FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

Fix autocast v fp16 + add benchmark config instructions in benchmark.md by eolecvk · Pull Request #11 · LambdaLabsML/lambda-diffusers · GitHub

/ lambda-diffusers Public

Fix autocast v fp16 + add benchmark config instructions in benchmark.md - #11

Draft
eolecvk wants to merge 5 commits into
mainfrom
eole/complete-benchmark-doc
ConversationCommits (5)ChecksFiles changed
Draft

Fix autocast v fp16 + add benchmark config instructions in benchmark.md#11
eolecvk wants to merge 5 commits into
mainfrom
eole/complete-benchmark-doc

Conversation

eolecvk commented Oct 12, 2022 •
edited
Loading

Copy link
Copy Markdown
Contributor
  • Fixed conditional logic when using autocast in benchmark code.
  • Updated diffusers==0.3.0 to diffusers==0.4.2
  • @chuanli11 : Any reason to not include torch and torchvision in the requirements?

Removing autocast does seem to reduce the latency and memory in a big way!
Here is what the new benchmark results for autocast v fp16 look like.

device precision autocast runtime n_samples latency memory
NVIDIA RTX A6000 single False pytorch 1 7.37 7.73
NVIDIA RTX A6000 half True pytorch 1 4.39 4.52
NVIDIA RTX A6000 half False pytorch 1 3.34 3.38
NVIDIA RTX A6000 single False pytorch 2 14.0 9.57
NVIDIA RTX A6000 half True pytorch 2 8.29 8.74
NVIDIA RTX A6000 half False pytorch 2 6.17 4.92
NVIDIA RTX A6000 single False pytorch 4 27.25 18.4
NVIDIA RTX A6000 half True pytorch 4 15.73 11.4
NVIDIA RTX A6000 half False pytorch 4 11.59 8.82

Also added benchmark config instructions in benchmark.md

eolecvk requested a review from chuanli11 October 12, 2022 19:02

chuanli11 commented Oct 12, 2022

Copy link
Copy Markdown
Contributor

@eolecvk seems torch and torchvision are included in the setup.py.

I don't know if @justinpinkney has particular reason for doing it that way.

eolecvk commented Oct 12, 2022

Copy link
Copy Markdown
Contributor Author

@eolecvk seems torch and torchvision are included in the setup.py.

I don't know if @justinpinkney has particular reason for doing it that way.

It's because the original repo was setup that way:
https://github.com/CompVis/stable-diffusion/blob/69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc/setup.py

...but even in their case, they install pytorch and torchvision in conda's environment.yaml:
https://github.com/CompVis/stable-diffusion/blob/69ae4b35e0a0f6ee1af8bb9a5d0016ccb27e36dc/environment.yaml

This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

chuanli11 Awaiting requested review from chuanli11

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

Back | FazBrowse Home | New Git URL