alibaba / alibaba/BladeDISC

Diffusion model benchmark

Open
#904 6 comments 2 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
933
Forks
169
PR merge metrics
No merged PRs in 30d

Description

We have support diffusers in https://github.com/alibaba/BladeDISC/issues/867 . This issue tracks performance of all the diffuser pipelines. For the concern of performance, we use BlaDNN to tuning models during runtime.
The following pipelines would be tested:
- [ ] StableDiffusionPipeline
- [ ] runwayml/stable-diffusion-v1-5
- [ ] stabilityai/stable-diffusion-2-1-base
- [ ] StableDiffusionImg2ImgPipeline
- [ ] runwayml/stable-diffusion-v1-5
- [ ] StableDiffusionDepth2ImgPipeline
- [ ] stabilityai/stable-diffusion-2-depth
- [ ] StableDiffusionInpaintPipeline
- [ ] runwayml/stable-diffusion-inpainting
- [ ] AltDiffusionPipeline
- [ ] BAAI/AltDiffusion

Contributor guide

No contributing guide indexed for this repository

Research direction

Review the Diffusers support tracked in issue 867 and the pipeline/model checklist in this issue. Start by determining how each listed pipeline should be benchmarked with BlaDNN runtime tuning, then record performance results for Stable Diffusion and AltDiffusion variants. Done means every checklist entry has been tested and its performance is documented.

Written by the indexing model from the issue text.

Assessment

Tech stack
pytorch
Domain
compilers, machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.