deepspeedai / deepspeedai/DeepSpeed

[BUG]init_inference() fails for diffusers

Open
#4,742 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug inference
Dominant language
Python
Stars
43.1k
Forks
5k
Avg merge
4d 15h
Merged PRs (30d)
112

Description

Describe the bug
Code source: https://github.com/microsoft/DeepSpeedExamples/blob/master/inference/huggingface/stable-diffusion/test-stable-diffusion.py

To Reproduce
I've tried both the latest version, and the requirements.txt version as supplied with the code. Running it through a single gpu this is no problem, however when running it with multiple gpus, it reports an error.

Expected behavior
Supports multi-gpu

Screenshots

20231127084144

Contributor guide

Open the contributing guide

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 inference/huggingface/stable-diffusion/test-stable-diffusion.py and its requirements.txt, then reproduce the reported init_inference() failure on one GPU and multiple GPUs. Inspect the error shown in the issue screenshot and compare the two execution modes. Done means the supplied example runs successfully with multiple GPUs while retaining single-GPU behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
distributed-systems, machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.