- 14 Feb, 2025 1 commit
-
-
Aryan authored
* update * fix * non_blocking; handle parameters and buffers * update * Group offloading with cuda stream prefetching (#10516) * cuda stream prefetch * remove breakpoints * update * copy model hook implementation from pab * update; ~very workaround based implementation but it seems to work as expected; needs cleanup and rewrite * more workarounds to make it actually work * cleanup * rewrite * update * make sure to sync current stream before overwriting with pinned params not doing so will lead to erroneous computations on the GPU and cause bad results * better check * update * remove hook implementation to not deal with merge conflict * re-add hook changes * why use more memory when less memory do trick * why still use slightly more memory when less memory do trick * optimise * add model tests * add pipeline tests * update docs * add layernorm and groupnorm * address review comments * improve tests; add docs * improve docs * Apply suggestions from code review Co-authored-by:
Steven Liu <59462357+stevhliu@users.noreply.github.com> * apply suggestions from code review * update tests * apply suggestions from review * enable_group_offloading -> enable_group_offload for naming consistency * raise errors if multiple offloading strategies used; add relevant tests * handle .to() when group offload applied * refactor some repeated code * remove unintentional change from merge conflict * handle .cuda() --------- Co-authored-by:
-
- 13 Feb, 2025 4 commits
-
-
Aryan authored
update
-
Aryan authored
update
-
Aryan authored
* disable peft input autocast * use new peft method name; only disable peft input autocast if submodule layerwise casting active * add test; reference PeftInputAutocastDisableHook in peft docs * add load_lora_weights test * casted -> cast * Update tests/lora/utils.py
-
Fanli Lin authored
fix contiguous bug
-
- 12 Feb, 2025 6 commits
-
-
Eliseu Silva authored
* feat: new community mixture_tiling_sdxl pipeline for SDXL mixture-of-diffusers support * fix use of variable latents to tile_latents * removed references to modules that are not being used in this pipeline * make style, make quality * fixfeat: added _get_crops_coords_list function to pipeline to automatically define ctop,cleft coord to focus on image generation, helps to better harmonize the image and corrects the problem of flattened elements.
-
Daniel Regado authored
* SDXL with MultiControlNetUnionModel --------- Co-authored-by:hlky <hlky@hlky.ac>
-
hlky authored
Fix `use_lu_lambdas` and `use_karras_sigmas` with `beta_schedule=squaredcos_cap_v2` in `DPMSolverMultistepScheduler` (#10740)
-
Dhruv Nair authored
* update * update
-
Thanh Le authored
* Update peft_utils.py * Update peft_utils.py * Update peft_utils.py --------- Co-authored-by:Sayak Paul <spsayakpaul@gmail.com>
-
Aryan authored
* OmniGen model.py * update OmniGenTransformerModel * omnigen pipeline * omnigen pipeline * update omnigen_pipeline * test case for omnigen * update omnigenpipeline * update docs * update docs * offload_transformer * enable_transformer_block_cpu_offload * update docs * reformat * reformat * reformat * update docs * update docs * make style * make style * Update docs/source/en/api/models/omnigen_transformer.md Co-authored-by:
shitao <2906698981@qq.com> Co-authored-by:
-
- 11 Feb, 2025 6 commits
-
-
Le Zhuo authored
* Add support for lumina2 --------- Co-authored-by:
csuhan <hanjiaming@whu.edu.cn> Co-authored-by:
YiYi Xu <yixu310@gmail.com> Co-authored-by:
Aryan <aryan@huggingface.co> Co-authored-by:
-
Eliseu Silva authored
* feat: new community mixture_tiling_sdxl pipeline for SDXL mixture-of-diffusers support * fix use of variable latents to tile_latents * removed references to modules that are not being used in this pipeline * make style, make quality
-
Shitao Xiao authored
* OmniGen model.py * update OmniGenTransformerModel * omnigen pipeline * omnigen pipeline * update omnigen_pipeline * test case for omnigen * update omnigenpipeline * update docs * update docs * offload_transformer * enable_transformer_block_cpu_offload * update docs * reformat * reformat * reformat * update docs * update docs * make style * make style * Update docs/source/en/api/models/omnigen_transformer.md Co-authored-by:
-
Dhruv Nair authored
* update * update
-
Mathias Parger authored
* speedup causal mask generation * fixing hunyuan attn mask test case
-
Sayak Paul authored
* add a test to check if we can train with layerwise casting. * updates * updates * style
-
- 10 Feb, 2025 2 commits
-
-
hlky authored
-
Sayak Paul authored
* fix peft state dict parsing * updates
-
- 07 Feb, 2025 1 commit
-
-
hlky authored
-
- 06 Feb, 2025 3 commits
-
-
hlky authored
-
Leo Jiang authored
* NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * NPU Adaption for Sanna * [bugfix]NPU Adaption for Sanna --------- Co-authored-by:
J石页 <jiangshuo9@h-partners.com> Co-authored-by:
-
suzukimain authored
* Added `auto_load_textual_inversion` and `auto_load_lora_weights` * update README.md * fix * make quality * Fix and `make style`
-
- 05 Feb, 2025 1 commit
-
-
xieofxie authored
Co-authored-by:hualxie <hualxie@microsoft.com>
-
- 04 Feb, 2025 4 commits
-
-
SahilCarterr authored
* Update pipeline_utils.py Added Self in from_pretrained method so inference will correctly recognize pipeline * Use typing_extensions --------- Co-authored-by: -
Parag Ekbote authored
* Fix Doc Tutorial. * Add 4 Notebooks and improve their example scripts.
-
Nicolas authored
-
Sayak Paul authored
* fix dequantization for latest bnb. * smol fixes. * fix type annotation * update peft link * updates
-
- 03 Feb, 2025 2 commits
-
-
Parag Ekbote authored
Fix Doc Tutorial.
-
Ikpreet S Babra authored
-
- 01 Feb, 2025 1 commit
-
-
Vedat Baday authored
feat(training-utils): support device and dtype params in compute_density_for_timestep_sampling (#10699) * feat(training-utils): support device and dtype params in compute_density_for_timestep_sampling * chore: update type hint * refactor: use union for type hint --------- Co-authored-by:
-
- 31 Jan, 2025 2 commits
-
-
Thanh Le authored
* Update train_instruct_pix2pix.py Fix inconsistent random transform in instruct_pix2pix * Update train_instruct_pix2pix_sdxl.py
-
Max Podkorytov authored
* fix enable memory efficient attention on ROCm while calling CK implementation * Update attention_processor.py refactor of picking a set element
-
- 29 Jan, 2025 4 commits
-
-
SahilCarterr authored
fix_shape_error
-
Vedat Baday authored
-
Teriks authored
* support StableDiffusionAdapterPipeline.from_single_file * make style --------- Co-authored-by:
Teriks <Teriks@users.noreply.github.com> Co-authored-by:
-
Sayak Paul authored
update llamatokenizer in hunyuanvideo tests
-
- 28 Jan, 2025 3 commits
-
-
Dimitri Barbot authored
Fix pipeline dtype unexpected change when using SDXL reference community pipelines in float16 mode (#10670) Fix pipeline dtype unexpected change when using SDXL reference community pipelines
-
Sayak Paul authored
* conditionally check if compute capability is met. * log info. * fix condition. * updates * updates * updates * updates
-
Aryan authored
* update * remove unused fn * apply suggestions based on review * update + cleanup 🧹 * more cleanup 🧹 * make fix-copies * update test
-
