Even if the `qweight_type` is one of the `UNQUANTIZED_TYPES`, qweight still has to be "dequantized" because it is stored as an 8-bit tensor. Without doing so, it is therefore a shape mismatch in the following matmul.
Side notes:
- why isn't DIFFUSERS_GGUF_CUDA_KERNELS on by default? It's significantly faster and only used when installed
- https://huggingface.co/Isotr0py/ggml/tree/main/build has no build for torch 2.8 (or the upcoming 2.9). Who can we contact to make such a build?
Co-authored-by: YiYi Xu <yixu310@gmail.com>
* Add ZImageInpaintPipeline
Updated the pipeline structure to include ZImageInpaintPipeline
alongside ZImagePipeline and ZImageImg2ImgPipeline.
Implemented the ZImageInpaintPipeline class for inpainting
tasks, including necessary methods for encoding prompts,
preparing masked latents, and denoising.
Enhanced the auto_pipeline to map the new ZImageInpaintPipeline
for inpainting generation tasks.
Added unit tests for ZImageInpaintPipeline to ensure
functionality and performance.
Updated dummy objects to include ZImageInpaintPipeline for
testing purposes.
* Add documentation and improve test stability for ZImageInpaintPipeline
- Add torch.empty fix for x_pad_token and cap_pad_token in test
- Add # Copied from annotations for encode_prompt methods
- Add documentation with usage example and autodoc directive
* Address PR review feedback for ZImageInpaintPipeline
Add batch size validation and callback handling fixes per review,
using diffusers conventions rather than suggested code verbatim.
* Update src/diffusers/pipelines/z_image/pipeline_z_image_inpaint.py
Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>
* Update src/diffusers/pipelines/z_image/pipeline_z_image_inpaint.py
Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>
* Add input validation and fix XLA support for ZImageInpaintPipeline
- Add missing is_torch_xla_available import for TPU support
- Add xm.mark_step() in denoising loop for proper XLA execution
- Add check_inputs() method for comprehensive input validation
- Call check_inputs() at the start of __call__
Addresses PR review feedback from @asomoza.
* Cleanup
---------
Co-authored-by: Álvaro Somoza <asomoza@users.noreply.github.com>
* add metadata field to input/output param
* refactor mellonparam: move the template outside, add metaclass, define some generic template for custom node
* add from_custom_block
* style
* up up fix
* add mellon guide
* add to toctree
* style
* add mellon_types
* style
* mellon_type -> inpnt_types + output_types
* update doc
* add quant info to components manager
* fix more
* up up
* fix components manager
* update custom block guide
* update
* style
* add a warn for mellon and add new guides to overview
* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update docs/source/en/modular_diffusers/mellon.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* more update on custom block guide
* Update docs/source/en/modular_diffusers/mellon.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* a few mamual
* apply suggestion: turn into bullets
* support define mellon meta with MellonParam directly, and update doc
* add the video
---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: yiyi@huggingface.co <yiyi@ip-26-0-160-103.ec2.internal>
* tag loader_id from Automodel
* style
* load_components by default only load components that are not already loaded
* by default, skip loading the componeneets does not have the repo id
* add a real quick start guide
* Update docs/source/en/modular_diffusers/quickstart.md
* update a bit more
* fix
* Apply suggestions from code review
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update docs/source/en/modular_diffusers/quickstart.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* Update docs/source/en/modular_diffusers/quickstart.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
* update more
* Apply suggestions from code review
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* address more feedbacks: move components amnager earlier, explain blocks vs sub-blocks etc
* more
* remove the link to mellon guide, not exist in this PR yet
---------
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Fix Wan/WanI2V patchification
* Apply style fixes
* Apply suggestions from code review
I agree with you for the idea of using `patch_size` instead. Thanks!😊
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
* Fix logger warning
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: dg845 <58458699+dg845@users.noreply.github.com>
* avoid creating attention masks when there is no padding
* make fix-copies
* torch compile tests
* set all ones mask to none
* fix positional encoding from becoming > 4096
* fix from review
* slice freqs_cis to match the input sequence length
* keep only attenton masking change
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
* Add `WanAnimateTransformer3DModel` to `SINGLE_FILE_LOADABLE_CLASSES`
* Fixed dtype mismatch when loading a single file
* Fixed a bug that results in white noise for generation
* Update dtype check for time embedder - caused white noise output
* Improve code readability
* Optimize dtype handling
Removed unnecessary dtype conversions for timestep and weight.
* Apply style fixes
* Refactor time embedding dtype handling
Adjust time embedding type conversion for compatibility.
* Apply style fixes
* Modify comment for WanTimeTextImageEmbedding class
---------
Co-authored-by: Sam Edwards <sam.edwards1976@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
* up
* up up
* update outputs
* style
* add modular_auto_docstring!
* more auto docstring
* style
* up up up
* more more
* up
* address feedbacks
* add TODO in the description for empty docstring
* refactor based on dhruv's feedback: remove the class method
* add template method
* up
* up up up
* apply auto docstring
* make style
* rmove space in make docstring
* Apply suggestions from code review
* revert change in z
* fix
* Apply style fixes
* include auto-docstring check in the modular ci. (#13004)
* Run ruff format after auto docstring generation
* up
* upup
* upup
* style
---------
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
