Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Integrate deep cache #426

Merged
merged 28 commits into from Dec 19, 2023
Merged

Integrate deep cache #426

merged 28 commits into from Dec 19, 2023

Conversation

clackhan
Copy link
Contributor

@clackhan clackhan commented Dec 14, 2023 •
edited by hjchen2

ComfyUI Node and Example

Node name: ModuleDeepCacheSpeedup

Example workflow:
deepcache onediff workflow

Depending on the new oneflow community edition

cuda 11.8: python3 -m pip install --pre oneflow -f https://oneflow-pro.oss-cn-beijing.aliyuncs.com/branch/community/cu118

cuda12.1: python3 -m pip install --pre oneflow -f https://oneflow-pro.oss-cn-beijing.aliyuncs.com/branch/community/cu121

cuda12.2: python3 -m pip install --pre oneflow -f https://oneflow-pro.oss-cn-beijing.aliyuncs.com/branch/community/cu122

SDXL UNet iter speed

A100

  • 1024 * 1024
SDXL(Pytorch) DeepCache DeepCache with OneDiff
7.79it/s(1x) 16.92it/s(2.17x) 23.58it/s(3.03x)
  • 512 * 512
SDXL(Pytorch) DeepCache DeepCache with OneDiff
22.47it/s(1x) 48.73it/s(2.17x) 54.79it/s(2.44x)

3090

  • 1024 * 1024
SDXL(Pytorch) DeepCache DeepCache with OneDiff
4.01it/s(1x) 8.79it/s(2.19x) 14.11it/s(3.52x)
  • 512 * 512
SDXL(Pytorch) DeepCache DeepCache with OneDiff
13.88it/s(1x) 29.81it/s(2.15x) 43.56it/s(3.14x)

@strint strint changed the base branch from main to dev_optimize_mock_torch December 14, 2023 11:12
clackhan and others added 5 commits December 15, 2023 07:53
@clackhan
add_src_html
0794598
@clackhan
refine_workflow
a573129
@clackhan
remove_blank_file
daefb97
@ccssu
refine mock
3d48a70
@ccssu
refine mock (#428)
6c4a604 
community_add_optimize_mock_torch：
siliconflow/oneflow#55
commit : 7f2b00cb3cff5e1ed50c0e527a30684d26294847
@strint strint marked this pull request as ready for review December 18, 2023 15:50
Base automatically changed from dev_optimize_mock_torch to main December 19, 2023 07:38
@strint strint merged commit 8a35a9e into main Dec 19, 2023
4 checks passed
@strint strint deleted the integrate_deep_cache branch December 19, 2023 10:18
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@strint strint strint approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
3 participants
@clackhan @strint @ccssu