deepspeedai / deepspeedai/DeepSpeed

[Question] How to preshard a model for tensor parallism

Open
#2,379 48 comments 0 reactions 2 assignees View on GitHub

@mrwyattii is already working on this.

Since Feb 17, 2023.

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

Description

Currently we are trying to run inference with pretrained BLOOM model. However, the loading takes very long due to DeepSpeed sharding in runtime. Since there is a pre-sharded version of BLOOM:

microsoft/bloom-deepspeed-inference-fp16

Is that possible to share the script that done the above job or any guidance on how to preshard to speed up loading experience?

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.