deepspeedai / deepspeedai/DeepSpeedExamples

[BUG in Stable Diffusion inference] There's an error on CUDAGraph when using deepspeed inference. How to fix it?

Open
#866 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
6.8k
Forks
1.1k
Avg merge
2d 16h
Merged PRs (30d)
1

Description

【Repo Link】:
Stable-Diffusion inference

【The Command used to run】:
deepspeed --num_gpus 1 test-stable-diffusion.py

【Envs】:

RTX 3090
deepspeed 0.12.6
torch 1.13.1
diffusers 0.26.1
triton 2.0.0.dev20221202

【Traceback information】:
image

It seems like the CUDAGraph is not available, which confused me a lot.
Please take time to review the issue and give me some feedback. Appreciate!

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the Stable-Diffusion inference example linked in the issue, especially test-stable-diffusion.py, and reproduce it with the supplied deepspeed command and environment versions. Inspect the linked traceback to determine why CUDAGraph is unavailable during inference; done means identifying a reproducible cause and a verified fix or compatible configuration.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.