Nouamane Tazi 9ebaea545f Optimize Stable Diffusion (#371) ...

* initial commit

* make UNet stream capturable

* try to fix noise_pred value

* remove cuda graph and keep NB

* non blocking unet with PNDMScheduler

* make timesteps np arrays for pndm scheduler
because lists don't get formatted to tensors in `self.set_format`

* make max async in pndm

* use channel last format in unet

* avoid moving timesteps device in each unet call

* avoid memcpy op in `get_timestep_embedding`

* add `channels_last` kwarg to `DiffusionPipeline.from_pretrained`

* update TODO

* replace `channels_last` kwarg with `memory_format` for more generality

* revert the channels_last changes to leave it for another PR

* remove non_blocking when moving input ids to device

* remove blocking from all .to() operations at beginning of pipeline

* fix merging

* fix merging

* model can run in other precisions without autocast

* attn refactoring

* Revert "attn refactoring"

This reverts commit 0c70c0e189.

* remove restriction to run conv_norm in fp32

* use `baddbmm` instead of `matmul`for better in attention for better perf

* removing all reshapes to test perf

* Revert "removing all reshapes to test perf"

This reverts commit 006ccb8a8c.

* add shapes comments

* hardcore whats needed for jitting

* Revert "hardcore whats needed for jitting"

This reverts commit 2fa9c698ea.

* Revert "remove restriction to run conv_norm in fp32"

This reverts commit cec592890c.

* revert using baddmm in attention's forward

* cleanup comment

* remove restriction to run conv_norm in fp32. no quality loss was noticed

This reverts commit cc9bc1339c.

* add more optimizations techniques to docs

* Revert "add shapes comments"

This reverts commit 31c58eadb8.

* apply suggestions

* make quality

* apply suggestions

* styling

* `scheduler.timesteps` are now arrays so we dont need .to()

* remove useless .type()

* use mean instead of max in `test_stable_diffusion_inpaint_pipeline_k_lms`

* move scheduler timestamps to correct device if tensors

* add device to `set_timesteps` in LMSD scheduler

* `self.scheduler.set_timesteps` now uses device arg for schedulers that accept it

* quick fix

* styling

* remove kwargs from schedulers `set_timesteps`

* revert to using max in K-LMS inpaint pipeline test

* Revert "`self.scheduler.set_timesteps` now uses device arg for schedulers that accept it"

This reverts commit 00d5a51e5c.

* move timesteps to correct device before loop in SD pipeline

* apply previous fix to other SD pipelines

* UNet now accepts tensor timesteps even on wrong device, to avoid errors
- it shouldnt affect performance if timesteps are alrdy on correct device
- it does slow down performance if they're on the wrong device

* fix pipeline when timesteps are arrays with strides

2022-09-30 09:49:13 +02:00

..

source

Optimize Stable Diffusion (#371)

2022-09-30 09:49:13 +02:00