Skip to content

GitLab

Switch branch/tag
  1. 14 Feb, 2025 1 commit
    • Aryan's avatar
      Module Group Offloading (#10503) · 9a147b82
      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: default avatarSteven 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: default avatarSteven Liu <59462357+stevhliu@users.noreply.github.com>
      9a147b82
  3. 22 Jan, 2025 1 commit
    • Aryan's avatar
      [core] Layerwise Upcasting (#10347) · beacaa55
      Aryan authored 
      

* update

* update

* make style

* remove dynamo disable

* add coauthor
Co-Authored-By: default avatarDhruv Nair <dhruv.nair@gmail.com>

* update

* update

* update

* update mixin

* add some basic tests

* update

* update

* non_blocking

* improvements

* update

* norm.* -> norm

* apply suggestions from review

* add example

* update hook implementation to the latest changes from pyramid attention broadcast

* deinitialize should raise an error

* update doc page

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

* update docs

* update

* refactor

* fix _always_upcast_modules for asym ae and vq_model

* fix lumina embedding forward to not depend on weight dtype

* refactor tests

* add simple lora inference tests

* _always_upcast_modules -> _precision_sensitive_module_patterns

* remove todo comments about review; revert changes to self.dtype in unets because .dtype on ModelMixin should be able to handle fp8 weight case

* check layer dtypes in lora test

* fix UNet1DModelTests::test_layerwise_upcasting_inference

* _precision_sensitive_module_patterns -> _skip_layerwise_casting_patterns based on feedback

* skip test in NCSNppModelTests

* skip tests for AutoencoderTinyTests

* skip tests for AutoencoderOobleckTests

* skip tests for UNet1DModelTests - unsupported pytorch operations

* layerwise_upcasting -> layerwise_casting

* skip tests for UNetRLModelTests; needs next pytorch release for currently unimplemented operation support

* add layerwise fp8 pipeline test

* use xfail

* Apply suggestions from code review
Co-authored-by: default avatarDhruv Nair <dhruv.nair@gmail.com>

* add assertion with fp32 comparison; add tolerance to fp8-fp32 vs fp32-fp32 comparison (required for a few models' test to pass)

* add note about memory consumption on tesla CI runner for failing test

---------
Co-authored-by: default avatarDhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: default avatarSteven Liu <59462357+stevhliu@users.noreply.github.com>
      beacaa55
  5. 09 Jan, 2025 1 commit
  7. 19 Dec, 2024 1 commit
  9. 24 Sep, 2024 1 commit
  11. 12 Sep, 2024 1 commit
  13. 03 Sep, 2024 1 commit
    • Aryan's avatar
      [tests] remove/speedup some low signal tests (#9285) · 24053832
      Aryan authored 
      * remove 2 shapes from SDFunctionTesterMixin::test_vae_tiling

* combine freeu enable/disable test to reduce many inference runs

* remove low signal unet test for signature

* remove low signal embeddings test

* remove low signal progress bar test from PipelineTesterMixin

* combine ip-adapter single and multi tests to save many inferences

* fix broken tests

* Update tests/pipelines/test_pipelines_common.py

* Update tests/pipelines/test_pipelines_common.py

* add progress bar tests
      24053832
  15. 26 Jun, 2024 1 commit
  17. 24 Jun, 2024 1 commit
  19. 13 Jun, 2024 1 commit
  21. 06 Jun, 2024 1 commit
  23. 29 May, 2024 1 commit
  25. 10 May, 2024 1 commit
    • Mark Van Aken's avatar
      #7535 Update FloatTensor type hints to Tensor (#7883) · be4afa0b
      Mark Van Aken authored 
      * find & replace all FloatTensors to Tensor

* apply formatting

* Update torch.FloatTensor to torch.Tensor in the remaining files

* formatting

* Fix the rest of the places where FloatTensor is used as well as in documentation

* formatting

* Update new file from FloatTensor to Tensor
      be4afa0b
  27. 09 May, 2024 2 commits
  29. 02 May, 2024 1 commit
  31. 10 Apr, 2024 2 commits
    • Sayak Paul's avatar
      [Tests] reduce the model sizes in the SD fast tests (#7580) · b2323aa2
      Sayak Paul authored 
      * give it a shot.

* print.

* correct assertion.

* gather results from the rest of the tests.

* change the assertion values where needed.

* remove print statements.
      b2323aa2
    • Sayak Paul's avatar
      [Core] add "balanced" `device_map` support to pipelines (#6857) · 3e4a6bd2
      Sayak Paul authored 
      

* get device <-> component mapping when using multiple gpus.

* condition the device_map bits.

* relax condition

* device_map progress.

* device_map enhancement

* some cleaning up and debugging

* Apply suggestions from code review
Co-authored-by: default avatarMarc Sun <57196510+SunMarc@users.noreply.github.com>

* incorporate suggestions from PR.

* remove multi-gpu condition for now.

* guard check the component -> device mapping

* fix: device_memory variable

* dispatching transformers model to have force_hooks=True

* better guarding for transformers device_map

* introduce support balanced_low_memory and balanced_ultra_low_memory.

* remove device_map patch.

* fix: intermediate variable scoping.

* fix: condition in cpu offload.

* fix: flax class restrictions.

* remove modifications from cpu_offload and model_offload

* incorporate changes.

* add a simple forward pass test

* add: torch_device in get_inputs()

* add: tests

* remove print

* safe-guard to(), model offloading and cpu offloading when balanced is used as a device_map.

* style

* remove .

* safeguard device_map with more checks and remove invalid device_mapping strategues.

* make  a class attribute and adjust tests accordingly.

* fix device_map check

* fix test

* adjust comment

* fix: device_map attribute

* fix: dispatching.

* max_memory test for pipeline

* version guard the tests

* fix guard.

* address review feedback.

* reset_device_map method.

* add: test for reset_hf_device_map

* fix a couple things.

* add reset_device_map() in the error message.

* add tests for checking reset_device_map doesn't have unintended consequences.

* fix reset_device_map and offloading tests.

* create _get_final_device_map utility.

* hf_device_map -> _hf_device_map

* add documentation

* add notes suggested by Marc.

* styling.

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

* move updates within gpu condition.

* other docs related things

* note on ignore a device not specified in .

* provide a suggestion if device mapping errors out.

* fix: typo.

* _hf_device_map -> hf_device_map

* Empty-Commit

* add: example hf_device_map.

---------
Co-authored-by: default avatarMarc Sun <57196510+SunMarc@users.noreply.github.com>
Co-authored-by: default avatarSteven Liu <59462357+stevhliu@users.noreply.github.com>
Co-authored-by: default avatarPedro Cuenca <pedro@huggingface.co>
      3e4a6bd2
  33. 04 Apr, 2024 1 commit
    • UmerHA's avatar
      Skip `test_freeu_enabled ` on MPS (#7570) · 71f49a5d
      UmerHA authored 
      * Skip `test_freeu_enabled ` on MPS

* Small fixes

- import skip_mps correctly
- disable all instances of test_freeu_enabled

* Empty commit to trigger tests

* Empty commit to trigger CI
      71f49a5d
  35. 29 Mar, 2024 2 commits
    • Dhruv Nair's avatar
      Memory clean up on all Slow Tests (#7514) · 4d39b748
      Dhruv Nair authored 
      

* update

* update

---------
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      4d39b748
    • Sayak Paul's avatar
      [Tests] Speed up some fast pipeline tests (#7477) · fac76169
      Sayak Paul authored 
      * speed up test_vae_slicing in animatediff

* speed up test_karras_schedulers_shape for attend and excite.

* style.

* get the static slices out.

* specify torch print options.

* modify

* test run with controlnet

* specify kwarg

* fix: things

* not None

* flatten

* controlnet img2img

* complete controlet sd

* finish more

* finish more

* finish more

* finish more

* finish the final batch

* add cpu check for expected_pipe_slice.

* finish the rest

* remove print

* style

* fix ssd1b controlnet test

* checking ssd1b

* disable the test.

* make the test_ip_adapter_single controlnet test more robust

* fix: simple inpaint

* multi

* disable panorama

* enable again

* panorama is shaky so leave it for now

* remove print

* raise tolerance.
      fac76169
  37. 19 Mar, 2024 1 commit
  39. 14 Mar, 2024 1 commit
    • M. Tolga Cangöz's avatar
      [`Tests`] Update a deprecated parameter in test files and fix several typos (#7277) · 5d848ec0
      M. Tolga Cangöz authored 
      * Add properties and `IPAdapterTesterMixin` tests for `StableDiffusionPanoramaPipeline`

* Fix variable name typo and update comments

* Update deprecated `output_type="numpy"` to "np" in test files

* Discard changes to src/diffusers/pipelines/stable_diffusion_panorama/pipeline_stable_diffusion_panorama.py

* Update test_stable_diffusion_panorama.py

* Update numbers in README.md

* Update get_guidance_scale_embedding method to use timesteps instead of w

* Update number of checkpoints in README.md

* Add type hints and fix var name

* Fix PyTorch's convention for inplace functions

* Fix a typo

* Revert "Fix PyTorch's convention for inplace functions"

This reverts commit 74350cf65b2c9aa77f08bec7937d7a8b13edb509.

* Fix typos

* Indent

* Refactor get_guidance_scale_embedding method in LEditsPPPipelineStableDiffusionXL class
      5d848ec0
  41. 27 Feb, 2024 1 commit
  43. 23 Feb, 2024 1 commit
  45. 08 Feb, 2024 1 commit
  47. 26 Jan, 2024 1 commit
  49. 23 Jan, 2024 3 commits
    • Dhruv Nair's avatar
      [Refactor] Update from single file (#6428) · fee93c81
      Dhruv Nair authored 
      * update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update'

* update

* update

* update

* update

* update

* update

* up

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* up

* update

* update

* update

* update

* update'

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* update

* clean

* update

* update

* clean up

* clean up

* update

* clean

* clean

* update

* updaet

* clean up

* fix docs

* update

* update

* Revert "update"

This reverts commit dbfb8f1ea9c61a2b4e02f926245be2b3d387e577.

* update

* update

* update

* update

* fix controlnet

* fix scheduler

* fix controlnet tests
      fee93c81
    • Sayak Paul's avatar
      [Tests] Test for passing local config file to `from_single_file()` (#6638) · 5308cce9
      Sayak Paul authored 
      make config file local too.
      5308cce9
    • YiYi Xu's avatar
      fix dpm related slow test failure (#6680) · 318556b2
      YiYi Xu authored 
      

fix
Co-authored-by: default avataryiyixuxu <yixu310@gmail,com>
      318556b2
  51. 09 Jan, 2024 1 commit
  53. 26 Dec, 2023 1 commit
  55. 22 Dec, 2023 1 commit
  57. 18 Dec, 2023 1 commit
  59. 16 Dec, 2023 1 commit
  61. 10 Dec, 2023 1 commit
    • Aryan V S's avatar
      IP adapter support for most pipelines (#5900) · 88bdd97c
      Aryan V S authored 
      

* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_upscale.py

* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_attend_and_excite.py

* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_instruct_pix2pix.py

* update tests

* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_panorama.py

* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_sag.py

* support ip-adapter in src/diffusers/pipelines/stable_diffusion_safe/pipeline_stable_diffusion_safe.py

* support ip-adapter in src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_text2img.py

* support ip-adapter in src/diffusers/pipelines/latent_consistency_models/pipeline_latent_consistency_img2img.py

* support ip-adapter in src/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_ldm3d.py

* revert changes to sd_attend_and_excite and sd_upscale

* make style

* fix broken tests

* update ip-adapter implementation to latest

* apply suggestions from review

---------
Co-authored-by: default avatarYiYi Xu <yixu310@gmail.com>
Co-authored-by: default avatarSayak Paul <spsayakpaul@gmail.com>
      88bdd97c
  63. 27 Nov, 2023 1 commit
    • dg845's avatar
      Add Custom Timesteps Support to LCMScheduler and Supported Pipelines (#5874) · 67d07074
      dg845 authored 
      * Add custom timesteps support to LCMScheduler.

* Add custom timesteps support to StableDiffusionPipeline.

* Add custom timesteps support to StableDiffusionXLPipeline.

* Add custom timesteps support to remaining Stable Diffusion pipelines which support LCMScheduler (img2img, inpaint).

* Add custom timesteps support to remaining Stable Diffusion XL pipelines which support LCMScheduler (img2img, inpaint).

* Add custom timesteps support to StableDiffusionControlNetPipeline.

* Add custom timesteps support to T21 Stable Diffusion (XL) Adapters.

* Clean up Stable Diffusion inpaint tests.

* Manually add support for custom timesteps to AltDiffusion pipelines since make fix-copies doesn't appear to work correctly (it deletes the whole pipeline).

* make style

* Refactor pipeline timestep handling into the retrieve_timesteps function.
      67d07074
  65. 21 Nov, 2023 1 commit
  67. 16 Nov, 2023 1 commit
  69. 09 Nov, 2023 1 commit