, we could override the scaling dict with the alpha values
derived from the second adapter's config, but changing the dict will
trigger a guard for recompilation, defeating the main purpose of the
feature.

I also found that compilation flags can have an impact on whether this
works or not. E.g. when passing "reduce-overhead", there will be errors
of the type:

> input name: arg861_1. data pointer changed from 139647332027392 to
139647331054592

I don't know enough about compilation to determine whether this is
problematic or not.

Current state

This is obviously WIP right now to collect feedback and discuss which
direction to take this. If this PR turns out to be useful, the
hot-swapping functions will be added to PEFT itself and can be imported
here (or there is a separate copy in diffusers to avoid the need for a
min PEFT version to use this feature).

Moreover, more tests need to be added to better cover this feature,
although we don't necessarily need tests for the hot-swapping
functionality itself, since those tests will be added to PEFT.

Furthermore, as of now, this is only implemented for the unet. Other
pipeline components have yet to implement this feature.

Finally, it should be properly documented.

I would like to collect feedback on the current state of the PR before
putting more time into finalizing it.

* Reviewer feedback

* Reviewer feedback, adjust test

* Fix, doc

* Make fix

* Fix for possible g++ error

* Add test for recompilation w/o hotswapping

* Make hotswap work

Requires https://github.com/huggingface/peft/pull/2366

More changes to make hotswapping work. Together with the mentioned PEFT
PR, the tests pass for me locally.

List of changes:

- docstring for hotswap
- remove code copied from PEFT, import from PEFT now
- adjustments to PeftAdapterMixin.load_lora_adapter (unfortunately, some
  state dict renaming was necessary, LMK if there is a better solution)
- adjustments to UNet2DConditionLoadersMixin._process_lora: LMK if this
  is even necessary or not, I'm unsure what the overall relationship is
  between this and PeftAdapterMixin.load_lora_adapter
- also in UNet2DConditionLoadersMixin._process_lora, I saw that there is
  no LoRA unloading when loading the adapter fails, so I added it
  there (in line with what happens in PeftAdapterMixin.load_lora_adapter)
- rewritten tests to avoid shelling out, make the test more precise by
  making sure that the outputs align, parametrize it
- also checked the pipeline code mentioned in this comment:
  https://github.com/huggingface/diffusers/pull/9453#issuecomment-2418508871;


  when running this inside the with
  torch._dynamo.config.patch(error_on_recompile=True) context, there is
  no error, so I think hotswapping is now working with pipelines.

* Address reviewer feedback:

- Revert deprecated method
- Fix PEFT doc link to main
- Don't use private function
- Clarify magic numbers
- Add pipeline test

Moreover:
- Extend docstrings
- Extend existing test for outputs != 0
- Extend existing test for wrong adapter name

* Change order of test decorators

parameterized.expand seems to ignore skip decorators if added in last
place (i.e. innermost decorator).

* Split model and pipeline tests

Also increase test coverage by also targeting conv2d layers (support of
which was added recently on the PEFT PR).

* Reviewer feedback: Move decorator to test classes

... instead of having them on each test method.

* Apply suggestions from code review
Co-authored-by: default avatarhlky <hlky@hlky.ac>

* Reviewer feedback: version check, TODO comment

* Add enable_lora_hotswap method

* Reviewer feedback: check _lora_loadable_modules

* Revert changes in unet.py

* Add possibility to ignore enabled at wrong time

* Fix docstrings

* Log possible PEFT error, test

* Raise helpful error if hotswap not supported

I.e. for the text encoder

* Formatting

* More linter

* More ruff

* Doc-builder complaint

* Update docstring:

- mention no text encoder support yet
- make it clear that LoRA is meant
- mention that same adapter name should be passed

* Fix error in docstring

* Update more methods with hotswap argument

- SDXL
- SD3
- Flux

No changes were made to load_lora_into_transformer.

* Add hotswap argument to load_lora_into_transformer

For SD3 and Flux. Use shorter docstring for brevity.

* Extend docstrings

* Add version guards to tests

* Formatting

* Fix LoRA loading call to add prefix=None

See:
https://github.com/huggingface/diffusers/pull/10187#issuecomment-2717571064



* Run make fix-copies

* Add hot swap documentation to the docs

* Apply suggestions from code review
Co-authored-by: default avatarSteven Liu <59462357+stevhliu@users.noreply.github.com>

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
Co-authored-by: default avatarhlky <hlky@hlky.ac>
Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>
Co-authored-by: default avatarSteven Liu <59462357+stevhliu@users.noreply.github.com>
      fb544996
  65. 20 Mar, 2025 1 commit